Global Application of Regenerative Agriculture: A Review of Definitions and Assessment Approaches

Jayasinghe, Sadeeka L.; Thomas, Dean T.; Anderson, Jonathan P.; Chen, Chao; Macdonald, Ben C. T.

doi:10.3390/su152215941

Abstract

Regenerative agriculture (RA) is an approach to farming pursued globally for sustaining agricultural production and improving ecosystem services and environmental benefits. However, the lack of a standardized definition and limited bioeconomic assessments hinder the understanding and application of RA more broadly. An initial systematic review revealed a wide range of definitions for regenerative agriculture, although it is generally understood as a framework consisting of principles, practices, or outcomes aimed at improving soil health, biodiversity, climate resilience, and ecosystem function. To address existing gaps, we propose a working definition that integrates socioeconomic outcomes and acknowledges the significance of local knowledge and context to complement established scientific knowledge. A second systematic review identified indicators, tools, and models for assessing biophysical and economic aspects of RA. Additionally, a third literature review aimed to identify the potential integration of advanced analytical methods into future assessments, including artificial intelligence and machine learning. Finally, as a case study, we developed a conceptual framework for the evaluation of the bioeconomic outcomes of RA in the mixed farming setting in Australia. This framework advocates a transdisciplinary approach, promoting a comprehensive assessment of RA outcomes through collaboration, integrated data, holistic frameworks, and stakeholder engagement. By defining, evaluating assessment methods, and proposing a pragmatic framework, this review advances the understanding of RA and guides future research to assess the fit of RA practices to defined contexts.

Keywords:

bioeconomic models; framework; indicators; mixed farming; regenerative agriculture; machine learning

1. Introduction

Conventional industrial agriculture has played a vital role in feeding the growing world population [1,2]. This has resulted in enhanced food security, with undernourishment rates dropping globally from 14.7% in 2000 to 9.9% in 2020 [1]. This success was achieved through various advancements, including mechanization, synthetic agrochemicals, improved crop varieties, and intensive practices in monoculture cropping [3,4], and was assisted by distribution chain enhancements. However, the extensive use of synthetic agrochemicals and fossil fuels strains food systems through environmental repercussions such as soil degradation, water pollution, pest resistance, greenhouse gas emissions, and reliance on non-renewable energy sources [3,4]. Furthermore, driven by the projected global population of 8.6 billion by 2030, the intensified practices of conventional industrial agriculture exacerbate resource exploitation and environmental degradation, posing significant sustainability challenges in meeting the surging food demand [5]. This has sparked increased interest in the development of more sustainable farming systems and practices that require reduced synthetic inputs. Regenerative agriculture (RA) is one such farming system that offers the synergistic potential of landscape restoration and biodiversity conservation [6,7]. Despite its potential benefits, adopting RA can be challenged by transition periods, initial costs, yield variability, risk management, economic viability, ambiguous standards, and the need for farmers to acquire new skills [8,9,10]. Understanding and evaluating the performance of RA is, therefore, vital for its widespread adoption.

The global RA market was valued at USD 975.2 million in 2022 and is projected to grow at a compound annual growth rate (CAGR) of 15.9% from 2023 to 2030, surpassing USD $4290.9 million by 2032 [11]. In 2022, North American countries, including the United States, Canada, and Mexico, held the largest market share (37%) of RA. Other leading nations in this sector include the Western European countries, United Kingdom, Germany, and France, as well as Asia–Pacific countries such as India, China, and Australia (Supplementary Figure S1). RA practices offering options to reverse trends in degrading landscapes hold significant potential for the future of global sustainable agriculture. While its basic principles can serve as a foundation for developing more sustainable farming systems worldwide, specific practices, outcomes, and participation levels may vary depending on a country’s resources, infrastructure, and socioeconomic conditions. In developing countries, RA offers solutions to enhance food security and the potential to increase family farm income [12]. Conversely, in developed countries such as the United States, Germany, and the United Kingdom, RA aligns with principles of environmental stewardship aimed at reducing chemical usage, preserving natural resources, and transitioning toward sustainable and carbon-neutral agriculture that are of importance to markets and governments [13,14]. To promote RA, federal policies, knowledge-sharing, certification, infrastructure diversification, farmer support, and research funding are essential.

RA and sustainability are closely linked; however, RA is a holistic land management approach that goes beyond sustainable farming practices. It focuses on restoring soil and ecosystem health, with an emphasis on improving agricultural production functions rather than reverting to its native production status. In contrast, sustainability predominantly seeks to maintain existing systems [15,16], focusing on optimizing the beneficial interactions between soil and plants, reducing external inputs, and embracing ecological farming methods [17,18]. Soil fertility and resilience play a central role in RA, aiming to optimize biogeochemical cycles, enhance disease resistance, and increase productivity while maintaining strong symbiotic soil–plant relationships [19,20]. Additionally, livestock plays a vital role in RA, as rotational grazing patterns can contribute to increased grass production and carbon sequestration in rangelands [21,22]; however, the implementation of RA can vary based on principles, practices, and outcomes [23]. Khangura et al. [6] highlighted that the term “regenerative agriculture” lacks a consensus definition, attributed to individual users defining it broadly according to their specific purposes and contexts. A lack of a globally recognized and clear science-based definition and varying terminology has caused confusion among scholars, farmers, and the public [9]. Establishing a scientific definition is crucial for developing a comprehensive framework that fosters resilient agricultural systems and improves food production.

Transitioning from conventional farming to RA involves addressing competing demands for environmental and economic outcomes in land-use systems [24]. Advanced decision support is necessary for land managers to navigate trade-offs and implement scientifically substantiated landscape changes [25,26]. Essential for robust RA evaluation and expanded business benchmarking, advanced modeling approaches surpass traditional econometrics. Evaluating RA requires considering farm economics, ecological services, and system maintenance, as environmental benefits alone are likely insufficient to motivate many farmers to transition [27]. Comprehensive modeling, integrating indicators, methodologies, bioeconomic models, and advanced analytics (Artificial intelligence (AI) and Machine learning (ML)) can establish an assessment framework for RA [28,29]. However, there is still a lack of research and reviews that thoroughly assess the biophysical and economic aspects. Assessment methods fall into distinct categories: indicators, indicator-based tools, frameworks, ex ante bioeconomic models, surveys, consultations, and participatory tools [30,31,32]. Indicators and tools play roles in evaluating farm sustainability within a framework [33] and guiding decisions [34]. Previous studies of RA primarily relied on positivist scientific methodologies that prioritize biophysical indicators of ecological improvement [35,36]. Therefore, it is vital to explore indicators, tools, and frameworks that enable the evaluation of biophysical and economic dimensions in RA scenarios.

Biophysical and economic models also play a crucial role in representing scenarios, providing information to support decision-making in farming systems, and assessing agricultural practices to accomplish desired goals [37]. These models depict the complex interactions among different components of a farm at different levels, including within certain areas or across multiple areas of a farm and between the biophysical and socioeconomic dimensions [38,39]. Utilizing AI techniques infused with proximal sensing devices (e.g., spatiotemporal imagery, unmanned aerial vehicles) and predictive modeling (e.g., big data, machine learning) enables rapid on-site bioeconomic analysis, supporting the development of context-specific and region-specific models for RA [20]. Existing integrative farm models, such as FarmDESIGN and LiGAPS, can provide insights into the complexity and performance of RA practices [7]. However, these models are limited in their ability to optimize and assess the real effectiveness of soil-based regenerative practices. Field-level models, such as Soil Navigator and the open soil index, consider various soil features but lack a comprehensive assessment of the environmental and socioeconomic implications of farm-level soil management practices [40,41]. The emergence of AI, big data analytics, and machine learning has catalyzed studies on the quantification of grassland biomass and regenerative grazing in many countries using remote sensing technologies [28,29]. Nevertheless, these studies frequently have limited geographical scope, primarily concentrate on agronomic aspects, and tend to overlook economic assessments, disregarding the intricate complexities inherent in the RA system.

The challenges of adopting RA include diverse definitions, lack of consensus on indicators and models, lack of baseline data, limited digital integration, and insufficient locally relevant information and evidence. This review establishes a prospective framework for regenerative farming systems to facilitate the quantitative evaluation of biophysical and economic effects associated with RA interventions. In particular, Australia was suitable as a case study for several reasons; for example, its diverse, mixed farming landscapes facilitate the seamless implementation of regenerative techniques, such as crop–livestock integration, rotational grazing, cover cropping, and agroforestry [24]. Furthermore, the degree of enthusiasm of Australia’s land managers in adopting and implementing RA practices (Figure S1) makes it an operational focal point for this study.

Given the variations in the definition of RA and the limited number of bioeconomic assessments, this review aims to (1) develop a working definition of RA based on a comprehensive assessment of existing definitions; (2) evaluate methods for the biophysical and economic assessment of RA systems (i.e., tools, indicators, models, methodologies, and advanced analytical techniques); and (3) propose a practical framework for assessing the effectiveness of farm-scale regenerative agricultural practices, using mixed farming systems in Australia as a case study, with a focus on economic and biophysical outcomes. Figure 1 illustrates the research questions, objectives, and workflow of this study.

Figure 1. An overview of the research questions, objectives, and main methodology followed in the review. Note: a literature review offers a broad overview of existing knowledge, while a systematic review is a rigorous methodological approach that comprehensively analyzes and synthesizes all available evidence on a specific research question.

2. Materials and Methods

2.1. Search Strategy and Data Compilation

To fulfill the first and second objectives of the review (Figure 1), Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) search techniques were employed (Figure 2). Two search strategies were utilized within the Web of Science (WoS) and Scopus databases to identify relevant research publications addressing (1) the definition of RA and (2) the methods, tools, models, and frameworks used to assess or quantify RA practices or outcomes. Conducting two separate systematic reviews in the same research area was important to address the distinct research questions being considered, each with unique inclusion criteria, search strategies, and data extraction processes. For the first research question, the choice of search terms reflected key concepts and terminology related to RA definitions. Comprehensive search terms, including “Regenerative Agriculture” and “RA”, along with synonyms, were selected. The second research question focused on the assessment methods of biophysical and economic aspects of RA and employed search terms guided by specific indicators, tools, methods, frameworks, and models. Boolean operators (e.g., OR, AND) were effectively employed to combine search terms in both systematic reviews. Additionally, a literature review was conducted to uncover alternative methodologies that could be adopted in the development of a framework for RA, providing a more general overview of the literature as part of the pursuit of the third objective. Approaches taken in each of the reviews are outlined in Figure 1.

Figure 2. PRISMA flow diagrams for systematic reviews illustrating (A) the definition of RA and (B) assessment methods for quantifying its practices or outcomes. Note: Asterisks denote where searches have been broadened by allowing the inclusion of prefixes or suffixes, or other character groups.

2.1.1. RA Definition

Based on the parameters described in Figure 2, an initial search was conducted to find papers where RA was defined. A total of 982 publications on RA from 1985 to early 2023 were found in both databases. There were 240 publications after excluding duplicate records, unreviewed materials, irrelevant materials, and non-English materials. After the records were further filtered based on title and abstract, 142 articles were found to be eligible for full-text screening. After full-text screening, 21 entries were removed because they were irrelevant, unavailable, or duplicates. Only publications that were specifically about RA (n = 121) were included in the systematic review (Figure 2). By employing a snowball approach, which involves examining the reference lists and citations of key papers, a total of eight significant publications on RA were identified. The final sample included a total of 129 papers, 8 of which were from the grey literature (Supplementary Table S1).

In addition to performing a systematic review to accomplish the first objective, we exported the data gathered from the initial literature review to Microsoft Excel for Office 365 MSO (version 2310) and VOSviewer software for supplementary analysis. VOSviewer version 1.6.5 [42] (accessed on 11 February 2023) was utilized to generate co-occurrence density maps based on the relevant keywords extracted from the selected full-text articles. We used information on the frequency of keywords in the formulation of our proposed definition of RA.

2.1.2. RA Biophysical and Economic Analysis

The second literature search identified papers proposing and/or analyzing approaches, frameworks, methods, tools, models, or indicators to measure economic, social, and environment outcomes of RA practices. Few publications directly measured the performance of RA; thus, the search code was revised to include additional concepts such as organic agriculture, sustainable agriculture, and agroecology in addition to RA (Figure 2). The search results covered the literature related to RA from 1985 to February 2023. Out of 1379 publications, 444 peer-reviewed English-language articles were screened for the next step. After excluding irrelevant and duplicate articles and articles with insufficient information on the assessment method, 267 articles were found to be possibly relevant for full-text screening. After a careful review of these articles, only those that focused on (1) assessment based on indicators or metrics to measure sustainability pillars or (2) any framework/model to examine RA practices or scenarios were included (n = 84) (Table S2). Further, the review of 25 recent papers aimed to identify modern methodologies applicable for framework development (Table S3).

2.2. Data Analysis and Review Structure

The initial literature search produced a collection of publications that were subsequently grouped into categories based on different types of RA definitions: (1) principle-oriented, (2) practice-oriented, (3) outcome-oriented, (4) any combination of these types, (5) RA in an Australian context, and (6) no explicit definition (Table S1). The second literature review led to outcomes that were classified into three categories: (1) indicator-based sustainability assessment approaches, (2) tools used in sustainability assessments, and (3) models employed in agriculture that can be applied to assessing RA. Additionally, a literature review was conducted, which identified 15 papers that highlighted modern technologies and assessment methods that could be utilized in developing a framework for RA.

An analysis of the content was conducted using MXAQDA software version 24 (accessed on 12 March 2023), employing an inductive coding process to extract pertinent information from the abstracts of the final dataset [43]. During the process, the full texts of each article were thoroughly reviewed, relevant subjects were identified, and corresponding codes were assigned, such as “principles, practices, outcomes in the first literature search”. The data were organized in multiple tables, including details such as title, authors, country, year of publication, and main findings.

3. Results

3.1. RA Definition

The concept of RA has increasingly surfaced in academic literature [6,8] (Figure S2), and authors have utilized various components when defining and describing it. Accordingly, Figure 3 illustrates the predominant keywords identified through VOSviewer in the selected 129 papers. A total of 103 keywords were categorized into 12 distinct node colors, which grouped terms with similar co-occurrence patterns into clusters. Among them, the 10 most frequently mentioned keywords (nodes) in the studies related to RA or used in defining RA were “RA”, “soil health”, “biodiversity”, “agroecology”, “ecosystem service”, “sustainability”, “carbon sequestration”, “climate change”, “sustainable agriculture”, and “economy” (Figure 3). The results were categorized into different types of RA definitions, considering the focus of the definition, contextual details, and whether the definition was explicit or not. These categories included principle-oriented, practice-oriented, outcome-oriented, combinations of these types, RA in an Australian context, and no explicit definition.

Figure 3. Co-occurrence density visualization of keywords from 240 papers on RA, with a threshold level of two nodes.

3.1.1. Principles-Oriented Definition for RA

Some authors (n = 10) have explained RA through the framework of guiding principles (Figure S3). Francis et al. [44] identified the primary principles of RA as soil fertility, integrated pest control, advancements in plant breeding, and integrated crop–animal systems. Massy [8] aimed to promote five natural cycles: solar energy, water, soil minerals, ecosystem biodiversity, and human social. Brown [45] proposed five important principles: minimizing disturbance, protecting the soil’s surface, fostering diversity, maintaining living roots in the soil, and integrating animals. Various authors have provided insights into RA and its guiding principles; Kamenetzky and Maybury [46] described it as working with nature, while Gremmen [47] highlighted its connection to biomimetic technology. Dahlberg [48] emphasized the shift in health standards and the appreciation for diversity in regenerative systems. Landers et al. [49] identified three conservation agriculture principles: minimal soil disturbance, long-term soil cover, and species diversification. Tittonell et al. [50] focused on soil preservation, empowering farmers, and animal welfare. LaCanne and Lundgren [51] outlined four common principles: reduced tillage, cover cropping, integrating livestock, and enhanced plant diversity.

3.1.2. Practices-Oriented Definition for RA

Some researchers (n = 20) defined RA primarily based on practices (Supplementary Figure S2). For example, Colley et al. [35] emphasized extensive agriculture practices like no-till farming, reduced synthetic chemical usage, rotational grazing, and perennial grasses. Khangura et al. [6], Lal [19], and Cusser et al. [52] highlighted system-based conservation agriculture involving regenerative practices such as no-till farming, cover crops, integrated nutrient and pest management, and crop–tree–animal integration. Burgess et al. [53] defined RA as an annual cropping system that incorporates at least four of these six techniques: crop rotation, cover cropping, organic farming, green manure, no tillage, and composting. Xu, Bhadha [54] and Xu, Amgain [55] mentioned regenerative farming as a popular practice for improving soil health.

Various researchers have often associated RA with organic farming methods that aim to enhance nutrient utilization efficiency by improving soil quality, which reduces reliance on chemical inputs and instead utilizes on-farm resources [44]. Pearson [56], Brown [45], Rhodes [57], and Ikerd [58] emphasized the practice of reducing chemical herbicides and fertilizers for energy cost savings, environmental preservation, and soil biology. Burgess et al. [53] and Pawan and Minkashi [59] described RA as an advanced technique that incorporates organic farming practices. Common practices mentioned in defining RA include mixed farming, reduced tillage, improved crop rotation, the use of manure and compost, minimization of external inputs, and the integration of crop and livestock operations [7,51,60,61,62]. The compatibility of livestock breeds and crops with the local environment is also considered [63].

Elevitch et al. [64] examined connections between popular agroforestry practices and RA, such as alley cropping, forest farming, riparian buffers, silvopasture, and windbreaks. Other researchers also found relevance in windbreaks [60], silvopasture [50], managed grazing [64,65], and grass–clover mixtures [66]. In RA, perennial plants are preferred over annuals in multi-cropping systems [44]. Perennials often have deeper and wider root systems, the architecture of which optimizes access to water and nutrients from deeper soil layers, eliminating the need for fallow periods between growing seasons. These resource-efficient adaptations enable them to thrive without the need for fallow periods, resulting in benefits such as water conservation, reduced soil erosion, decreased nutrient discharge, and carbon sequestration [64,67,68]. RA prioritizes animal manure over synthetic fertilizers and natural pest control over chemicals [56,57]. Minimizing tillage reduces soil disturbance, relying on earthworms to aerate the soil and enhance nutrient distribution [9].

3.1.3. Outcome-Oriented Definitions of RA

Among the identified studies (n = 13), it was evident that descriptions or definitions of RA were focused primarily on outcomes. To provide further insights into our findings, these outcomes were categorized into three groups: (i) environmental, (ii) social, and (iii) economic.

Studies That Focus on Environmental Outcomes

Previous studies have focused on achieving agricultural outcomes in resource and energy management, nutrition, and crop and animal health, aiming to minimize waste, explore synergistic approaches, regenerate resources, and enhance recycling (Supplementary Figure S2) [3,68,69]. According to Giller et al. [23], RA aims to restore soil health, enhance carbon capture, combat climate change, and promote biodiversity. It involves practices to improve soil quality [70,71], minimize tillage [44,51], contribute to fertility [64], and enhance soil health [72]. Studies have explored various aspects of soil health, including biodiversity enhancement [51,66], carbon sequestration [64,65], and organic matter accumulation [57,60] while mitigating soil threats such as erosion and degradation [62]. Overall, RA aims to integrate multiple elements to achieve sustainable outcomes for soil health, water resources, and climate mitigation. Studies on RA also address water supply and quality improvements, such as achieving clean runoff, reducing water shortages, and enhancing water infiltration and holding capacity [62,64]. Additionally, RA is described as having the potential to mitigate climate change through carbon sequestration and reduction of greenhouse gas emissions [19,73].

Studies That Focus on Social Outcomes

The reviewed articles highlighted the significance of investing in various aspects of RA for the social system [48], human health [36,74], interspecies equity, social justice, farm families, social cost, local populations [48,68,75], sustainable food supply [44], reduction of food shortages [62], production of high-nutritional-quality food [64,70], improved animal welfare [35], cultural re-appreciation [76], and social diversity [77].

Studies That Focus on Economic Outcomes

Studies focusing on economic aspects observed that RA aims to contribute to agricultural yields [57], farm profitability [78], soil productivity [44], and political–economic repositioning [76] while also encompassing other economic dimensions and resilience [36,77,79]. For instance, Schreefel et al. [36] defined RA as an agricultural approach that prioritizes soil conservation to regenerate and enhance multiple ecosystem services, aiming to improve not only environmental sustainability but also the social and economic dimensions of sustainable food production.

3.1.4. Other Definitions

A number of definitions and descriptions have been formulated by combining various principles, practices, and outcomes in the context of RA (n = 7). For example, Schoolman [80] discussed practices such as cover cropping, crop rotation, reduced tillage, and biological pest control, along with reduced chemical usage, focusing on practices and outcomes for agricultural output. Brown et al. [15] viewed RA as a philosophical approach, emphasizing principles such as incorporating natural systems, continuous practice evaluation, and on-farm learning. Kenny and Castilla-Rho [81] broadly defined RA as an alternative form of food and fiber production that aims to enhance and restore resilient systems supported by functional ecosystem processes and healthy, organic soils capable of providing various ecosystem services, including soil carbon sequestration and improved water retention. O’Donoghue [10] mentioned that RA improves product quality and resource availability by acknowledging natural complexity and environmental limits. Fenster et al. [82] developed practice-based scoring systems to define RA by ranking farm outcomes.

Gordon et al. [83] mentioned nine discourses related to RA, encompassing both practices (reducing or eliminating the use of synthetic inputs) and outcomes focused on enhancing and restoring holistic, regenerative, resilient systems with functional ecosystem processes and healthy, organic soils capable of providing ecosystem services, including soil carbon sequestration and improved water quality. Sands et al. [8] proposed an anti-colonial definition for RA that intertwines Indigenous principles of Earth nurturing with values such as reciprocity, respect, collective wellbeing, knowledge collaboration, and (re)localization.

3.1.5. RA in an Australian Context

Roberston et al. [25], considering the Australian context, proposed five main characteristics to describe RA: a whole-system approach, adaptation of farming practices based on agroecological circumstances and socioeconomic factors, involvement of non-farmers as key stakeholders, preservation and improvement of natural capital (e.g., soil, water, native species, soil carbon), and integration of indigenous knowledge into existing scientific frameworks. Massy [18] shares his experiences as a nonindigenous Australian sheep farmer exploring regenerative farming practices within the Australian agricultural landscape. According to Massy [18], RA is “ultimately a story about renewing Mother Earth and her systems and our deep co-dependency on these”.

3.1.6. Studies without a Definition

Some of the reviewed papers (n = 77) used the term “regenerative agriculture” without providing a clear definition or description (e.g., [84,85,86]).

3.2. RA Biophysical and Economic Assessment

Based on the findings of the systematic review, this section presents a range of applicable indicators, models, and tools/frameworks for broadacre agriculture. When assessing regenerative farming practices in Australia’s mixed broadacre farming system, it is important to consider various assessment methods (i.e., Table 1, Table 2, Table 3, Table 4 and Table 5) applicable to this context. This approach facilitates a comprehensive assessment, ensuring that the evaluation captures these practices’ diverse biophysical and economic aspects. By exploring different options, the assessment methods can be tailored to the specific context, enabling an understanding of the strengths and limitations of each approach, enhancing the comprehension of the complex relationships involved, and staying updated with methodological advancements. A thorough exploration of indicators, models, and tools/frameworks ultimately enables a more robust and nuanced assessment of regenerative farming practices in Australia’s mixed broadacre farming system. The discussion section further explores potential approaches for bioeconomic modeling in regenerative farming practices, with a particular focus on selecting indicators, models, and tools to assess the biophysical and economic aspects (Table 6).

3.2.1. Indicators

A total of 62 indicators were identified, including biophysical (n = 17), economic (n = 29), and social (n = 16), along with their descriptions, calculation methods, and units (Table 1). Commonly used biophysical indicators include crop, land, soil, water, air, nutrients, and biodiversity-related indicators. In assessing financial performance, widely recognized indicators include net farm income, gross farm income, and return on assets. Farm profitability indicators consist of gross margin, net profit margin, and cost of production. Moreover, various economic indicators are utilized to evaluate viability, stability, productivity, a farm’s resilience, intensification, diversity, independence from external inputs, and processing (Table 1). Economic indicators are typically quantitative, expressed in monetary terms or ratios, although some assessment systems can employ reference scales (Table 1). Table 1 also includes social indicators that are relevant at the farm level, covering aspects such as education, working conditions, quality of life, farmer satisfaction, and the quality of goods.

Table 1. Biophysical, economical, and social indicators applicable to broadacre agriculture.

Dimension	Indicator	Description	Calculation Method	Unit	Ref.
Biophysical	Animal productivity	Output obtained from animal production per unit.	Total output of a specific animal product/quantity of animals or input.	kg/day or year	[87]
	Biodiversity index	Assessment of species diversity and abundance.	Calculated using various formulas, indices, or metrics considering species richness and evenness within the ecosystem (e.g., Simpson diversity index).	Ratio or percentage	[88]
	Crop productivity	Yield of a specific crop per unit of land area.	Yield per unit of land area.	t/ha	[89]
	Cropping index	Intensity of cropping relative to available time.	Total cropped area/total arable land area × 100.	Ratio or percentage	[88]
	Forage quality	Nutritional value and suitability of forage for livestock consumption.	Nutrient content, digestibility, palatability, animal performance, stage of maturity.	Varies	[90]
	GHG emission	Emission of greenhouse gases from agricultural activities.	Varies (e.g., kg CO₂eq).	Measurement of greenhouse gas emissions using standardized methods	[90,91]
	Input productivity	Efficiency of inputs relative to resulting output.	Total output/quantity of input.	AUD/ha	[92]
	Integrated nutrient and pest management	Integrated approach to managing nutrients and pests.	Implementation of practices and strategies that integrate nutrient management and pest control.	Integrated pest management score	[88,89]
	Land productivity	Measure of output or yield from a specific land area.	Total yield of a crop/land area.	t/ha	[92,93]
	Land use pattern	Spatial distribution and arrangement of land use.	Mapping and analysis of land use categories and their spatial arrangement	Land use land cover maps	[93]
	Leaf area index	Information about the density and productivity of vegetation.	Amount of leaf surface area/unit of ground area.	No unit	[94]
	Biological nitrogen fixation	Crops that can fix atmospheric nitrogen that is then available for that crop or subsequent crops.	Amount of atmospheric nitrogen fixed into plant available forms both in-crop and residual nitrogen for the subsequent crop.	kg/ha, ratio or percentage	[95]
	Nutrient balance	Balance between nutrient inputs and outputs.	Nutrient inputs–nutrient outputs–losses).	Varies (e.g., kg/ha)	[93]
	Organic farming practices	Farm enrolment in organic farming practices (part of or the total UL).	Number of organic practices implemented.	Binary/scale	[96]
	Soil erosion	Removal or displacement of topsoil.	Measured using erosion plots, sediment traps, or modeling approaches, index (e.g., revised universal soil loss equation (RUSLE)).	Varies	[88]
	Soil organic matter	Organic material presents in the soil.	Measured through laboratory analysis, determining the weight of organic carbon as a percentage of the total soil weight.	Percentage or weight (Eg., Walkley-Black C × 1.72 = OM)	[97]
	Solid waste disposal	Quantity of the solid waste quantities.	Weight of the solid waste quantities.	kg	[91]
	Water quality	Assessment of the quality of water resources.	Measured through water sampling and analysis for parameters such as pH, dissolved oxygen, nutrient levels, and pollutant concentrations, or index (e.g., water quality index).	Score	[91]
Economics	Adoption index	Measure of the adoption level of specific practices or technologies in agriculture.	Number of farmers adopting the practice or technology/total number of farmers surveyed.	Ratio or percentage	[98]
	Average expected loss	Conditional value at risk (CVaR).	Probability-weighted average loss potential in a particular risk scenario.	Currency (e.g., AUD)	[91]
	Average expected loss	Average amount of loss expected in a specific scenario	Probability-weighted average loss potential in a particular risk scenario.	Currency (e.g., AUD)	[91]
	Capital productivity	Farm income per unit of farm capital (non-land).	Agricultural output/capital investment.	Ratio or percentage	[91]
	Input costs (e.g., fertilizer, herbicide, fungicides, seeds, diesel, etc.)	Expenses incurred for purchasing inputs.	Total cost of purchasing inputs during a specific period.	Currency (e.g., AUD)	[99]
	Cost/benefit ratio of production	Ratio of production costs to benefits derived.	Total production costs/total benefits derived from production activities.	Ratio or percentage	[97]
	Economic stability	Ability of a farm operation to withstand financial shocks	Evaluation of income stability over time or through financial ratios.	Ratio or percentage	[100]
	Equity ratio	Ratio of farm owner’s equity to total farm assets.	Owner’s equity/total farm assets.	Ratio or percentage	[93]
	Farm continuity	Ability of a farm operation to continue functioning.	Evaluation of the farm’s ability to sustain operations over time.	Measure of continuity (scale)	[101]
	Farm resilience	Farm’s capacity to adapt and recover from both short-term disruptions and long-term changes in the agricultural landscape.	Economic resilience, using financial stability score based on debt-to-equity ratio, liquidity ratio, and profitability margins, environmental resilience, e.g., soil health score.	Weighted scores, composite resilience index	[101]
	Farm expansion	Growth or increase in the scale or size of the farm operation.	Increase in the land area, livestock numbers, or production capacity of the farm.	Measure of expansion (scale)	[95]
	Farmer’s risks	Risks and uncertainties faced by farmers in their operations/crop price volatility (price volatility).	Identification and assessment of potential risks and uncertainties in farming activities.	Measure of risk	[96]
	Fertilizer use efficiency	Output of any crop/unit of the nutrient applied under a specified set of soil and climatic conditions.	Kilograms of crop yield per kilogram of applied fertilizer.	(kg/kg)	[88]
	Gross margin	Difference between total revenue and variable costs.	Total revenue–variable costs.	Currency (e.g., AUD)	[102]
	Labor cost	Cost associated with labor inputs in farm operations.	Wages, salaries, and benefits. paid to farm workers and labor-related expenses.	Currency (e.g., AUD)	[93]
	Labor productivity	Farm income per annual work unit (AWU).	Agricultural output/labor input.	$/AWU	[103]
	Land fragmentation	Number of paddock/plots per farm.	Paddock/farm.	hectares, acres, or square meters	[96]
	Machine performance	Capability and reliability of machines in carrying out specific operations.	Varies, e.g., effective field capacity.	ha/hours	[104]
	Net farm income	Income generated from farming operations after deducting costs.	Total revenue from farm operations–total production costs.	Currency (e.g., AUD)	[100,105]
	Off-farm income	Income earned from non-farm sources.	Income generated from activities outside of the farm.	Currency (e.g., AUD)	[89]
	Operating cash flow	Cash flow generated from day-to-day farm operations.	Total cash inflows–total cash outflows.	Currency (e.g., AUD)	[88]
	Operational cost	Total cost associated with ongoing farm operations.	Sum of expenses related to labor, equipment, inputs, maintenance, and other operating activities.	Currency (e.g., AUD)	[93]
	Product prices	Price at which a product or service is sold in the market.	Market-based pricing determined by supply and demand dynamics.	Currency (e.g., AUD)	[88,106]
	Production cost	Total cost incurred in the production of goods or services.	Sum of all direct and indirect costs associated with production activities.	Currency (e.g., AUD)	[106]
	Profitability	Ability of a business to generate profits.	Net income/total revenue.	Ratio or percentage	[107]
	Return on farm asset	Return on investment or assets in the farm operation.	Net farm income/total farm assets.	Ratio or percentage	[108]
	Salary level	Compensation level for farm employees.	Average wage or salary paid to farm workers or employees.	Ratio or percentage	[96]
	Stocking rate	Number of livestock (such as cattle, sheep, or goats) that are maintained per unit of land area.	Dry sheep equivalents per hectare/energy requirement of a dry 50 kg ewe, which is 8.3 MJ ME/head/day.	DSE/ha	[109]
	Total agricultural products	Aggregate value of all agricultural products produced.	Sum of the value of all crops, livestock, and other agricultural products.	Currency (e.g., AUD)	[110]
	Type of employment	Nature or categorization of employment in the farm operation.	Different types of employment arrangements, such as permanent, temporary, full-time, or part-time.	Binary/scale	[96]
Social	Access to resources	Availability and equitable distribution of farm internal and external resources.	Assessment of access to land, water, credit, inputs, technology, and other resources among farmers.	Measure of access or score	[106]
	Age	Age distribution of farmers and agricultural workforce.	Analysis of age demographics among farmers and agricultural workers.	Age distribution or range, farmer’s age (years)	[104]
	Agri-environmental measures	Adoption and implementation of environmental practices.	Farm enrolment in agri-environmental measures (part of or the total utilized land).	Measure of adoption or score	[96]
	Animal welfare and health	Well-being and health of animals in agricultural systems.	Assessment of animal health, care, and welfare practices.	Measure of welfare or score	[107]
	Education	Level of education and educational attainment among farmers.	Assessment of educational qualifications and attainment levels among farmers.	Education level or attainment (years)	[104]
	Effectiveness of extension services	Performance and impact of agricultural extension programs.	Evaluation of extension services based on reach, adoption, and impact of information and interventions.	Measure of effectiveness or score	[111]
	Environment sensitization	Awareness and consciousness of environmental sustainability.	Assessment of farmers’ knowledge and practices related to environmental conservation and sustainability.	Measure of sensitization or score	[96]
	Farmers’ awareness	Knowledge and understanding of farming practices and innovations.	Surveys, interviews, or assessments to measure farmers’ knowledge and awareness of specific agricultural concepts.	Measure of awareness or score	[111]
	Farmer’s satisfaction	Degree of contentment and satisfaction among farmers	Surveys, interviews, or assessments to measure farmers’ satisfaction with their farming activities.	Measure of satisfaction or score	[101]
	Gender ratio	Proportion of male to female individuals in farming	Number of male farmers/number of female farmers.	Ratio or percentage	[111]
	Input self-sufficiency	Ability of a farm to meet its input requirements.	Number of external input/farm size.	Ratio	[93]
	Quality of life	Overall well-being and quality of life of farmers.	Assessment of factors such as income, health, education, housing, and social well-being among farmers.	Measure of quality or score (binary/scale)	[112]
	Quality of products	Level of performance and intended function.	Quality indices.	Binary/scale	[34]
	Social capital	Social networks, relationships, and community connections.	Assessment of social connections, trust, cooperation, and support networks among farmers and stakeholders.	Measure of social capital	[113]
	Total labor	Total number of individuals engaged in farm labor.	Count of all individuals involved in farm-related activities.	Number of individuals	[97,101]
	Working conditions	Quality and safety of working conditions for farm laborers.	Evaluation of factors such as labor rights, occupational safety, and working environment.	Measure of conditions or score	[100]

Note: Some indicators may have overlapping aspects across the categories, as they can have influences on multiple dimensions of broadacre agriculture.

3.2.2. Tools/Framework

The result of the review reveals a diverse range of established tools and frameworks (n = 45) for assessing biophysical and socioeconomic indicators, each with its own scope, context, and limitations (Table 2). Table 2 also presents acronyms used for these methods in the main text of the review. Some sustainability assessment methods adopt a holistic approach, considering economic, environmental, and social factors. Examples of such methodologies include MCDA, SOSTARE, SAFE, SEAMLESS, COSA, AVIBO, RISE, MOTIFS, IDEA, MESMIS, SRP, DLGZertifikat, ISAP, KSNL, MMF, OCIS PG, PG Tool, SDA, SEEbalance, and SPA (Table 2). The assessment levels vary among these methods, and certain tools operate at the product, landscape, or regional level (e.g., SALCAsstain, PSDCIFASA, MMF, SEAMLESS, SIRUS, and SAFA). The broad applicability of SAFE, MOTIFS, RISE, SOSTARE, IDEA, and SOSTARE models is evident in their ability to assess farm-level performance. Many methodologies allow for the use of primary and secondary data sources, and most can utilize either qualitative or quantitative data. However, these tools have limitations, including location specificity (e.g., IDEA, SRP, and DairySAT), the requirement for site- and scale-specific indicators (e.g., MMF, REPRO), industry/enterprise-specific tools (e.g., DairySAT, Fieldprint calculator, and SRP), the need for a large volume of data (e.g., Agri-LCA and IFSC), and their complex nature (e.g., MCDA, MOTIFS, IDEA, and SAFE), which may impede their user-friendliness and broad applicability in diverse agricultural contexts.

Table 2. Tools and frameworks for assessing biophysical and socioeconomic indicators applicable to broadacre agriculture.

Tool/Frameworks	Scope	Geographic Context	Feature/s	Limitation/s	Assessment Level	Reference
Agri-LCA: Agricultural Life Cycle Assessment	Environmental	United Kingdom	Stand-alone models designed to assess environmental impacts of agricultural products/systems, and life cycle perspective.	Data availability challenges, assumptions and simplifications, spatial and temporal variability, limited scope (i.e., environment).	Product, farm, systems, sector levels	[114]
AUI: The agri-environmental indicators	Environmental	Switzerland	Provide information about sudden and undesired changes, which then allows a thorough investigation of the causes.	Transparency of assumptions: description not yet available, assessed via different tools.	Farm level	[114]
AVIBIO (tool derived from the AVIBIO project)	Environmental, economic, and social	France	A tool to assess the sustainability of the organic poultry production chain in France.	Limited to the poultry sector.	Farm level	[115]
CAPRI: the European Commission for Agricultural Policy Analysis	Environmental and economic	European Union	It combines economic and biophysical models to simulate and analyze the effects of policy measures on various aspects of the agricultural sector, including production, trade, land use, and environmental indicators.	Focuses on policy analysis rather than on-farm practices, failing to capture the positive synergies that a better environment brings associated.	Farm/sector level	[116]
COSA: Committee on Sustainability Assessment	Environmental, economic, and social	Developing countries	Considers producer livelihood (revenue, costs, income), risk (diversification, information, credit, volatility, vulnerability), competitiveness (business development, differentiation, efficiency), producer organization (governance, services), perception of economic circumstances.	The procedural environmental consideration is low. Relies on data availability and stakeholder engagement.	Farm level	[114]
DairySAT: Dairy Self-Assessment Tool	Evaluates sustainability of dairy farms	Australia	An environmental self-assessment and action planning tool for Australian dairy farmers.	Data requirements and subjectivity of self-assessment.	Farm level, regional level	[114]
DLGZertifikat/http://www.nachhaltige-landwirtschaft.info/ (accessed on 12 March 2023)	Environmental, economic, and social	Universal	Based on the analysis of indicators from ecology, economy, social affairs, and management. In this way, the sustainability profile of a farm in its entirety or in parts as well as the sustainable production method of food can be demonstrated.	The DLR certificate is valid for two years. The process should be repeated and is time-consuming.	Farm level	[114]
DRAM: Dutch Regionalized Agricultural Model	Environmental and economic	Netherlands-developed, universally applicable.	The objective function of DRAM is to maximizes income from agricultural activities, i.e., total gross margin, under technological and market constraints. It generates product ion volume for a number of crops and animal products as well as manure at the regional level.	No capability to consider the impact of decoupled payments on investments through changes in liquidity, credit, expectations, and off-farm work decisions.	Sector level	[116]
FARMIS: Farm Modeling Information System	Environmental and economic	Germany, Switzerland	Provides a framework for collecting, organizing, and analyzing data related to agricultural systems, including information on farm operations, inputs, outputs, and management practices.	Only process limited farm-specific environmental information.	Sector level	[114]
FESLM: Framework for Evaluation of Sustainable Land Management	Flexible	Global	Compare the performance of a given land use with the objectives of the five pillars of sustainable land management: productivity, security, protection, viability, and acceptability.	It does not attempt to classify sustainability in absolute terms, but simply to indicate, with an acceptable degree of confidence, whether we are on the right track.	Landscape	[114]
Field print calculator: https://www.ideals.illinois.edu/handle/2142/13458 (accessed on 11 March 2023)	Environmental	USA	Measure the environmental impacts of commodity crop production and identify opportunities for continuous improvement.	Limited to specific industries of corn, cotton, rice, wheat, potatoes, and soybean in USA.	Field level	[117]
Framework with 12 indicators	Environmental, economic, and social	Bangladesh	Study of the sustainability of conventional and ecological farming systems. Simple statistical approach to compare the two systems.	Not validated to other regions.	Regional level	[93]
GEMIS: Gesamt-Emissions-Modell Integrierter Systeme	Environmental	Various	Focused on emissions modeling	Only evaluates environmental effects.	Product level	[114]
IDEA: Indicateurs de Durabilité des Exploitations Agricoles	Environmental, economic, and social	France	Consider factors such as land use, water management, biodiversity conservation, energy efficiency, greenhouse gas emissions, soil health, labor conditions, economic viability, and social equity.	Potential subjectivity in the assessment process, reliance on simplified indicators, and a lack of contextual relevance. Restricted to France, Tunisia, Morocco, and Mexico.	Farm level	[118]
IFSC: lllinois Farm Sustainability Calculator	Environmental and economic	USA	Process-dynamic models to determine emissions from soil carbon change through management changes.	Highly depends on user’s input data, based solely on the integration of soil type and the effects of soil type on crop yield.	Farm level	[119]
Indicator-Based Framework	Environmental, economic, and social	Developing countries	Comparison of indicator results with reference values. Proposed set of operational indicators for measuring agricultural sustainability at the farm level in developing countries.	Restricted to developing countries.	Farm level	[111]
Indicator-Based Framework	Environmental and economic	Italy	Simple statistical approach to compare different systems. Assess the economic and environmental performance of cropping systems in animal and arable farms.	Only potential, not actual, environmental impacts are calculated for nutrient and pesticide management. Soil type and weather conditions are implicitly considered.	Farm level	[120]
ISAP: Indicator of Sustainable Agricultural Practice	Environmental, economic, and social	United Kingdom	A total of ISAP score is obtained from four criteria in sustainability, minimizing off-farm inputs, minimizing inputs from non-renewable sources, maximizing use of (knowledge of) natural biological processes, promoting local biodiversity or environmental quality.	Requires data availability and context-specific applicability.	Farm level	[121]
KSNL: Kriteriensystem nachhaltige Landwirtschaft	Environmental, economic, and social	Germany	A tool for identification of avoidable problems (weakness analysis) with sufficient selectivity to meet advisory requirements for precise management optimization and strategic decision-making in German farm businesses.	An evaluation of animal welfare standards is not considered.	Farm level	[114]
MCDA: Multi-Criteria Decision Analysis	Environmental, economic, and social		It provides a simple and cheap but holistic tool to evaluate the degree of sustainability at a farm level. It visualizes the potentials and failures of farm management.	It does not give definitive results/solutions to problems as the results consist of trade-offs among objectives–one area improves while another deteriorates.	Different scale	[122]
MESMIS: Evaluating the Sustainability of Complex Socioenvironmental Systems	Environmental, economic, and social	Mexico and Latin American countries	It aims to establish a cyclical process by integrating evaluation within the decision-making process. It is examined across diverse socioecological contexts to facilitate comparisons and analysis.	Common agendas are needed to examine and improve the theoretical and operational aspects of evaluation.	From farm plot to local villages	[97]
MMF: Multi-scale Methodological Framework	Environmental, economic, and social	Mali	Engage stakeholders in the community, beyond farm owners/managers.	Focuses on peasant systems, requires site- and scale-specific indicators.	Field, farm, landscape/region	[97]
MODAM: Multi-Omics Data and Application	Environmental and economic	Germany	Calculates the economic returns and environmental impacts and runs farm optimizations with a linear programming tool. It can be applied to various agroecological problems with specific applications and adjustments.	Plotting trade-off functions, marginal abatement cost curves or scenario measures can only be calculated, if input–output relationships and the impacts on the environment are known.	Research, Policy advice sector level, farm level	[123]
MOTIFS: Monitoring Tool for Integrated Farm Sustainability	Environmental, economic, and social	Europe	Indicator-based monitoring tool for integrated farm sustainability. Applied in Flemish dairy farms. This method allows a detailed study of sustainability by choosing the most appropriate sustainability indicators.	Highly data dependent. Need to scan readily available data, extended questionnaires, on-farm evaluations by experts and more appropriate for Europe and sector scope.	Farm level	[122]
OCIS PG: Organic Conversion Information Service—Public Good Tool	Environmental, economic, and social	Europe	A simple, measurable, and accessible way to show the public good that accrues through organic farming systems and provide a measurable and quantifiable system of recording the provision of public good over a given time period.	There are issues with regard to intellectual property (IP) and copyright. The tool is for its own charitable and commercial purposes.	Farm level	[114]
PASMA: Positive Agricultural Sector model of Austria	Environmental and economic	Austria	Applicable for the whole sector and not for a representative number of farms only. Evaluates the rural development program on farm income, crop and livestock production, and farm labor at regional and national scales.	It is a regionally disaggregated formal representation of the Austrian agricultural sector.	Sector level	[114]
PG (Public Good) Tool	Environmental, economic, and social	Europe	Combination of available accountancy data, cropping/livestock records, and farmer knowledge.	It has been developed in relation to a particular agri-environment scheme in England.	Farm level	[114]
PSDCIFASA: Problem-oriented Status-Driver Composite Indicator-base Framework of Agricultural Sustainability Assessment	Environmental, economic, social, and governance	Iran	Choose the most appropriate sustainability indicators. Weighting and scoring of indicator results.	Data requirement is high.	Farm/regional level	[114]
RAUMIS: Regional Agricultural and Environmental Information System	Environmental and economic	Germany	Designed for continuous usage in the scope of long-term agricultural and environmental policy impact analyses.	The specification of the regionally most appropriate strategies necessitates a coupling of RAUMIS to hydrological models in order to get closer to the diffuse pollution problem.	Sector level	[114]
REPRO: Hülsbergen (2003)	Environmental and economic	Germany and neighboring countries	A complex balance model used to describe material and energy flows and the ecological and economic assessment of farms. Quantify carbon fluxes and greenhouse gas emissions, energy balances, estimate the risk of soil erosion as well as farm income/value added, profitability of production factors, change in equity capital net investments, & profit.	A number of assumptions needed.	Farm level, product level	[122]
RISE: Response-Inducing Sustainability Evaluation	Environmental, economic, and social	Global	It assesses economic viability, farm management, and requires moderate data.	It is based on 12 indicators only.	Farm Level	[100]
SAFA: Sustainability Assessment of Food and Agriculture Systems	Environmental, economic, social, and governance	Global	Developed by FAO. It supports sustainability management that facilitates progress toward production, processing, and distribution of food and agricultural products.	Guidelines: ongoing, it is in the development process and has been applied in few studies.	Plot, farm, regional level	[122,124]
SAFE: Sustainability Assessment of Farming and the Environment	Environmental, economic, and social	Global	Assessment mechanism to identify, develop, and evaluate agricultural production systems, techniques, and policies that are more sustainable at the local level.	Relies on data availability, and the absence of comprehensive and reliable data can hinder the accuracy.	Parcel/farm/spatial level	[124]
SALCA: Swiss Agricultural Life Cycle Assessment	Environmental	Switzerland	A number of assumptions have been published in reports and publications on the web.	Economic information is not covered, and data needs are high.	Product level	[124]
SALCAsustain: Swiss Agricultural Life Cycle Assessment Method	Environmental and economic	Switzerland	Considers the full agricultural life cycle, including inputs, production, processing, distribution, consumption, and disposal. It assesses greenhouse gas emissions, energy use, land utilization, water consumption, and nutrient flows.	Additional work is needed to adapt the SALCA model, e.g., for soil types, and certain adjustments may have to be made to run on the economic dimensions of other countries.	Farm/regional level	[122]
SDA: Stakeholder-Delphi-Approach	Environmental, economic, and social	Switzerland	Includes face-to-face interviews among regional stakeholders and a consolidating workshop in each case study region.	The accuracy and reliability of outcomes rely on stakeholder participation. Limited sample size and missing responses hinder the ability to make precise assumptions and formulate recommendations.	Sector level	[114]
SEAMLESS/SEAMLESS-IF: System for Environmental and Agricultural Modeling, Linking European Science and Society	Environmental, economic, and social	European countries	It connects model and data components, enabling their flexible reuse and linkage within a software infrastructure. It tackles the challenges of integrated assessment tools by linking micro and macro analysis, reusing standalone model components for field, farm, and market analysis, and addressing the weighting and scoring of indicator results.	Knowledge about important processes or relationships is not always available, which limits the applicability of the method.	Field, farm, region to EU and global	[39]
SEEbalance	Environmental, economic, and social	Global	This is a system based on the ideas and methods of the eco-efficiency analysis that also includes an assessment of the social dimension.	Need to have information about eco-toxicological substances.	Product level	[122]
SILAS: Swiss Agricultural Sectoral Information and Forecasting System	Environmental and economic	Switzerland	It is an optimization model; it chooses the quantities of the activities, such as crops and animals, with the objective of maximizing agricultural sector income.	Limitations of the optimisation model on the supply side, there is no interaction between supply and price developments, which is detrimental to the validity of the forecasts.	Sector level	[114]
SIRIUS: Sustainable Irrigation Water Management and River-Basin Governance: Implementing User-driven Services	Environmental, economic, social, and governance	Global	Assess the sustainability of irrigated agricultural areas in a holistic perspective. Can be applied to assess sustainability of irrigated agricultural systems in very different countries and contexts, at the irrigation perimeter/watershed scale.	It does not have underlying sustainability target values and does not explicitly include absolute reference values for the suggested indicators.	Irrigation perimeter/regional level	[114]
SMART: Sustainability Monitoring and Assessment Routine	Environmental, social, economic, governance	Global	Applicable at all food supply chain levels and includes stakeholder and employee surveys. Consists of a pool of more than 430 indicators for processing and trade and 240 indicators for primary production.	The practical applicability is yet to be tested and evaluated under a diversity of conditions.	Food company level, farm level	[125]
SOSTARE: Analysis of Farm Technical Efficiency and Impacts on Environmental and Economic Sustainability	Environmental and economic	Italy and other European countries	Model is based on a set of indicators, which are aggregated in a stepwise fashion to provide the user with an immediate valuation of a farm’s performance using Weighting and scoring of indicator results weighting and scoring of indicator results.	SOSTARE does not include any social evaluation/no assessment of work conditions.	Farm level	[126]
SPA: Sustainability Potential Analysis	Environmental, economic, and social	Global	Based on the function–structure–context framework. This model integrates energy, material, and financial flows, agent networks, driving forces, and systemic interdependencies.	It does not guarantee a holistic, sustainable development assessment from a systemic perspective.	Regional level	[122]
SRP: Sustainable Rice Platform	Environmental, economic, and social	Thailand	Useful tool for measuring and monitoring the sustainability level of rice cultivation practices. Comparison of indicator results with reference values.	In order to optimize the practical effectiveness of the SRP within a country, it is necessary to develop specific National Interpretation Guidelines. Focuses solely on rice cultivation.	Farm level, landscape level	[114]

3.2.3. Biophysical and Economic Models

Biophysical and economic models provide valuable insights into their capabilities and functionalities, enabling a deeper understanding of their potential applications and benefits across various components, including crop modeling, soil carbon dynamics, biogeochemical cycles, pasture and livestock simulations, economic analysis, and whole farm simulation. An overview of the applications and specific features of the selected biophysical and economic models (n = 28), which are applicable in broadacre mixed crop–livestock farming, is provided in Table 3. APSIM, DSSAT, CropSyst, EPIC, and GPFARM are used extensively in crop modeling; STICS simulates plant growth, water, carbon, and nitrogen fluxes. RothC is a soil carbon simulation model; Biogeochemical cycle models include DayCent, CERES-EGC, and DNDC; Models such as PaSim, EcoMod, SGS Pasture Model, GrazFeed, GrassGro, LINCFARM, and The Hurley Pasture Model focus on simulating pasture and livestock; whole farm-simulation models include IFSM, Dexcel model, FaSSET, FARMAX, UDDER, and MDSM. In terms of broadacre mixed farm modeling in the review results, notable bioeconomic models comprise LUSO, MIDAS, Farmpredict, and FSSIM (Table 3).

3.3. Advanced Analytical Methods Used in Broadacre Agriculture

The utilization of cutting-edge analytical techniques empowers researchers and practitioners to make informed choices based on rigorous data analysis and interpretation. Table 4 presents a diverse range of advanced analytical methods derived from a literature review on broadacre agriculture. These methods include artificial intelligence, big data analytics, machine learning, sensors, mapping technology, and tracking technologies that can be used in the bioeconomic modeling of RA. Table 4 also details the characteristics of these methods, the supportive analytical tools/software used to enhance their functionality, and their applications in agriculture.

Recent studies highlight the extensive use of machine learning in RA [28,29]. To explore its potential in bioeconomic modeling, a comprehensive literature review was conducted. We identified 52 machine learning algorithms, which are presented in Table 5, along with their functionalities and applications in the agricultural domain. Table 6 showcases algorithms that are potentially useful in the bioeconomic modeling of RA. These findings will be further discussed in the Discussion Section.

Table 3. Biophysical and economic models applicable to broadacre agriculture.

Model	Description	Main Modeling Aspect	Features	Ref.
APSIM	The Agricultural Production Systems sIMulator	Crop model	Analyzes the whole-farm system, including crop and pasture sequences, rotations, and livestock. Includes various crop modeling projects, such as soil water and nitrogen balance, nitrogen leaching, growth of arable crops, crop interactions, adaptation to salinity, climate change scenarios, production risk, row configurations for sowing seeds, and gene-environment interactions. Simulations can be run with multiple paddocks with different crops and soil characteristics. Integrates models from various research efforts. Allows users to script custom management procedures, like defining harvest thresholds.	[127]
Yield Prophet	Yield Prophet		A mechanistic model assists farmers in making informed decisions regarding grain management and predicts potential grain yields, biomass, soil water content, and flowering dates.	[128]
DSSAT	Decision Support System for Agrotechnologand Transfer		DSSAT was developed for crop modeling in agronomic research, integrating soil, crop, weather, and management effects. It includes application programs for seasonal, spatial, sequence, and crop rotation analyses. The model assesses economic risks and environmental impacts related to irrigation, fertilizer and nutrient management, climate variability, climate change, soil carbon sequestration, and precision management. DSSAT can predict crop yield, resource dynamics (e.g., water, nitrogen, carbon), environmental impact (e.g., nitrogen leaching), evapotranspiration, and SOM accumulation.	[129]
CropSyst	Cropping Systems Simulation Model		Analyzes the impact of cropping systems management on productivity and the environment. It simulates soil water and nitrogen budgets, crop growth, yield, residue production and decomposition, and erosion. Management options include cultivar selection, crop rotation, irrigation, nitrogen fertilization, diverse tillage operations, and residue management. The model is written in C++.	[130]
EPIC	Environmental Policy Integrated Climate		It can simulate around 80 crops using unique parameter values for each crop. The model predicts changes in soil, water, nutrient, and pesticide movements, as well as crop yields due to management decisions. It also assesses water quality, nitrogen and carbon cycling, climate change impacts, and the effects of atmospheric CO₂.	[131]
STICS	Simulateur mulTIdiscplinaire pour les Cultures Standard	Soil–Crop model	By selecting suitable options and parameter values, the model can simulate diverse plants, from annual crops to perennial grasses or trees. It encompasses plant growth and tracks water, carbon, and nitrogen fluxes. The model evaluates a wide range of management options and their impact on agronomic outputs (such as biomass, grain productivity, and quality) and environmental outcomes (including carbon and nitrogen storage, nitrate leaching, and N₂O emissions).	[132]
RothC	Rothamsted Carbon Model	Carbon model	A specific tool designed for assessing organic C turnover in non-waterlogged topsoil. The model considers the effects of soil type, temperature, moisture content, and plant cover on the turnover process.	[133]
CERES-EGC	Crop Environment REsource Synthesis–Environnement et Grandes Cultures	Biogeochemical model	The model simulates water, C, and N cycles in agro-ecosystems. It predicts crop production and assesses environmental impacts (e.g., N₂O, NO, NH₃, CO₂, NO₃) for various arable crops (e.g., wheat, barley, maize, sorghum, sunflower, pea, sugar-beet, oilseed rape, miscanthus). Crop-specific modules consider plant growth and development coupled with a generic soil sub-model.	[134]
DayCent	Daily time-step version of the Century Model		The biogeochemical model simulates crop growth, soil C dynamics, N leaching, gaseous emissions (N₂O, NO, N₂, NH₃, CH₄, CO₂), and C fluxes (NPP, NEE) in various ecosystems (crop fields, grasslands, forests, savannas). It also incorporates management practices (fertilization, tillage, pruning, cutting, grazing) and external disturbances (fires). The plant growth sub-model considers genetic potential, phenology, nutrient availability, water/temperature stress, and solar radiation (energy biomass conversion factor).	[135]
DNDC	DeNitrification-DeComposition		The model simulates C and N biogeochemistry in agroecosystems, predicting crop growth, soil regimes (temperature and moisture), soil C dynamics, N leaching, and emissions of trace gases (N₂O, NO, N₂, NH₃, CH₄, CO₂). It was expanded in 2012 to include biophysical processes in whole-farm systems.	[136]
PaSim	Pasture Simulation Model	Pasture–livestock simulation model	It is a process-based, grassland-specific ecosystem model that simulates grassland and pasture productivity and GHG emissions to the atmosphere. The model consists of sub-models for grass, animals, microclimate, soil biology, soil physics and management.	[137]
DairyMod	EcoMod (model/modify, observe, design) suite: Collectively termed GrazeMod		The models include modules for pasture growth, grazing animal utilization, animal physiology (including milk production), water and nutrient dynamics, and options for pasture management, irrigation, and fertilizer application. A hypothetical farm can have up to 100 distinct paddocks representing different areas, and EcoMod simulates the spatially diverse return of nutrients within patches.	[138]
EcoMod
SGS Pasture Model
GrazFeed	GRAZPLAN: Decision-Support Systems for Australian Grazing Enterprises		Includes the animal model that details the protein and energy needs for all varieties of sheep and cattle in every physiological condition.	[139]
GrassGro			Simulates a whole grazing operation, linking pasture development to higher-order plant and animal models with local meteorological data, soil qualities, management information, and financial information.	[139]
LINCFARM	Lincoln University Farm Model		The model includes a pasture development module, multiple paddocks, animal mob management, and comprehensive representations of animal growth, lactation, wool, and intake. It simulates various aspects of sheep production systems, including lactation, maintenance, growth (including fat and protein deposition, genetic variation, and wool), pregnancy, and wool production. The model also predicts animal conception rates, considering live weight change before mating.	[140]
The Hurley Pasture Model			The Hurley Pasture Model includes submodules for plants, water and soil/litter, and animals. The plant sub-model accurately simulates carbon, nitrogen, and water cycles in perennial ryegrass and clover pastures, while the water and soil/litter sub-models describe the water cycle, soil and plant water absorption, nitrogen cycling, organic matter turnover, nitrogen fixation, and nutrient leaching. The animal submodule determines the rate of plant tissue removal during grazing. The model also incorporates management processes such as fertilizer application, pasture harvesting, and stocking rate adjustments throughout the year.	[141]
IFSMIFSM	Integrated Farm System Model	Other whole farm-simulation model	Formerly known as DaFOSyM, this model consists of nine major submodules: crop and soil, grazing, machinery, tillage and planting, crop harvest, crop storage, herd and feeding, manure handling, and economic analysis. It simulates nitrogen movement, transformation, and losses in the soil. Pastures can include up to four different species, with grazing replicated every 30 days. The model incorporates simulated dairy and beef animals. The equipment sub-model determines resource consumption rates and efficiency for agricultural machinery operations. Economic impacts are evaluated using whole-farm and partial budgets, comparing the risk or variability caused by weather conditions using specific years’ economic data.	[142]
GPFARM	Great Plains Framework for Agricultural Resource Management		GPFARM expands economic and environmental risk components, replicates systems and settings, and enhances decision-making in farming. It includes modules for surface residues, soil carbon/nitrogen cycles, water flow, crop development, evapotranspiration, water balance, chemical transport, soil erosion, animal and feed production, and weed dynamics. It simulates various crops like winter wheat, corn, sunflower, sorghum, pros millet, and foxtail/hay millet. The animal production module simulates cow-calf operations on natural grasslands with parameter settings for typical cattle breeds.	[131]
Dexcel model	Dexcel Whole Farm Model for Dairy—New Zealand		A comprehensive dairy farm model that integrates various sub-modules and emphasizes whole-farm economics. It considers factors such as weather, soil, pastures, paddocks, animals, decision-making guidelines, and reporting. The model provides information on land characteristics, such as paddock size, available supplements, pasture type, and minimum grazing residual. The model provides information on land characteristics, management practices, and outputs physical performance and economic summaries.	[142]
FaSSET	Farm Assessment Tool		This is divided into two primary components: a simulation module that combines daily temperature data with real farm characteristics and outside impacts, and a planning module that uses linear programming to create management plans for all operations of each component in the farm system. Gross margins are calculated by the economic model using either set prices or a Monte Carlo simulation.	[142,143]
FARMAX	Decision-Support Tool for Pastoral Farmers		FARMAX, based on StockPol, includes a simplified interface for graziers. The farm planning service involves flock and herd structure, as well as seasonal decision-making such as paddock allocation and livestock trading. Build a model of a unique farm system, utilize it to record actual farm performance data, forecast future expectations, and explore unlimited scenarios for potential changes to the farm system.	[142]
UDDER	UDDER farm systems tool		Used to evaluate supplementation strategies for early and late lactation in order to increase milk yields per cow and the farm gross margin and to optimise farm management to maximise gross margin.	[142,144]
MDSM	Moorepark Dairy System Model		A stochastic budgetary simulation model was developed for dairy farms to investigate the effects of various processes on profitability. The model integrates animal inventory, milk supply, feed requirement, land and labor utilization, and economic analysis.	[4]
LUSO	Land Use Sequence Optimiser	Bioeconomic Model	The model incorporates a deterministic, bioeconomic state, and transition model for crop sequences. It is a tool for optimizing land use planning decisions, considering factors such as soil quality, climate, and economic viability. This aims to determine the most efficient and sustainable land use sequence, maximizing productivity while minimizing environmental impacts. It also assesses risks and promotes stakeholder collaboration.	[143]
MIDAS	Model of an Integrated Dryland Agricultural System		A whole-farm model employs linear programming to describe dryland farming, considering factors like soil moisture, rainfall, crop selection, water management, and soil conservation. It evaluates the economic viability of different systems, providing valuable insights into dryland agriculture.	[145]
Farmpredict	Micro-Simulation Model		A data-driven model simulates the impact of climate change on profits of Australian broadacre farms. It combines farm panel data with site-specific weather information to estimate statistical models. It provides detailed estimates of output, revenue, costs, inventories, and profits at the farm level, covering extensive cropping and livestock industries across Australia.	[145]
FSSIM	Farm System SIMulator		Integrates biological and economic aspects, including crop growth, livestock management, input costs, output prices, and profitability. It enables the evaluation of economic viability and sustainability, making it a decision-support tool for farm system analysis.	[146]

Table 4. Advanced analytical techniques used in modern agriculture.

Advanced Analytical Method	Description	Supportive Analytical Tools/Software	Application in Agriculture	References
Big Data Analytics	The process of examining large and complex datasets to uncover patterns, insights, and trends for decision-making.	Apache Hadoop, Apache Spark, Tableau, Power BI, RapidMiner, Google BigQuery, Repositories (i.e., Data lakes—D2D CRC, Loc-I)	Market trend analysis, crop yield prediction, precision farming, and supply-chain optimization.	[147]
Blockchain	A decentralized and transparent digital ledger that securely records and verifies transactions across multiple parties.	Distributed ledger platforms (Python, Java, Ethereum, Hyperledger), smart contracts, IoT integration	Traceability and supply chain management, authentication of organic or regenerative practices, ensuring transparency and fairness in agricultural transactions, fair pricing and payments for farmers, secure sharing of data and transactions among stakeholders, managing and verifying certifications and standards compliance, optimizing payment and settlement processes.	[148]
Computer Vision	A field of study focused on developing algorithms and systems that enable computers to understand and interpret visual information from images or videos.	OpenCV (Python), TensorFlow Object Detection API (Python), ImageJ (Java), DLIB (C++)	Plant counting for yield estimation, fruit grading and sorting, weed detection, and targeted herbicide application, crop health assessment using image analysis, automated livestock monitoring for behavior analysis, tracking invasive species, plant disease detection from images, and land cover classification.	[149]
Data Fusion	The integration and analysis of data from multiple sources to create a more comprehensive and accurate understanding of a phenomenon or situation.	Geographic Information Systems (GIS), Remote Sensing Platforms, Internet of Things (IoT) Platforms, Sensor Fusion Systems, Machine Learning and AI	Integrated crop monitoring using satellite imagery, weather data, and ground-based sensors.	[150]
Deep Learning	A subset of machine learning that utilizes artificial neural networks with multiple layers to learn and extract high-level features from complex data.	TensorFlow (Python), PyTorch (Python), Keras (Python), Caffe (C++), Theano (Python), MXNet (Python), Microsoft Cognitive Toolkit (CNTK), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Generative Adversarial Networks (GANs)	Disease diagnosis, yield prediction, crop classification, anomaly detection, monitoring plant growth and stress, automated fruit and vegetable sorting, animal behavior analysis and recognition.	[151]
Genetic Analysis	The study and analysis of genetic information to understand traits, variations, and relationships within organisms, such as crops or livestock.	Genomic selection, Marker-Assisted Selection (MAS), Genome-Wide Association Studies (GWAS), Next-Generation Sequencing (NGS) technologies.	Marker-assisted breeding, trait selection, disease resistance breeding, and genetic diversity analysis.	[152]
Geographic Information Systems (GIS)	Computer-based systems for capturing, managing, analyzing, and visualizing geospatial data to support decision-making in agriculture.	Geographic Information System (ArcGIS), Quantum Geographic Information System (QGIS), Geographic Resources Analysis Support System (GRASS GIS), Integrated Land and Water Resources Information System (IDRISI), System for Automated Geoscientific Analyses (SAGA GIS)	Soil mapping, land suitability analysis, precision agriculture, and irrigation management.	[153]
Internet of Things (IoT)	A network of interconnected devices embedded with sensors, software, and connectivity to collect and exchange data for monitoring and control purposes.	IoT platforms (e.g., AWS IoT, Azure IoT), sensor networks, actuators, smart irrigation controllers, livestock tracking, Sensors (Python, C++), IoT platforms (Python, C++, Java)	Smart irrigation systems, real-time environmental monitoring, livestock tracking and health monitoring, tracking and monitoring farm assets and equipment, optimizing resource use and energy efficiency, and early detection of equipment malfunctions.	[154]
Machine Learning	The development and application of algorithms and models that enable computers to learn from data and make predictions or decisions without explicit programming.	Random Forest, Support Vector Machines (SVM), Artificial Neural Networks (ANN), Decision Trees, Gradient Boosting, Deep Learning models.	Crop yield prediction, disease detection, pest management, soil nutrient optimization, quality grading of agricultural products, resource allocation optimization, crop rotation recommendations, soil fertility prediction, livestock health monitoring, and disease detection.	[155]
Multi-Criteria Decision Analysis (MCDA)	An approach for evaluating and comparing alternatives based on multiple criteria or factors to support decision-making in agriculture.	Analytical Hierarchy Process (AHP), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), PROMETHEE.	Sustainable farming practices selection, crop variety selection, and resource allocation optimization.	[156]
Natural Language Processing (NLP)	The ability of machines to understand, interpret, and generate human language-enabling tasks such as text analysis, language translation, and sentiment analysis.	NLTK (Python), SpaCy (Python), Gensim (Python), Word2Vec (Python), BERT (Python), TextBlob (Python), IBM Watson Natural Language Understanding, Google Cloud, API, Amazon Comprehend, Aylien	Automated customer support, market sentiment analysis, and weather forecasting interpretation.	[157]
Precision Agriculture	The use of advanced technologies, data analysis, and precise farm management techniques to optimize agricultural practices and resource allocation.	Global Positioning System/Global Navigation Satellite System (GPS/GNSS), remote sensing (Python, C++), variable rate technology (Python, C++, Java), GIS software (Python, Java), FarmLens, Agremo, FieldX, SST Software	Variable rate application of fertilizers and pesticides, site-specific irrigation management, precision planting and seeding, prescription maps for optimizing resource use, monitoring crop health and growth variability, remote sensing-based crop stress detection, soil mapping and nutrient management, spatial analysis for farm planning and optimization.	[158]
Predictive Analytics	The use of historical data, statistical algorithms, and machine learning techniques to make predictions and forecasts about future events or trends.	Data mining tools (Python, R), statistical modeling software (R, SAS, SPSS), regression models, time series analysis, Regression models, Time series analysis, Gaussian processes, Ensemble methods, Long Short-Term Memory (LSTM) networks.	Predicting crop yields, optimizing planting schedules, irrigation management, disease and pest risk assessment and management, weather event forecasting, market demand prediction, optimizing supply chain management, financial analysis and risk assessment for agricultural investments.	[158]
Remote Sensing	The acquisition and interpretation of data from remote platforms, such as satellites or drones, to monitor and analyze agricultural landscapes and crop health.	Satellite imagery (e.g., Landsat, Sentinel, MODIS, Planet), Unmanned Aerial Vehicles (UAVs) or Drones (DJI Phantom, Parrot Sequoia, MicaSense RedEdge), hyperspectral sensors (Headwall Photonics, SPECIM Aisa), aerial imagery. Cloud platforms, NDVI vegetation indices, Image processing RS software (e.g., ENVI, ERDAS)	Crop health assessment, soil moisture analysis, land use mapping, irrigation management, yield estimation.	[152]
Robotics and Automation	The use of robotic systems and automation technologies to perform agricultural tasks, increase efficiency, and improve productivity in farming operations.	Autonomous drones (Python, C++), robotic arms (C++, Python), automated machinery (C++, Python), autonomous vehicles (C++, Python), Robot Operating System (ROS), Robotic Farming Simulator (RFSim), FarmBot	Autonomous harvesting, robotic weeding, precision planting and seeding, crop monitoring and data collection using drones, automated irrigation systems, smart sensing for livestock management and monitoring, automated feeding systems, autonomous farm machinery for field operations, and autonomous pest and disease control.	[159]
Sensor Technologies	The deployment of various sensors, such as soil moisture sensors, weather sensors, and imaging sensors, to collect real-time data for monitoring and analysis purposes.	Soil moisture sensors, weather stations, multispectral sensors, pH and EC sensors, sap flow sensors, temperature, and humidity sensors.	Collects real-time data on soil conditions, weather parameters, and crop health for informed decision-making.	[159]
Sentiment Analysis	The process of analyzing and determining the sentiment, emotion, or opinion expressed in text or speech data often used for understanding public perception or feedback.	Social media analytics tools (Brandwatch, Hootsuite), text mining platforms (Lexalytics, Semantria)	Analysis of consumer preferences and sentiment towards agricultural products, identifying market trends, monitoring brand reputation, and improving marketing and advertising strategies.	[160]

Table 5. Machine learning algorithms used in agricultural applications.

ML Algorithm	Functionality (Descriptive Analytics)	Application	Reference
Adaptive-Neuro Fuzzy Inference Systems (ANFIS)	Utilizes fuzzy logic and neural networks	Crop yield prediction	[161]
	Combines fuzzy logic and neural networks	Soil classification	[162]
	Integrates fuzzy logic and neural networks	Crop disease diagnosis	[163]
	Applies fuzzy logic and neural networks	Irrigation management	[161]
Artificial Neural Networks (ANN)	Neural network	Crop yield prediction	[164]
		Soil property prediction, soil classification	[165]
		Irrigation scheduling, water demand forecasting	[155]
		Nutrient recommendation, yield optimization	[166]
		Pest and disease identification, yield prediction	[167]
		Livestock growth prediction, milk production	[168]
		Farm revenue prediction, machinery maintenance cost, economic modeling	[169]
		Weather forecasting, extreme event prediction	[170]
Association Rule Mining	Discovering patterns in data	Identifying crop rotation patterns	[171]
Bagging	Ensemble learning	Crop disease diagnosis	[172]
Bagging	Ensemble learning	Crop yield prediction, model averaging	[173]
Bayesian Belief Network (BBN)	Probabilistic modeling	Weather prediction, irrigation optimization, etc.	[146]
Bayesian Networks (BN)	Probabilistic modeling	Crop management, precision agriculture, etc.	[174]
		Crop water requirement prediction, uncertainty analysis	[175]
		Nutrient requirement prediction, uncertainty analysis	[176]
		Crop rotation modeling, decision support	[177]
		Farm risk assessment, decision analysis	[178,179]
Boosting	Ensemble learning	Crop yield prediction, model boosting	[180]
Back-Propagation Network (BPN)	Neural network	Crop yield prediction, weed detection, etc.	[181]
Classification and Regression Trees (CART)	Decision trees	Crop classification, yield prediction, etc.	[182]
Chi-Square Automatic Interaction Detector (CHAID)	Decision trees	Crop yield analysis, soil quality assessment, etc.	[183]
Clustering Algorithms (e.g., K-means, DBSCAN)	Grouping similar data points	Customer segmentation, farm classification	[184]
Convolutional Neural Networks (CNN)	Deep learning, image analysis	Crop disease detection, yield estimation	[185]
		Pest and disease image recognition, object detection	[172]
		Weed image recognition, weed segmentation	[185]
	Convolutional neural network	Weather image analysis and identification, cloud classification	[185]
Convolutional LSTM (ConvLSTM)	Spatiotemporal modeling	Crop phenology analysis, yield prediction	[186]
Counter propagation (CP)	Neural network	Crop clustering, yield forecasting, etc.	[187]
Deep Boltzmann Machine (DBM)	Generative model	Crop phenotype analysis, genomic prediction, etc.	[188]
Deep Belief Network (DBN)	Deep learning	Crop yield prediction, disease diagnosis, etc.	[189]
Decision Trees (e.g., CART, CHAID)	Classification and regression	Crop classification, pest and disease detection	[190]
		Crop yield prediction, feature importance	[191]
		Soil property prediction, soil classification	[182]
		Crop water requirement estimation, decision making	[182]
		Nutrient recommendation, crop response prediction	[192]
		Pest and disease detection, decision support	[193]
		Animal disease diagnosis, decision support	[182]
		Crop rotation decision support	[194]
		Yield prediction, crop selection, decision support	[193]
		Farm management decision support, risk analysis	[182,195]
Deep Learning Models	Neural networks	Weed detection, weed species classification	[196]
Deep Neural Networks (DNN)	Deep learning	Crop yield prediction, plant phenotyping, etc.	[197]
Extreme Learning Machines (ELM)	Feedforward neural network	Weather prediction, precipitation modeling	[198]
	Efficient learning algorithm	Crop classification, yield estimation, etc.	[199]
	Neural network	Soil property prediction, efficient learning	[200]
Ensemble Learning	Combination of multiple models	Pest and disease classification, ensemble decision-making	[201]
Fuzzy Logic	Approximate reasoning	Livestock management	[202]
		Crop rotation planning	[203]
		Expert systems for farm management	[204]
Genetic Algorithms (GA)	Optimization and search	Irrigation scheduling, parameter optimization	[205]
		Nutrient management optimization, parameter tuning	[152]
		Pest management optimization, parameter tuning	[205]
		Weed management optimization, control strategies	[206]
		Livestock management optimization, parameter tuning	[205]
		Optimal crop rotation planning, genetic diversity	[205]
		Farm management optimization, resource allocation	[205]
		Portfolio optimization, risk analysis	[205]
Gradient Boosting Machines (GBM)	Ensemble learning	Weather risk analysis, extreme event forecasting	[207]
Genetic Algorithms (GA)	Optimization and search	Crop yield optimization, crop rotation planning	[205]
Gaussian Mixture Models (GMM)	Probabilistic modeling	Weed detection, weed clustering	[208]
Gaussian Mixture Models (GMM)	Probabilistic modeling	Livestock grouping, anomaly detection	[208]
Gaussian Naive Bayes (GNB)	Probabilistic modeling	Pest and disease classification, weed detection	[209]
Gaussian Processes (GP)	Probabilistic modeling	Weather uncertainty estimation, risk analysis	[210]
Gaussian Process Regression (GPR)	Bayesian non-parametric regression	Crop yield prediction, yield variability	[211]
		Soil property prediction, uncertainty estimation	[211,212]
		Nutrient deficiency prediction, uncertainty estimation	[211]
Hidden Markov Models (HMM)	Sequential data modeling	Animal behavior detection, pest and disease spread analysis	[213,214]
	Probabilistic modeling	Animal behavior analysis, anomaly detection	[215]
		Crop rotation prediction, anomaly detection	[214]
		Price volatility analysis, market trend prediction	[214]
		Weather state modeling, hidden pattern recognition	[214]
Image Processing Techniques	Image analysis and feature extraction	Weed detection, weed segmentation	[216]
K-Nearest Neighbors (KNN)	Instance-based learning	Crop yield prediction, data imputation	[217]
		Soil property prediction, soil classification	[217,218]
		Crop water requirement estimation, water stress detection	[219]
		Nutrient deficiency detection, soil nutrient mapping	[220]
		Pest and disease detection, weed classification	[172]
		Weed detection, weed species classification	[217]
		Animal classification, anomaly detection	[217,221]
Linear Regression	Regression analysis	Crop yield forecasting, resource allocation, price prediction, cost analysis, trend analysis	[222]
Linear Regression	Classification analysis	Farm loan default prediction, risk assessment	[223]
Long Short-Term Memory (LSTM)	Recurrent neural network	Soil moisture	[224]
		Crop yield prediction, time series analysis	[225]
		Weather time series prediction, rainfall forecasting	[226]
Markov Decision Processes (MDP)	Sequential decision-making	Dynamic farm planning, risk management	[227]
Multi Layer Perceptron (MLP)	Neural network	Crop yield prediction, yield optimization	[168]
Multiple Linear Regression (MLR)	Regression	Crop yield prediction, input-output analysis	[222]
Multiple Linear Regression (MLR)	Regression	Soil property prediction, correlation analysis	[222]
Multi-Objective Optimization Algorithms	Optimization	Trade-off analysis in irrigation management	[228]
Multivariate Analysis	Statistical analysis	Data exploration, pattern recognition	[229]
Naive Bayes	Probabilistic modeling	Weed classification, weed species identification	[209]
Naive Bayes Classifier	Probabilistic classification	Weed detection, pest and disease classification	[230]
Particle Swarm Optimization (PSO)	Optimization and search	Parameter optimization, crop yield optimization	[231]
Principal Component Analysis (PCA)	Dimensionality reduction	Feature extraction, soil data visualization	[232]
Partial Least Squares Regression (PLSR)	Regression	Soil property prediction, latent variable analysis	[233]
Random Forest (RF)	Ensemble learning	Crop yield prediction, pest and disease detection	[234]
Reinforcement Learning	Sequential decision-making	Optimal irrigation control, resource allocation	[235]
		Optimal nutrient management strategies	[165]
		Pest control, optimal pesticide application	[155]
		Optimal feeding management, behavior control	[235]
		Optimal crop rotation strategies, resource allocation	[235]
		Optimal resource allocation, machinery scheduling	[236]
		Optimal farm investment, risk management	[235]
Random Forest (RF)	Ensemble learning	Crop yield prediction, feature importance	[166]
		Soil property prediction, feature importance	[234]
		Irrigation scheduling, water use efficiency	[237]
		Nutrient recommendation, feature selection	[237]
		Pest, disease & weed classification, feature selection	[238]
		Disease prediction, animal behavior analysis	[234]
		Crop rotation planning, yield prediction	[239]
		Crop price forecasting, risk modeling	[240]
		Weather prediction, risk assessment	[234]
Recurrent Neural Networks (RNN)	Recurrent neural network	Weather time series analysis, temperature forecasting	[241]
Support Vector Machines (SVM)	Classification and regression	Crop disease and pest detection, weed classification	[242]
		Crop water stress detection, irrigation optimization	[243]
		Nutrient deficiency detection	[244]
		Pest and disease detection, weed classification	[245]
		Animal classification, health monitoring	[242]
		Crop rotation optimization, Crop classification, anomaly detection, yield prediction	[239]
		Market trend analysis, credit scoring	[242]
		Weather pattern recognition, risk analysis	[242]
Support Vector Regression (SVR)	Regression	Crop yield prediction, yield stability	[246]
		Soil property prediction, soil quality assessment	[247]
		Nutrient recommendation, nutrient uptake modeling	[248]
Transfer Learning	Knowledge transfer from pre-trained models	Crop disease detection, weed classification, animal behavior detection	[249]

Table 6. Potential indicators, tools, and models for RA assessment in Australian mixed broadacre farming, categorized by biophysical and economic focus.

Dimension	Indicators	Tools/Framework	Models	Advanced Analytical Methods
Biophysical	Soil physical properties (e.g., texture, soil moisture content, water holding capacity, soil compaction), chemical properties (e.g., pH, soil nutrient levels N, P, K), soil organic matter, soil organic carbon), and biological properties (e.g., soil microbial activity, microbial diversity, nitrogen mineralization, and soil respiration). Crop biomass, leaf area index (LAI), plant height, crop growth stage, cropping index, crop productivity, nutrient content in plants, pest and disease incidence, weed density, plant diversity (species richness and evenness), biodiversity index livestock productivity (e.g., weight gain, milk production), animal health and disease incidence, stocking rate, grazing intensity, forage quality, carbon footprint, greenhouse gas emissions, water use efficiency, water holding capacity, irrigation efficiency, fertilizer use efficiency, pesticide use, and residue levels, integrated nutrient and pest management, land use pattern, organic farming practices.	Agri-LCA: Life Cycle Assessment (LCA), GEMIS: Gesamt-Emissions-Modell Integrierter Systeme, ISAP: Indicator of Sustainable Agricultural Practice, MOTIFS: Monitoring tool for integrated farm sustainability, SALCA: Swiss Agricultural Life Cycle Assessment method, SALCAsustain: Swiss Agricultural Life Cycle Assessment method, SPA: Sustainability Potential Analysis ISAP; Indicator of Sustainable Agricultural Practice.	APSIM: Agricultural Production Systems Simulator, APSIM-Wheat: APSIM model specifically designed for wheat crops, CERES: Crop Estimation through Resource and Environment Synthesis, CERES-EGC: Crop Environment Resource Synthesis–Energy, Greenhouse gases, and Carbon, CropSyst: Crop System Simulation Model, DNDC: DeNitrification DeComposition, DSSAT: Decision Support System for Agrotechnology Transfer, EPIC: Environmental Policy Integrated Climate, FASSET (Farm System Simulator), GPFARM: Generalized Plant and Food Agricultural Resource Model, GrassGro: Grassland Growth Model, GrazFeed: Grazing and Feed Management Decision Support System, LINCFARM: Linked Indicator Farm Model, STICS: Simulateur mulTIdisciplinaire pour les Cultures Standard, The Hurley Pasture Model: A pasture simulation model developed by the Hurley Pasture Research Group at Lincoln University, New Zealand	Big Data analytics, Blockchain technology, Computer vision techniques, Data fusion, Internet of Things (IoT), Geographic Information Systems (GIS), Remote sensing (RS), MCDA: Multi-Criteria Decision Analysis Machine Learning Algorithms ANFIS: Adaptive-Neuro Fuzzy Inference Systems, ANN: Artificial Neural Networks, BN: Bayesian Networks, Clustering Algorithms (K-means, DBSCAN), CNN: Convolutional Neural Networks, LSTM: Long Short-Term Memory, RNN: Recurrent Neural Networks, RF: Random Forest
Economical	Production cost, product prices, gross farm income, net farm income, return on investment (ROI), net present value (NPV), total agricultural products, cost/benefit ratio of production, equity ratio, land productivity, input productivity, capital productivity, labor productivity, stocking rate, off-farm income, cost for fertilizer, profitability, economic stability, gross margin, return on farm asset, adoption index, machine performance, operating cash flow, operational cost, labor cost, land fragmentation, farmer’s risks, average expected loss, expenditure on external inputs, Conditional values-at-risk (CVaR).	CAPRI: Common Agricultural Policy Regionalized Impact, FARMIS; Farm Modeling Information System, PASMA; positive agricultural sector model of Austria, IFSC; lllinois Farm Sustainability Calculator.	Farmpredict: A farm management and optimization tool, FSSIM: Farm Simulation for Sustainability Impact Assessment, LUSO: Land Use Sequence Optimiser, MIDAS: Model of an Integrated Dryland Agricultural System

Note: Some models, tools, or frameworks are grouped based on their primary focus, even though their elements can be classified under any biophysical and economical category.

4. Discussion

4.1. Defining RA: Key Elements and Perspectives

Our review revealed that RA has gained considerable attention as an approach that goes beyond sustainability, with keywords indicating soil health, biodiversity, and agroecology being major research foci within the field. The presence of keywords related to carbon sequestration, climate change, and sustainable agriculture indicates a growing interest in investigating the environmental impact of RA. Additionally, the inclusion of keywords like sustainability and economy emphasizes the holistic approach and broader implications of RA, extending beyond ecological aspects.

Our systematic review shows that RA has been loosely and variously defined, which provides some indication of principles (9%), practices (16%), outcomes (10%), or combined dimensions (5%). A significant portion of articles do not provide a clear definition (60%), possibly due to its challenging nature or the authors’ uncertainty. It is important to note that RA is not a specific practice but rather an ethos focused on sustainable techniques, encompassing a spectrum that ranges from foundational beliefs to well-validated practices [83].

Our results further highlight that the concept of RA includes fundamental principles such as understanding the farm-specific context (including local environment, local land use, and topography), reducing synthetic inputs, integrating livestock, supporting soil fertility, and mimicking natural processes [250]. Common practices associated with RA include reducing external inputs, using cover crops, supporting roots year-round, and minimizing tillage. Many publications focus on how RA interacts with the environment, including soil, air, water, and agricultural outcomes. While there are overlaps among principles and practices, the principles are generally more universal and can be achieved by combining multiple practices. Our findings indicate that the general definition of RA emphasizes outcomes rather than specific principles and practices. For example, Wilson et al. [75] proposed that RA is outcome-focused and context-specific, allowing for the use of multiple practices based on desired results and individual circumstances. However, some definitions overlook contextual evidence when linking practices to outcomes, which is a limitation. Additionally, our findings highlighted the absence of socioeconomic components in many outcome-based definitions in research articles. This may be because traditionally, RA has been focused on nature-positive outcomes rather than a clear economic narrative [9]. RA is characterized by distinct narratives focused on the relationship between humans and nature, separate from industrial-productivist agriculture [83,251].

Within Australia’s broadacre agriculture industry, there is an increasing interest in implementing RA practices to enhance land productivity, increase its value, and preserve natural capital [25]. The process of defining and adopting RA practices necessitates the establishment of context-specific definitions that effectively capture the essence of RA, thus maximizing its potential benefits. Two studies have described the RA context in Australia, highlighting the importance of integrating indigenous knowledge of the landscape and the application of economic frameworks to assess natural capital [21], as well as viewing RA as the transformative mechanism for the restoration of Earth systems with new approaches, rather than sustaining current systems [14]. The limited number of Australian studies highlights the need for further work in the realm of RA in this context.

Having a broad range of definitions creates uncertainty, which hinders researchers’ ability to evaluate claims and impacts policy formulation [252]. Moreover, the ambiguity surrounding the term can mislead consumers and enable unethical commercial promotion (e.g., green-washing) [9]. While previous studies have presented a wide range of definitions for RA, it is generally understood as a framework consisting of principles, practices, or outcomes aimed at improving soil health, biodiversity, climate resilience, ecosystem function, and socioeconomic outcomes. We positioned RA as a transdisciplinary approach, which is a perspective supported by previous studies [8,25,32]. We propose extending the definition to recognize the importance of integrating the knowledge of local landholders and indigenous people with established scientific knowledge. As such, we propose the following definition. “RA is an agricultural and transdisciplinary approach that integrates local and indigenous knowledge of landscapes, as well as their management, with established scientific knowledge. It combines a range of adoptable principles with context-specific practices, focusing on soil conservation as the initial step to restore soil health, enhance ecosystem functions, and promote improved socioeconomic outcomes”. This definition recognizes the significance of diverse perspectives and promotes a transdisciplinary approach.

4.2. Biophysical and Economic Assessment of RA

Global food and fiber production is facing a number of challenges associated with changes in climate and sustainability expectations from markets. RA pertains not only to food production but also extends to the provision of source materials for various industrial processes. To assess the potential role of RA to improve environmental sustainability while maintaining food productivity and enterprise profitability, and hence long-term viability, a framework of tools and models is required to enable assessment of the applicability of individual practices to local environments. Our study has identified a wide range of tools relevant to the assessment of RA practices. This section discusses an integrated paradigm of the potential indicators, tools, frameworks, models, artificial intelligence, machine learning and other data-driven approaches (detailed in Table 6) that can be used in the bioeconomic modeling of RA scenarios.

4.2.1. Potential Indicators for Assessing RA

To contextualize RA, we selected prospective indicators from previous research (i.e., Table 1) that are practical and applicable for measuring RA within the context of mixed farming in Australia. Accordingly, this study identified a range of biophysical indicators of systems function, including soil, crop, livestock, and biodiversity indicators. Soil-related indicators play a pivotal role in assessing RA in two main ways. First, our research highlights the prominent focus of RA on soil conservation, which is consistent with previous studies [6,36]. Second, when implementing RA practices in Australian mixed farming systems, attention should be given to restoring soil health due to the predominantly coarse-textured and inherently low soil carbon nature of Australian soils [145]. Therefore, key soil properties, such as physical properties (e.g., texture, soil moisture content, water holding capacity), chemical properties (e.g., pH, soil nutrient levels, soil organic matter, soil organic carbon), and biological properties (e.g., soil microbial activity, microbial diversity, nitrogen mineralization, and soil respiration), have been chosen as valuable indicators for assessing the effectiveness of regenerative practices in improving soil health and quality (Table 6). These indicators are also supported by previous studies [6,253]. Crop biomass, crop rotation, leaf area index (LAI), and plant height provide insights into crop growth and productivity, aiding grazing and forage management [254]. Assessing forage quality determines the nutritional value, aiding balanced diets and optimizing livestock productivity [90]. Rotational grazing and livestock productivity gauge the efficiency of mixed crop–livestock systems, serving as key indicators in evaluating RA systems and enabling adjustments for optimal performance [255,256]. Biodiversity indicators encompass plant diversity, habitat quality, and pollinator abundance, enabling the evaluation of ecosystem services conservation and enhancement within the mixed crop–livestock regenerative system [34,257]. Indicators related to land use and land cover management, carbon sequestration, and greenhouse gas emissions can significantly impact the evaluating of the effectiveness of RA practices in mixed farming, aligning with previous research [258,259,260]. The important economic indicators used in mixed farming in Australia include farm profitability (e.g., gross farm income, net farm income, ROI, NPV), production costs and efficiency (e.g., cost/benefit ratio, cost for fertilizer, operational cost), productivity (e.g., land productivity, input productivity, capital productivity, stocking rate), and risk and resilience (e.g., farmer’s risk, average expected loss, conditional value-at-risk (CVaR)) [96,261]. Accordingly, these indicators were selected as potential economic indicators for assessing RA in terms of profitability, productivity, efficiency, sustainability, and risk management within mixed farming systems in Australia. For instance, CvaR can serve as an indicator of risk management by quantifying downside risk in crop yield predictions within agricultural systems modeling. Unlike measures such as standard deviation, CVaR focuses on business outcomes in the poorest 20% of seasons, making it more relevant for farmers. It offers clear definitions, meaningful units, and mathematical coherence [262]. Selecting and validating these indicators to form a user-friendly assessment metric requires an integrated approach involving research, expert knowledge, and stakeholder involvement [128].

4.2.2. Potential Tools/Frameworks for Assessing RA

There are potential biophysical and economic tools that contribute to the assessment of RA in mixed farming systems in Australia. For instance, the Agri-LCA tool can be employed to evaluate the environmental impacts of RA practices associated with crop and livestock production systems. This tool was applied in a previous delta life cycle assessment (LCA) by Colley et al. [35] to evaluate the effects of RA on an Australian sheep farming system. The Field Print Calculator can be used to measure the environmental impact of RA practices on specific crop production, including wheat, corn, soybean, and cotton. It takes into account factors such as water usage, energy consumption, and fertilizer application. Tools like GEMIS can be utilized to quantify emissions generated by mixed farming systems, whereas ISAP can be used to measure the sustainability of RA practices, including nutrient management, integrated pest management, and fertilizer use. Tools such as MOTIFS and SALCAsustain can serve as monitoring tools to assess the sustainability of crop–livestock integration at the farm level [114]. DairySAT, designed specifically for assessing the environmental aspects of the Austrian dairy sector [114], has limited applicability to all RA scenarios in mixed farming. However, in some cases, RA dairy production may utilize RA-derived inputs (e.g., feed grains produced in RA broadacre farming businesses), which provides an avenue for value-adding to products and managing the supply chain (Rob Hetherington, personal communication, 24 October 2023). To make their potential applicable in RA, various tools can be utilized to analyze the economic aspects of mixed farming systems. For instance, CAPRI can be employed to analyze market prices, subsidies, and trade flows [116]. FARMIS integrates data and models to analyze financial indicators, cost analysis, and profitability of mixed farming systems. IFSC can assess the economic performance at the farm level. Additionally, PASMA evaluates the economic impacts of agricultural practices on input costs, production levels, and market conditions. However, integrating these tools into local RA farming contexts in Australia’s mixed farming systems can be challenging and time-consuming due to their complexity. Hence, the application of an appropriate assessment framework becomes vital when evaluating RA scenarios within specific contexts and purposes.

4.2.3. Potential Biophysical and Economic Models for Assessing RA

The choice of models for assessing bioeconomic RA scenarios in mixed farming in the Australian context was made with careful consideration of their strengths, applicability, and capabilities. A key consideration was to consider existing modeling frameworks that are used for systems evaluation of traditional mixed farming scenarios. We specifically considered models developed to precisely and effectively represent key components such as crops, soil, pasture, livestock, and farm economics. These models should present the best option to simulate the complex biophysical and economic processes and interactions within mixed farming systems [131,139,145]. We took into account their capabilities in providing comprehensive analyses that canoutperform the time-consuming process of using multiple statistical steps [122]. We also focused on bioeconomic models with a well-established track record and published validation for simulating the bioeconomic performance of traditional mixed farming in the Australian context.

Well-known biophysical models, such as APSIM, CROPSYST, EPIC, STICS, and DSSAT, can be used to simulate processes in cropping systems, including crop yield, crop-soil dynamics, and crop phenological stages. However, compatibility issues have been identified among different models [129]. RothC, designed for assessing organic carbon turnover in non-waterlogged topsoil, shows potential for measuring the effect of RA on carbon sequestration. Biogeochemical models such as CERES-EGC, DayCent, and DNDC can provide insights into nutrient cycling in mixed farming systems. WFM, AusFarm, LINCFARM, The Hurley Pasture Model, GrassFeed, and GrassGro can be utilized as pasture–livestock simulation models in mixed farming settings, and they have been validated with experimental data from farming systems [261,262,263]. Among them, the GRAZPLAN pasture simulation model is widely utilized in Australia for research purposes and supporting producer decisions [262].

LUSO, MIDAS, Farmpredict, and FSSIM are valuable tools for economic analysis in Australian mixed farming [144,264], making them suitable for assessing the economic aspects of RA scenarios. LUSO is a bioeconomic model applied in analyzing the economic impact of various land use strategies and sequences. It enables researchers to evaluate profitability and productivity by considering factors such as crop rotation, pasture management, and resource allocation. LUSO takes into account weed disease and nutrient cycling models, as well as nitrogen supply to crops and pastures in successive years. Key outputs from the LUSO model include sequential crop impacts on yields, profitability, and financial risk [144,265]. MIDAS facilitates the assessment of economic viability and sustainability in dryland mixed farming systems, considering water availability, crop yields, input costs, and market conditions [266]. Farmpredict provides insights into optimizing resource allocation, input usage, and production planning to enhance profitability in Australian mixed farming. It empowers farmers to make informed decisions regarding crop selection, livestock management, and input investments based on economic analysis. FSSIM contributes to economic evaluation by assessing the financial implications of sustainable practices, such as resource-efficient technologies, conservation measures, and renewable energy integration.

Integrating biophysical and economic models with crop–livestock systems is important in representing broadacre farming in Australia. In Australia’s mixed farming context, models such as APSIM and the GRAZPLAN suite are useful for assuring profitability and resilience [142]. In particular, APSIM and GRAZPLAN can be combined within AusFarm, an agro-ecosystem modeling environment [139], to simulate daily interactions among climate, soil, plants, and animals in mixed farming. Limited use of biophysical or bioeconomic models to assess complex RA systems, such as the Soil Navigator (SN) and FarmDESIGN models, has been reported [267]. In a case study conducted by Schreefel et al. [37] on a Dutch dairy farm, SN and FarmDESIGN were employed to investigate and optimize the selection of regenerative goals and soil management practices. However, there is a lack of comprehensive research in Australia regarding overall farm outcomes, specifically farm profits, in the context of RA in broadacre farms [267]. Farm profits are a key component in assessing the benefits associated with transitioning to RA, and have a strong influence on farmers’ responses [51]. Existing studies evaluating broadacre agriculture scenarios have predominantly relied on process-based models, which have limitations in terms of their spatial coverage and ability to accurately capture farmers’ decision-making processes. Therefore, to ensure that economic evaluations can be more widely applied, the application of new analytical methods such as AI and ML may be needed to overcome some limitations and improve the flexibility of these models.

4.3. Advanced Analytical Methods Used in Broadacre Agriculture

There are many applications of advanced analytical methods that have been identified in our study, and their application in RA is also emerging [20]. Therefore, this review explored the potential utilization of artificial intelligence and machine learning in the bioeconomic assessment of RA within a mixed farming context.

Big data analytics, in combination with data lakes, incorporates data from diverse sources such as soil sensors, weather stations, satellite imagery, and historical crop records. This data is processed, filtered, and visualized through interactive dashboards, charts, heatmaps, and other graphical tools to reveal trends, anomalies, and patterns in broadacre agricultural data, enabling comprehensive analysis [147]. This has the potential to inform decision points, such as optimizing nutrient management schedules, identifying yield-limiting factors, and improving resource management [147]. These techniques are applicable to the case study of RA assessment in mixed farming in Australia. Furthermore, Blockchain technology ensures transparency and security in supply chains, enabling the traceability of the provenance of products from RA [148]. It is a decentralized, fixed ledger with data from producers, suppliers, logistics, manufacturing, quality control, distribution, and even consumers, supported by IoT devices, such as sensors and radio-frequency identification (RFID) tags. This technology can assist with traceability, reward systems, data collection, supply chain efficiency, and accountability, as well as in areas like crop insurance and carbon farming [268]. It has the potential to be employed in the bioeconomic modeling process by furnishing precise information on the origin and quality of products produced within RA farming systems.

Computer vision techniques, including deep learning models and robotics, contribute to the early detection of diseases and pests, reducing pesticide usage and minimizing environmental impact [149]. This is achieved through the acquisition of images of crops or animals, which are subsequently analyzed using deep-learning models to identify patterns indicative of the presence of diseases or pests. These techniques benefit mixed farming practices. Data fusion, by combining information from diverse sources, enhances modeling efforts in the bioeconomic assessment of RA. The data fusion methods can include missing-data methods, deep learning models, and other statistical techniques [152]. This will help to enable development of accurate and robust models to evaluate the economic and environmental performance of different RA practices. Geographic information systems (GIS) and remote sensing (RS) aid in crop monitoring, land use planning, yield estimation, soil mapping, fertility management, vegetation and biomass assessment [153]. For example, Ogungbuyi et al. [28] used machine learning and satellite imagery for remote small-scale pasture management in Australia, focusing on RA to enhance pasture productivity and reduce bare ground exposure. Their study involved biomass sampling of various pasture types (i.e., wallaby grass, kangaroo grass, Phalaris, and cocksfoot) and employed machine learning with Sentinel-2 imagery to estimate biomass. Their results demonstrated the potential of machine learning for managing small-scale pasture biomass via satellite imagery. Incorporating GIS and RS data into bioeconomic models allows for the assessment of the economic and environmental implications of spatially explicit management decisions.

The Internet of Things (IoT) facilitates real-time data collection [154], enabling precise monitoring of environmental conditions and optimized farming practices. The IoT can be effectively utilized in RA practices that integrate mixed farming. Previous studies provide compelling evidence of the effectiveness of the blockchain-assisted IoT framework in smart livestock farming [154] and could potentially assist with traceability of the RA credentials of produce through a supply chain. IoT sensors can collect data on soil moisture, temperature, livestock health, grazing behavior, and other environmental factors. This data can be used to optimize RA practices, particularly irrigation and fertilization, resulting in reduced water and fertilizer usage while also improving crop yields and soil health [168]. Multi-criteria decision analysis (MCDA) methodologies offer valuable assistance in assessing the economic viability of various farming practices [156]. For instance, it assists farmers in choosing the most profitable crops, animals, and productive lands by weighing criteria such as climate, market demand, and resource requirements, as indicated by previous literature [156,268]. RA practitioners can make informed decisions that prioritize sustainability, soil health, biodiversity, and economic viability. This structured approach helps them select the most appropriate practices and technologies to achieve RA outcomes while considering multiple criteria and their relative importance.

Machine learning algorithms leverage historical data to predict pest outbreaks and disease epidemics, enabling proactive measures and efficient management in mixed farming systems [155]. These algorithms are beneficial in data analysis, pattern recognition, predictive modeling, optimization, decision support, risk assessment and management, real-time monitoring, and adaptive management [20]. Therefore, integrating machine learning algorithms with real-time data streams such as weather data, crop and livestock sensor data, and market information has the potential to improve the bioeconomic modeling of RA scenarios. These techniques possess the capability to analyze complex data, identify patterns, make predictions, and optimize decision-making processes. For instance, adaptive-neuro fuzzy inference systems (ANFIS) combine fuzzy logic and neural networks [161], enabling the modeling of intricate and often non-linear relationships among a multitude of factors (e.g., soil health, climate conditions, biodiversity, and economic aspects) within bioeconomic systems. ANFIS effectively captures numerical information (e.g., temperature, rainfall) and linguistic terms (e.g., “favorable”, “low-risk”), making it valuable for modeling uncertain and imprecise data associated with RA systems. Artificial neural networks (ANN) learn from historical data and uncover hidden patterns [155]. ANN finds applications in predicting crop yields, market prices, and resource allocation based on input variables and historical data. For example, ANN has been used to predict crop yields in Saudi Arabia by using the multi layer perceptron (MLP) model to predict future values for different crop yields, such as potatoes, rice, sorghum, and wheat [269]. Association rule mining identifies relationships and associations in large datasets [171], assisting in the recognition of patterns in agricultural practices. Bayesian networks (BN) capture uncertainties and dependencies between factors [146]. More accurate predictions and decision analysis can be achieved through the use of BN. For example, a BN model is utilized to estimate the probability of organic farms exiting the sector. This model assists in identifying the key factors that influence the sustainability of organic farming in Italy, including farm size, soil quality, access to markets, and government support [270]. Clustering algorithms, like K-means and DBSCAN, segment agricultural data into meaningful groups [184], facilitating the identification of distinct farming practices and consumer preferences. Deep learning models, including convolutional neural networks (CNN), long short-term memory (LSTM), and recurrent neural networks (RNN), excel in processing complex sequential and spatial data [192]. These models find applications in image recognition, time series analysis, and natural language processing, enhancing understanding and prediction outcomes. Random forest (RF) is utilized to analyze the impact of factors on economic performance, such as identifying influential variables affecting profitability or determining the significance of different farming practices [234].

4.4. Recommendations for Evaluating RA Scenarios in the Australian Context

To address the growing interest in the application of RA, we have proposed a conceptual framework tailored to analyzing RA systems in the context of mixed farming in Australia. This RA approach sets itself apart from conventional industrial agriculture through its transdisciplinary and whole-system approach, desired outcomes, stakeholder engagement, responsible natural capital management, and integration of knowledge systems [128]. In a transdisciplinary research context, to accomplish this objective, an integrative approach will be employed, involving interviews with a diverse regional expert panel comprising farmers, advisers, and researchers. Identifying key application areas, such as the initial steps involved in implementing RA and interventions with demonstrated success, can offer valuable guiding principles for transdisciplinary research. Directly collecting information on RA farms and management practices will inform the selection of case studies for modeling scenarios and provide insights into the characteristics of RA practices implemented in mixed farms, including soil types and land use patterns, as well as crop, pasture, and animal management practices. It involves assessing the effects of these practices on land and resource utilization, developing methods to quantify nutrient and water balance at the whole-system level, and evaluating weather’s impact on system performance. Additionally, we will gain farmer insights into the trade-offs (biophysical or socioeconomic) associated with the use of different crop pasture rotations and N supply. In this process, we ascertain the practical applicability of the working definition developed in the present review for RA on farms in Australia. Data can be collected from various sources, including field data, big data (e.g., cloud computing, data lake, data fusion, IoTs), satellite data (e.g., Landsat, Sentinel, MODIS), real-time data, SILO products, and indices (i.e., crop, livestock, and soil). However, to effectively develop and apply an analytical framework suited to Australian broadacre farming, there is a clear need for transdisciplinary teams that bring together domain specialists and specialist data analytics expertise.

The integration of process-based models with artificial intelligence (AI) and machine learning (ML) techniques enables enhanced decision-making, as evidenced by studies evaluating crop rotations [271] and yield prediction [173]. Open-source software, such as R and Python, offers flexibility in combining different methods or models for a hybrid quantification of RA.

A conceptual modeling framework offers a structured, transdisciplinary approach to assess the biophysical and economic performance of diverse RA scenarios in Australian mixed farming enterprises. The framework includes submodules for crop, soil, pasture, livestock, and farm economics and integrates remote sensing and machine learning algorithms (Figure 4). The APSIM crop model is utilized to estimate yield potential for various crops commonly found in mixed farming systems in Australia. Soil characterization follows the recommended procedures, incorporating visual assessments and involving experts when field assessments are impractical. Soil properties, soil water, and nitrogen settings in the APSIM model can be parameterized using observable data, enabling simulations. Mapping of soil organic carbon (SOC), an important indicator of soil quality, is accomplished through advanced remote sensing and machine learning techniques [23,36]. Digital maps of SOC and predictions of changes pre- and post-RA adoption can be generated by combining field data, soil and vegetation indices from Landsat satellite images, topographic indices, and soil survey information followed by in-field studies to provide ground-truthing across soils/environments. Random forest (RF) generalized boosted regression models (GBM), and neural networks (e.g., CNN, ANN) can be integrated into pipelines to improve the accuracy of remote soil organic carbon (SOC) mapping.

Figure 4. A conceptual modeling framework for evaluating RA scenarios in the Australian context.

The implications of RA interventions in pasture and ruminant livestock systems can be modeled using simulation software such as GrassGro (version 3.2.2), which has been described earlier. This commercial ruminant model integrates biophysical, managerial, and financial components within the farm system. Economic analysis utilizes gross margin analysis based on expense and revenue data from the Australian Bureau of Statistics, with a particular focus on assessing whether there is sufficient sensitivity in the data to allow for adjustments related to RA practices. These simulations capture both biophysical and economic performance on a daily time step over a specified period (e.g., 30 years). The LUSO or MIDAS biophysical models can be used to link the APSIM and GrassGro models, enabling analysis of the farm system’s overall economic performance [272]. Outside the assessment of economic performance, tools such asIDEA and SAFE may be applied to measure the social performance of a farm.

Integrating biophysical and economic models, remote sensing, big data analysis, and machine learning is complex and requires expertise in multiple domains. Collaborating with experts in agricultural science, remote sensing, and data analysis enhances the quality and robustness of RA estimations and recommendations. A strong mathematical and statistical foundation is essential for comprehensive analysis in this RA scenario assessment framework. Mathematical methods, such as Markov chain Monte Carlo (MCMC), K-Means clustering, and ANN, are available for Bayesian analysis, clustering, and predictive modeling, respectively. In addition, statistical methodologies, including regression analysis and spatial analysis, may further enhance the assessment. For instance, applying geostatistical methods like Kriging to interpolate spatial data and to generate maps of RA-related variables, such as soil organic carbon levels. Regression analysis is used to facilitate the quantification of nutrient and water balance, modeling of crop yields, spatial mapping of soil properties, and the clustering of farms based on RA practices. These tools are particularly valuable when dealing with complex, non-linear models and uncertain input data. Principal component analysis (PCA) can identify key variables and reduce data dimensionality, thus simplifying RA modeling. Support vector machines (SVM) have the potential to predict whether farming practices align with regenerative principles through analyzing and classifying data based on specific features such as soil health indicators, crop diversity, and livestock management. Additionally, simulated annealing, a global optimization algorithm, can be employed to explore complex model parameter spaces. The integration of these mathematical algorithms into the framework enhances analytical capabilities for assessing RA scenarios, providing a solid foundation for more robust modeling and data-driven insights.

5. Conclusions

This systematic review highlights the increasing interest in RA as a sustainable alternative, particularly for soil and ecosystem restoration. It proposes a comprehensive definition of RA as follows: “RA is an agricultural and transdisciplinary approach that integrates local and indigenous knowledge of landscapes, as well as their management, with established scientific knowledge. It combines a range of adoptable principles with context-specific practices, focusing on soil conservation as the initial step to restore soil health, enhance ecosystem functions, and promote improved socioeconomic outcomes”. This definition addresses previously overlooked aspects and aims to bring clarity to the understanding of RA. We also considered the practical applicability of RA (according to the working definition developed in the present review) on mixed broadacre farms in Australia.

The overall system of RA is complex, and we have identified key areas for RA assessment. These include soil health indicators (e.g., increased soil organic matter, pH, improved nutrient levels, and enhanced microbial activity), biodiversity conservation (e.g., multiple species cropping and diversified crop rotations), pest and disease resilience through integrated pest management, livestock performance indicators (e.g., weight gain, stocking rate, grazing intensity), and greenhouse gas mitigation/carbon storage. Successful RA requires a holistic approach, combining practices like crop–livestock integration. We have emphasized the critical importance of incorporating economic indicators, namely profitability, production costs, and risk management, which are essential for evaluating RA. Additionally, landscape hydrology, knowledge transfer, and addressing adoption challenges and barriers to RA can be considered as other priority areas.

The review identifies potential biophysical and economic tools/frameworks for assessing RA in mixed farming systems, such as the Agri-LCA tool, Field print calculator, GEMIS, MOTIFS, SALCAsustain, CAPRI, FARMIS, IFSC, and PASMA. However, integrating these tools into local RA farming contexts can be challenging, necessitating the use of appropriate assessment frameworks. The research explores key models for simulating the bioeconomic aspects of RA practices in mixed farming in the Australian context, including APSIM, CROPSYST, EPIC, STICS, RothC, CERES-EGC, DayCent, DNDC, WFM, AusFarm, GrassGro, LUSO, MIDAS, Farmpredict, and FSSIM. Yet, it is evident that more research is required to comprehensively and systematically assess overall farm outcomes and profitability. The study evaluates the emerging potential of AI and ML techniques in RA assessments, highlighting their applications and benefits in comprehensive data analysis, traceability, disease detection, spatial management decisions, real-time data collection, economic viability assessment, and decision-making processes. It recommends the use of novel techniques in RA assessments, such as big data analytics, blockchain technology, computer vision, data fusion, GIS and remote sensing, IoT, MCDA, and machine learning algorithms (e.g., ANFIS, ANN), association rule mining, BN, clustering algorithms, deep learning models (e.g., CNN, LSTM, RNN), RF. However, conducting in-depth case studies is essential to select the most appropriate novel techniques for specific RA scenarios.

Finally, the review proposes a tailored framework for evaluating the biophysical and economic impacts of RA in mixed farming contexts, informed by a systematic review. This framework encourages a transdisciplinary research approach that facilitates a comprehensive and integrated assessment of the biophysical and economic outcomes of RA by promoting collaboration, integrating data, developing holistic frameworks, engaging stakeholders, and supporting policymaking. Overall, this review contributes to the advancement of knowledge in RA by providing a working definition, evaluating assessment methods, and proposing a practical framework that can inform future studies and support evidence-based decision-making.

Supplementary Materials

The following supporting information can be downloaded at: https://www.mdpi.com/article/10.3390/su152215941/s1, Figure S1: The regenerative agriculture market by country; Figure S2: Annual publication trends (1985–2023) in regenerative agriculture research based on Scopus data; Figure S3: Key principles, practices, and outcomes of regenerative agriculture; Table S1: Summary of included papers in the study and categories of regenerative agriculture definitions.

Author Contributions

Conceptualization, D.T.T. and S.L.J.; methodology, S.L.J. and D.T.T.; software, S.L.J.; systematic analysis, S.L.J. and D.T.T.; investigation, S.L.J., D.T.T., C.C., J.P.A. and B.C.T.M.; resources, S.L.J. and D.T.T.; data curation, S.L.J., D.T.T., C.C., J.P.A. and B.C.T.M.; writing—original draft preparation, S.L.J.; writing—review and editing, S.L.J., D.T.T., C.C., J.P.A. and B.C.T.M.; visualization, S.L.J.; supervision, D.T.T., C.C., J.P.A. and B.C.T.M.; project administration, D.T.T.; proofreading, S.L.J., D.T.T., C.C., J.P.A. and B.C.T.M. All authors have read and agreed to the published version of the manuscript.

Funding

This research was funded by CSIRO under project number WBS R-18964-01.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Data are contained within the article.

Acknowledgments

Review comments of Hamideh Keshavarzi provided prior to submission are gratefully acknowledged. Authors acknowledge the Winangay Early Research Career (CERC) scholarship provided by CSIRO to the first author.

Conflicts of Interest

The authors declare no conflict of interest.

Abbreviations and Acronyms

Agri-LCA	agricultural life cycle assessment
AHP	analytical hierarchy process
AI	artificial intelligence
ANFIS	adaptive-neuro fuzzy inference systems
ANN	artificial neural networks
APSIM	The Agricultural Production Systems sIMulator
ArcGIS	geographic information system (GIS) developed by Environmental Systems Research Institute
AUI	the agri-environmental indicators
AVIBIO	tool derived from the AVIBIO project
BBN	Bayesian belief network
BN	Bayesian networks
CAPRI	The European Commission for Agricultural Policy Analysis
CERES-EGC	Crop Environment REsource Synthesis–Environnement et Grandes Cultures
CNN	convolutional neural networks
COSA	Committee on Sustainability Assessment
CAGR	compound annual growth rate
CropSyst	cropping systems simulation model
DairyMod	EcoMod (model/modify, observe, design)-suite: collectively termed GrazeMod
DairySAT	dairy self-assessment tool
DayCent	daily time-step version of the century model
Dexcel model	Dexcel whole farm model for dairy- New Zealand
DNDC	denitrification–decomposition
DRAM	Dutch regionalized agricultural model
DSSAT	decision support system for agrotechnology transfer
EcoMod	EcoMod
EPIC	environmental policy integrated climate
FARMAX	decision support tool for pastoral farmers model
FARMIS	farm Modeling information system
FaSSET	farm assessment tool
FESLM	Framework for Evaluation of Sustainable Land Management
FSSIM	farm system SIMulator
GA	genetic algorithms
GANs	generative adversarial networks
GBM	gradient boosting machines
GBRM	generalized boosted regression models
GIS	geographic information systems
GP	Gaussian processes
GPFARM	Great Plains Framework for Agricultural Resource Management
GPR	Gaussian process pegression
GPS/GNSS	global positioning system/global navigation satellite system
GRASS GIS	geographic resources analysis support system
GRAZPLAN	decision support systems for Australian grazing enterprises
GWAS	genome-wide association studies
HMM	hidden Markov models
IDEA	indicateurs de durabilité des exploitations agricoles
IDRISI	integrated land and water resources information system
IFSC	Illinois farm sustainability calculator
IFSMIFSM	integrated farm system model
IoT	Internet of Things
ISAP	indicator of sustainable agricultural practice
KNN	K-nearest neighbors
KSNL	kriteriensystem nachhaltige landwirtschaft
LAI	leaf area index
LINCFARM	Lincoln University farm model
LSTM	long short-term memory
LUSO	land use sequence optimizer
MAS	marker-assisted selection
MCDA	multi-criteria decision analysis
MCMC	Markov chain Monte Carlo
MDP	Markov decision processes
MDSM	Moorepark dairy system model
MESMIS	evaluating the sustainability of complex socioenvironmental systems
MIDAS	model of an integrated dryland agricultural system
ML	machine learning
MLP	multi layer perceptron
MLR	multiple linear regression
MMF	multi-scale methodological framework
MODAM	multi-omics data and application
MOTIFS	monitoring tool for integrated farm sustainability
NGS	next-generation sequencing
NLP	natural language processing
OCIS PG	organic conversion information service- public good tool
PaSim	pasture simulation model
PASMA	positive agricultural sector model of Austria
PCA	principal component analysis
PG Tool	public goods tool
PLSR	partial least squares regression
PSDCIFASA	problem-oriented status-driver composite indicator-base framework of agricultural sustainability assessment
PSO	particle swarm optimization
QGIS	quantum geographic information system
RA	regenerative agriculture
RFID	radio-frequency identification
RAUMIS	regional agricultural and environmental information system
RF	random forest
RISE	response-inducing sustainability evaluation
RNN	recurrent neural networks
RothC	Rothamsted carbon model
RS	remote sensing
SAFA	sustainability assessment of food and agriculture systems
SAFE	sustainability assessment of farming and the environment
SAGA GIS	system for automated geoscientific analyses
SALCA	Swiss agricultural life cycle assessment
SALCAsustain	Swiss agricultural life cycle assessment method
SDA	stakeholder Delphi approach
SEAMLESS/SEAMLESS -IF	system for environmental and agricultural modeling, linking European science and society
SGS Pasture Model	sustainable grazing systems
SILAS	Swiss agricultural sectoral information and forecasting system
SIRIUS	sustainable irrigation water management and river-basin governance: implementing user-driven services
SMART	sustainability monitoring and assessment routine
SOC	soil organic carbon
SOSTARE	analysis of farm technical efficiency and impacts on environmental and economic sustainability
SPA	sustainability potential analysis
SRP	sustainable rice platform
STICS	simulateur mulTIdiscplinaire pour les cultures standard
SVM	support vector machines
SVR	support vector regression
TOPSIS	technique for order preference by similarity to ideal solution
kg/day	kilograms per day
kg CO₂eq	kilograms of carbon dioxide equivalent
t/ha	metric tons per hectare
USD	United States Dollar
AUD	Australian Dollar
AWU	annual work unit
CVaR	conditional value-at-risk
ha	hectares
DSE/ha	dry sheep equivalents per hectare
MJ	megajoules
ME/head/day	megajoules per head per day
MJ ME	megajoules of metabolizable energy

References

FAO; UNEP. The State of the World’s Forests 2020: Forests, Biodiversity and People; FAO: Rome, Italy, 2020. [Google Scholar]
Grimm, M.; Luck, N. Experimenting with a green ‘Green Revolution’. Evidence from a randomised controlled trial in Indonesia. Ecol. Econ. 2023, 205, 107727. [Google Scholar] [CrossRef] [Scilit]
Anderson, M.D.; Rivera-Ferre, M. Food system narratives to end hunger: Extractive versus regenerative. Curr. Opin. Environ. Sustain. 2021, 49, 18–25. [Google Scholar] [CrossRef] [Scilit]
Clapp, J.; Moseley, W.G. This food crisis is different: COVID-19 and the fragility of the neoliberal food security order. J. Peasant Stud. 2020, 47, 1393–1417. [Google Scholar] [CrossRef] [Scilit]
McKeon, C.S.; Tunberg, B.G.; Johnston, C.A.; Barshis, D.J. Ecological drivers and habitat associations of estuarine bivalves. PeerJ 2015, 3, e1348. [Google Scholar] [CrossRef] [Scilit]
Khangura, R.; Ferris, D.; Wagg, C.; Bowyer, J. Regenerative Agriculture—A Literature Review on the Practices and Mechanisms Used to Improve Soil Health. Sustainability 2023, 15, 2338. [Google Scholar] [CrossRef] [Scilit]
Hensel, K. Will Regenerative Agriculture Become the Next ‘Organic’? Institute of Food Technologists: Chicago, IL, USA, 2018; p. 23. [Google Scholar]
Sands, B.; Machado, M.R.; White, A.; Zent, E.; Gould, R. Moving towards an anti-colonial definition for regenerative agriculture. Agric. Hum. Values 2023, 40, 1–20. [Google Scholar] [CrossRef] [Scilit]
Newton, P.; Civita, N.; Frankel-Goldwater, L.; Bartel, K.; Johns, C. What Is Regenerative Agriculture? A Review of Scholar and Practitioner Definitions Based on Processes and Outcomes. Front. Sustain. Food Syst. 2020, 4, 577723. [Google Scholar] [CrossRef] [Scilit]
O’donoghue, T.; Minasny, B.; McBratney, A. Regenerative Agriculture and Its Potential to Improve Farmscape Function. Sustainability 2022, 14, 5815. [Google Scholar] [CrossRef] [Scilit]
Kapoor, V. Grand View Research. Regenerative Agriculture Market Size & Share Report. 2023 Business Specialist at TechSci Research. Available online: https://www.grandviewresearch.com/industry-analysis/regenerative-agriculture-market-report (accessed on 11 October 2023).
Tan, S.S.; Kuebbing, S.E. A synthesis of the effect of regenerative agriculture on soil carbon sequestration in Southeast Asian croplands. Agric. Ecosyst. Environ. 2023, 349, 108450. [Google Scholar] [CrossRef] [Scilit]
Herzog, R. Cultivating a Sustainable Future: The Investability of Regenerative Agriculture Technology. Insights by CESR. University of Colorado Boulder. 2023. Available online: https://www.colorado.edu/business/cesr/insights-new2023/09/11/Cultivating-a-Sustainable-Future-The-Investability-Regenerative-Agriculture-Technology (accessed on 11 September 2023).
Kurth, T.; Subei, B.; Plötner, P.; Krämer, S. The Case for Regenerative Agriculture in Germany—And Beyond. Yale Environment 360. 12 October 2021. Available online: https://e360.yale.edu/features/the-case-for-regenerative-agriculture-in-germany-and-beyond (accessed on 20 September 2023).
Brown, K.; Schirmer, J.; Upton, P. Regenerative farming and human wellbeing: Are subjective wellbeing measures useful indicators for sustainable farming systems? Environ. Sustain. Indic. 2021, 11, 100132. [Google Scholar] [CrossRef] [Scilit]
Hes, D.; Rose, N. Shifting from farming to tending the earth: A discussion paper. J. Org. 2019, 6, 3–22. [Google Scholar]
Francis, C.A.; Harwood, R.R.; Liebhardt, W.C.; Kauffman, C.R.; Barker, T.C. Resource efficient farming systems and technologies. Regen. Farming Syst. 1985, 19, 21–31. [Google Scholar]
Massy, C. Call of the Reed Warbler: A New Agriculture—A New Earth; University of Queensland Press: Brisbane, Australia, 2020. [Google Scholar]
Lal, R. Regenerative agriculture for food and climate. J. Soil Water Conserv. 2020, 75, 123A–124A. [Google Scholar] [CrossRef] [Scilit]
McLennon, E.; Dari, B.; Jha, G.; Sihi, D.; Kankarla, V. Regenerative agriculture and integrative permaculture for sustainable and technology driven global food production and security. Agron. J. 2021, 113, 4541–4559. [Google Scholar] [CrossRef] [Scilit]
Díaz de Otálora, X.; del Prado, A.; Dragoni, F.; Estellés, F.; Amon, B. Evaluating Three-Pillar Sustainability Modelling Approaches for Dairy Cattle Production Systems. Sustainability 2021, 13, 6332. [Google Scholar] [CrossRef] [Scilit]
Planisich, A.; Utsumi, S.; Larripa, M.; Galli, J. Grazing of cover crops in integrated crop-livestock systems. Animal 2020, 15, 100054. [Google Scholar] [CrossRef] [Scilit]
Giller, K.E.; Hijbeek, R.; Andersson, J.A.; Sumberg, J. Regenerative Agriculture: An agronomic perspective. Outlook Agric. 2021, 50, 13–25. [Google Scholar] [CrossRef] [Scilit]
Francis, J. Regenerative Agriculture—Quantifying the Cost; Occasional Paper No. 20.01; Australian Farm Institute: Sydney, Australia, 2020; p. 1. [Google Scholar]
Robertson, M.; Macdonald, B.; Farrell, M.; Norman, H.; Macdonald, L.; Vadakattu, G.; Taylor, J. What Can Science Offer the Proponents of Regenerative Agriculture Practices? Australian Farm Institute: Sydney, Australia, 2022. [Google Scholar]
Darnhofer, I.; Lindenthal, T.; Bartel-Kratochvil, R.; Zollitsch, W. Conventionalisation of organic farming practices: From structural criteria towards an assessment based on organic principles. A review. Agron. Sustain. Dev. 2010, 30, 67–81. [Google Scholar] [CrossRef] [Scilit]
Gatto, M.; DE Leo, G.A. Pricing Biodiversity and Ecosystem Services: The Never-Ending Story. BioScience 2000, 50, 347–355. [Google Scholar] [CrossRef] [Scilit]
Ogungbuyi, M.G.; Guerschman, J.P.; Fischer, A.M.; Crabbe, R.A.; Mohammed, C.; Scarth, P.; Tickle, P.; Whitehead, J.; Harrison, M.T. Enabling Regenerative Agriculture Using Remote Sensing and Machine Learning. Land 2023, 12, 1142. [Google Scholar] [CrossRef] [Scilit]
Efremova, N.; Foley, C.; Unagaev, A.; Karimi, R.; Averkin, A.; Gutierrez-Romero, R. Monitoring Large-Scale Regenerative Grazing Using Artificial Intelligence. 2022. Available online: https://assets.researchsquare.com/files/rs-2136218/v1_covered.pdf?c=1667450774 (accessed on 12 September 2023).
Chopin, P.; Mubaya, C.P.; Descheemaeker, K.; Öborn, I.; Bergkvist, G. Avenues for improving farming sustainability assessment with upgraded tools, sustainability framing and indicators. A review. Agron. Sustain. Dev. 2021, 41, 19. [Google Scholar] [CrossRef] [Scilit]
De Ridder, W.; Turnpenny, J.; Nilsson, M.; Von Raggamby, A. A framework for tool selection and use in integrated assessment for sustainable development. J. Environ. Assess. Policy Manag. 2007, 9, 423–441. [Google Scholar] [CrossRef] [Scilit]
Gasparatos, A.; Scolobig, A. Choosing the most appropriate sustainability assessment tool. Ecol. Econ. 2012, 80, 1–7. [Google Scholar] [CrossRef] [Scilit]
Bockstaller, C.; Feschet, P.; Angevin, F. Issues in evaluating sustainability of farming systems with indicators. OCL 2015, 22, D102. [Google Scholar] [CrossRef] [Scilit]
Lebacq, T.; Baret, P.V.; Stilmant, D. Sustainability indicators for livestock farming. A review. Agron. Sustain. Dev. 2012, 33, 311–327. [Google Scholar] [CrossRef] [Scilit]
Colley, T.A.; Olsen, S.I.; Birkved, M.; Hauschild, M.Z. Delta Life Cycle Assessment of Regenerative Agriculture in a Sheep Farming System. Integr. Environ. Assess. Manag. 2019, 16, 282–290. [Google Scholar] [CrossRef] [Scilit]
Schreefel, L.; Schulte, R.; de Boer, I.; Schrijver, A.P.; van Zanten, H. Regenerative agriculture—The soil is the base. Glob. Food Secur. 2020, 26, 100404. [Google Scholar] [CrossRef] [Scilit]
Schreefel, L.; van Zanten, H.; Groot, J.; Timler, C.; Zwetsloot, M.; Schrijver, A.P.; Creamer, R.; Schulte, R.; de Boer, I. Tailor-made solutions for regenerative agriculture in the Netherlands. Agric. Syst. 2022, 203, 103518. [Google Scholar] [CrossRef] [Scilit]
van der Linden, A.; de Olde, E.M.; Mostert, P.F.; de Boer, I.J. A review of European models to assess the sustainability performance of livestock production systems. Agric. Syst. 2020, 182, 102842. [Google Scholar] [CrossRef] [Scilit]
van Ittersum, M.K.; Ewert, F.; Heckelei, T.; Wery, J.; Olsson, J.A.; Andersen, E.; Bezlepkina, I.; Brouwer, F.; Donatelli, M.; Flichman, G.; et al. Integrated assessment of agricultural systems—A component-based framework for the European Union (SEAMLESS). Agric. Syst. 2008, 96, 150–165. [Google Scholar] [CrossRef] [Scilit]
Debeljak, M.; Trajanov, A.; Kuzmanovski, V.; Schröder, J.; Sandén, T.; Spiegel, H.; Wall, D.P.; Van de Broek, M.; Rutgers, M.; Bampa, F.; et al. A Field-Scale Decision Support System for Assessment and Management of Soil Functions. Front. Environ. Sci. 2019, 7, 115. [Google Scholar] [CrossRef] [Scilit]
Ros, G.H.; Fujita, Y. The Open Soil Index 0.3. NMI. 2020. Available online: https://www.nmi-agro.nl/wpcontent/uploads/2019/09/Factsheet-Open-Soil (accessed on 5 March 2023).
Van Eck, N.J.; Waltman, L. VOSviewer Manual. Manual for VOSviewer Version. 2011. Available online: https://www.vosviewer.com/getting-started (accessed on 11 February 2023).
Chaudhary, S.; Dhir, A.; Ferraris, A.; Bertoldi, B. Trust and reputation in family businesses: A systematic literature review of past achievements and future promises. J. Bus. Res. 2021, 137, 143–161. [Google Scholar] [CrossRef] [Scilit]
Francis, C.A.; Harwood, R.R.; Parr, J.F. The potential for regenerative agriculture in the developing world. Am. J. Altern. Agric. 1986, 1, 65–74. [Google Scholar] [CrossRef] [Scilit]
Brown, G. Dirt to Soil: One Family’s Journey into Regenerative Agriculture; Chelsea Green Publishing: Chelsea, VT, USA, 2018. [Google Scholar]
Kamenetzky, M.; Maybury, R.H. Agriculture in harmony with nature. Sci. Public Policy 1989, 16, 73–82. [Google Scholar] [CrossRef] [Scilit]
Gremmen, B. Regenerative agriculture as a biomimetic technology. Outlook Agric. 2022, 51, 39–45. [Google Scholar] [CrossRef] [Scilit]
Dahlberg, K.A. A transition from agriculture to regenerative food systems. Futures 1994, 26, 170–179. [Google Scholar] [CrossRef] [Scilit]
Landers, J.N.; de Freitas, P.L.; de Oliveira, M.C.; da Silva Neto, S.P.; Ralisch, R.; Kueneman, E.A. Next Steps for Conservation Agriculture. Agronomy 2021, 11, 2496. [Google Scholar] [CrossRef] [Scilit]
Tittonell, P.; El Mujtar, V.; Felix, G.; Kebede, Y.; Laborda, L.; Soto, R.L.; de Vente, J. Regenerative agriculture—Agroecology without politics? Front. Sustain. Food Syst. 2022, 6, 844261. [Google Scholar] [CrossRef] [Scilit]
LaCanne, C.E.; Lundgren, J.G. Regenerative agriculture: Merging farming and natural resource conservation profitably. PeerJ 2018, 6, e4428. [Google Scholar] [CrossRef] [Scilit]
Cusser, S.; Bahlai, C.; Swinton, S.M.; Robertson, G.P.; Haddad, N.M. Long-term research avoids spurious and misleading trends in sustainability attributes of no-till. Glob. Change Biol. 2020, 26, 3715–3725. [Google Scholar] [CrossRef] [Scilit]
Burgess, P.J.; Harris, J.; Graves, A.R.; Deeks, L.K. Regenerative Agriculture: Identifying the Impact; Enabling the Potential; Report for SYSTEMIQ; SYSTEMIQ: London, UK, 2019; p. 17. [Google Scholar]
Xu, N.; Bhadha, J.H.; Rabbany, A.; Swanson, S. Soil Health Assessment of Two Regenerative Farming Practices on Sandy Soils. Sustain. Agric. Res. 2019, 8, 61–71. [Google Scholar] [CrossRef] [Scilit]
Xu, N.; Amgain, N.R.; Rabbany, A.; Capasso, J.; Korus, K.; Swanson, S.; Bhadha, J.H. Interaction of soil health indicators to different regenerative farming practices on mineral soils. Agrosystems Geosci. Environ. 2022, 5, e20243. [Google Scholar] [CrossRef] [Scilit]
Pearson, C.J. Regenerative, Semiclosed Systems: A Priority for Twenty-First-Century Agriculture. BioScience 2007, 57, 409–418. [Google Scholar] [CrossRef] [Scilit]
Rhodes, C.J. The Imperative for Regenerative Agriculture. Sci. Prog. 2017, 100, 80–129. [Google Scholar] [CrossRef] [Scilit] [PubMed]
Ikerd, J. THE ECONOMIC PAMPHLETEER: Realities of regenerative agriculture. J. Agric. Food Syst. Community Dev. 2021, 10, 7–10. [Google Scholar] [CrossRef] [Scilit]
Pawan, M.; Minkashi, V. Organic agricultural crop nutrient. Res. J. Chem. Sci. 2014, 4, 94–98. [Google Scholar]
Diop, A.M. Sustainable Agriculture: New Paradigms and Old Practices? Increased Production with Management of Organic Inputs in Senegal. Environ. Dev. Sustain. 1999, 1, 285–296. [Google Scholar] [CrossRef] [Scilit]
Teague, R.; Kreuter, U. Managing Grazing to Restore Soil Health, Ecosystem Function, and Ecosystem Services. Front. Sustain. Food Syst. 2020, 4, 534187. [Google Scholar] [CrossRef] [Scilit]
Rhodes, C.J. Feeding and Healing the World: Through Regenerative Agriculture and Permaculture. Sci. Prog. 2012, 95, 345–446. [Google Scholar] [CrossRef] [Scilit]
Gosnell, H.; Charnley, S.; Stanley, P. Climate change mitigation as a co-benefit of regenerative ranching: Insights from Australia and the United States. Interface Focus 2020, 10, 20200027. [Google Scholar] [CrossRef] [Scilit]
Elevitch, C.R.; Mazaroli, D.N.; Ragone, D. Agroforestry Standards for Regenerative Agriculture. Sustainability 2018, 10, 3337. [Google Scholar] [CrossRef] [Scilit]
Provenza, F.D.; Kronberg, S.L.; Gregorini, P. Is Grassfed Meat and Dairy Better for Human and Environmental Health? Front. Nutr. 2019, 6, 26. [Google Scholar] [CrossRef] [Scilit] [PubMed]
De Haas, B.R.; Hoekstra, N.J.; van der Schoot, J.R.; Visser, E.J.; de Kroon, H.; van Eekeren, N. Combining agro-ecological functions in grass-clover mixtures. AIMS Agric. Food 2019, 4, 547–567. [Google Scholar] [CrossRef] [Scilit]
Teague, W.R. Toward Restoration of Ecosystem Function and Livelihoods on Grazed Agroecosystems. Crop. Sci. 2015, 55, 2550–2556. [Google Scholar] [CrossRef] [Scilit]
Teague, R.; Barnes, M. Grazing management that regenerates ecosystem function and grazingland livelihoods. Afr. J. Range Forage Sci. 2017, 34, 77–86. [Google Scholar] [CrossRef] [Scilit]
Al-Kaisi, M.M.; Lal, R. Aligning science and policy of regenerative agriculture. Soil Sci. Soc. Am. J. 2020, 84, 1808–1820. [Google Scholar] [CrossRef] [Scilit]
Grant, S. Organizing alternative food futures in the peripheries of the industrial food system. Int. J. Sustain. Educ. 2017, 14, 1–14. [Google Scholar]
Uddin Mahtab, F.; Karim, Z. Population and agricultural land use: Towards a sustainable food production system in Bangladesh. Ambio 1992, 21, 50–55. [Google Scholar]
Sherwood, S.; Uphoff, N. Soil health: Research, practice and policy for a more regenerative agriculture. Appl. Soil Ecol. 2000, 15, 85–97. [Google Scholar] [CrossRef] [Scilit]
Teague, W.R. Forages and Pastures Symposium: Cover Crops in Livestock Production: Whole-System Approach: Managing grazing to restore soil health and farm livelihoods1. J. Anim. Sci. 2018, 96, 1519–1530. [Google Scholar] [CrossRef] [Scilit]
Seymour, M.; Connelly, S. Regenerative agriculture and a more-than-human ethic of care: A relational approach to understanding transformation. Agric. Human Values 2023, 40, 231–244. [Google Scholar] [CrossRef] [Scilit]
Wilson, K.R.; Myers, R.L.; Hendrickson, M.K.; Heaton, E.A. Different Stakeholders’ Conceptualizations and Perspectives of Regenerative Agriculture Reveals More Consensus Than Discord. Sustainability 2022, 14, 15261. [Google Scholar] [CrossRef] [Scilit]
Van den Berg, L.; Roep, D.; Hebinck, P.; Teixeira, H.M. Reassembling nature and culture: Resourceful farming in Araponga, Brazil. J. Rural Stud. 2018, 61, 314–322. [Google Scholar] [CrossRef] [Scilit]
Zazo-Moratalla, A.; Troncoso-González, I.; Moreira-Muñoz, A. Regenerative Food Systems to Restore Urban-Rural Relationships: Insights from the Concepción Metropolitan Area Foodshed (Chile). Sustainability 2019, 11, 2892. [Google Scholar] [CrossRef] [Scilit]
Ogilvy, S.; Gardner, M.; Mallawaarachichi, T.; Schirmer, J.; Brown, K.; Heagney, E. NESP-EP: Nesp-Ep: Farm Profitability and Biodiversity Project Final Report; Canberra Australia Strategy; ANU Fenner School of Environment & Society: Acton, Australia, 2018. [Google Scholar]
White, C. Why Regenerative Agriculture? Am. J. Econ. Sociol. 2020, 79, 799–812. [Google Scholar] [CrossRef] [Scilit]
Schoolman, E.D. Do direct market farms use fewer agricultural chemicals? Evidence from the US census of agriculture. Renew. Agric. Food Syst. 2018, 34, 415–429. [Google Scholar] [CrossRef] [Scilit]
Kenny, D.C.; Castilla-Rho, J. What Prevents the Adoption of Regenerative Agriculture and What Can We Do about It? Lessons and Narratives from a Participatory Modelling Exercise in Australia. Land 2022, 11, 1383. [Google Scholar] [CrossRef] [Scilit]
Fenster, T.L.; LaCanne, C.E.; Pecenka, J.R.; Schmid, R.B.; Bredeson, M.M.; Busenitz, K.M.; Michels, A.M.; Welch, K.D.; Lundgren, J.G. Defining and validating regenerative farm systems using a composite of ranked agricultural practices. F1000Research 2021, 10, 115. [Google Scholar] [CrossRef] [Scilit]
Gordon, E.; Davila, F.; Riedy, C. Transforming landscapes and mindscapes through regenerative agriculture. Agric. Hum. Values 2021, 39, 809–826. [Google Scholar] [CrossRef] [Scilit]
Daverkosen, L.; Holzknecht, A.; Friedel, J.K.; Keller, T.; Strobel, B.W.; Wendeberg, A.; Jordan, S. The potential of regenerative agriculture to improve soil health on Gotland, Sweden. J. Plant Nutr. Soil Sci. 2022, 185, 901–914. [Google Scholar] [CrossRef] [Scilit]
Le, Q.V.; Cowal, S.; Jovanovic, G.; Le, D.-T. A Study of Regenerative Farming Practices and Sustainable Coffee of Ethnic Minorities Farmers in the Central Highlands of Vietnam. Front. Sustain. Food Syst. 2021, 5, 712733. [Google Scholar] [CrossRef] [Scilit]
Soloviev, E.R.; Landua, G. Levels of Regenerative Agriculture; Terra Genesis International: Ithaca, NY, USA, 2016. [Google Scholar]
Nasirahmadi, A.; Sturm, B.; Edwards, S.; Jeppsson, K.-H.; Olsson, A.-C.; Müller, S.; Hensel, O. Deep Learning and Machine Vision Approaches for Posture Detection of Individual Pigs. Sensors 2019, 19, 3738. [Google Scholar] [CrossRef] [Scilit] [PubMed]
Roy, R.; Chan, N.W. An assessment of agricultural sustainability indicators in Bangladesh: Review and synthesis. Environmentalist 2011, 32, 99–110. [Google Scholar] [CrossRef] [Scilit]
Nambiar, K.; Gupta, A.; Fu, Q.; Li, S. Biophysical, chemical and socio-economic indicators for assessing agricultural sustainability in the Chinese coastal zone. Agric. Ecosyst. Environ. 2001, 87, 209–214. [Google Scholar] [CrossRef] [Scilit]
Kebede, G.; Assefa, G.; Feyissa, F.; Mengistu, A. Forage Legumes in Crop-Livestock Mixed Farming Systems—A Review. Int. J. Livest. Res. 2016, 6, 1–18. [Google Scholar] [CrossRef] [Scilit]
Sydorovych, O.; Wossink, A. The meaning of agricultural sustainability: Evidence from a conjoint choice survey. Agric. Syst. 2008, 98, 10–20. [Google Scholar] [CrossRef] [Scilit]
Gowda, M.C.; Jayaramaiah, K. Comparative evaluation of rice production systems for their sustainability. Agric. Ecosyst. Environ. 1998, 69, 1–9. [Google Scholar] [CrossRef] [Scilit]
Rasul, G.; Thapa, G.B. Sustainability of ecological and conventional agricultural systems in Bangladesh: An assessment based on environmental, economic and social perspectives. Agric. Syst. 2004, 79, 327–351. [Google Scholar] [CrossRef] [Scilit]
Fang, H.; Baret, F.; Plummer, S.; Schaepman-Strub, G. An Overview of Global Leaf Area Index (LAI): Methods, Products, Validation, and Applications. Rev. Geophys. 2019, 57, 739–799. [Google Scholar] [CrossRef] [Scilit]
Unkovich, M.; Pate, J.; Sanford, P.; Armstrong, E. Potential precision of the δ15N natural abundance method in field estimates of nitrogen fixation by crop and pasture legumes in south-west Australia. Aust. J. Agric. Res. 1994, 45, 119–132. [Google Scholar] [CrossRef] [Scilit]
Stylianou, A.; Sdrali, D.; Apostolopoulos, C.D. Integrated Sustainability Assessment of Divergent Mediterranean Farming Systems: Cyprus as a Case Study. Sustainability 2020, 12, 6105. [Google Scholar] [CrossRef] [Scilit]
López-Ridaura, S.; Masera, O.; Astier, M. Evaluating the sustainability of complex socio-environmental systems. The MESMIS framework. Ecol. Indic. 2002, 2, 135–148. [Google Scholar] [CrossRef] [Scilit]
Gómez-Limón, J.A.; Sanchez-Fernandez, G. Empirical evaluation of agricultural sustainability using composite indicators. Ecol. Econ. 2010, 69, 1062–1075. [Google Scholar] [CrossRef] [Scilit]
Zhen, L.; Zoebisch, M.A.; Chen, G.; Feng, Z. Sustainability of farmers’ soil fertility management practices: A case study in the North China Plain. J. Environ. Manag. 2006, 79, 409–419. [Google Scholar] [CrossRef] [Scilit] [PubMed]
Hani, F.; Braga, F.S.; Stampfli, A.; Keller, T.; Fischer, M.; Porsche, H. RISE, a tool for holistic sustainability assessment at the farm level. Int. Food Agribus. Manag. Rev. 2003, 6, 78–90. [Google Scholar] [CrossRef]
Vecchione, G. EU Rural Policy: Proposal and Application of an Agricultural Sustainability Index. 2010. Available online: https://mpra.ub.uni-muenchen.de/id/eprint/27032 (accessed on 20 August 2023).
Gomez-Limon, J.A.; Riesgo, L. Alternative approaches on constructing a composite indicator to measure agricultural sustainability. In Proceedings of the 107th Seminar, Sevilla, Spain, 30 January–1 February 2008; European Association of Agricultural Economists: Wageningen, The Netherlands, 2008. [Google Scholar] [CrossRef]
Colnago, P.; Dogliotti, S. Introducing labour productivity analysis in a co-innovation process to improve sustainability in mixed family farming. Agric. Syst. 2019, 177, 102732. [Google Scholar] [CrossRef] [Scilit]
Dantsis, T.; Douma, C.; Giourga, C.; Loumou, A.; Polychronaki, E.A. A methodological approach to assess and compare the sustainability level of agricultural plant production systems. Ecol. Indic. 2010, 10, 256–263. [Google Scholar] [CrossRef] [Scilit]
Saltiel, J.; Bauder, J.W.; Palakovich, S. Adoption of Sustainable Agricultural Practices: Diffusion, Farm Structure, and Profitability1. Rural. Sociol. 1994, 59, 333–349. [Google Scholar] [CrossRef] [Scilit]
Smith, C.; McDonald, G. Assessing the sustainability of agriculture at the planning stage. J. Environ. Manag. 1998, 52, 15–37. [Google Scholar] [CrossRef] [Scilit]
van Calker, K.; Berentsen, P.; Romero, C.; Giesen, G.; Huirne, R. Development and application of a multi-attribute sustainability function for Dutch dairy farming systems. Ecol. Econ. 2006, 57, 640–658. [Google Scholar] [CrossRef] [Scilit]
Dillon, E.J.; Hennessy, T.C.; Hynes, S. Towards measurement of farm sustainability-an Irish case study. In Proceedings of the International Association of Agricultural Economists (IAAE) 2009 Conference, Beijing, China, 16–22 August 2009. [Google Scholar] [CrossRef]
Penfold, C.; Miyan, M.S.; Reeves, T.; Grierson, I. Biological farming for sustainable agricultural production. Aust. J. Exp. Agric. 1995, 35, 849–856. [Google Scholar] [CrossRef] [Scilit]
Chen, Y.; Tao, T. On evaluation indices of sustainable agriculture. Res. Agric. Mod. 2000, 21, 271–275. [Google Scholar]
Zhen, L.; Routray, J.K. Operational Indicators for Measuring Agricultural Sustainability in Developing Countries. Environ. Manag. 2003, 32, 34–46. [Google Scholar] [CrossRef] [Scilit] [PubMed]
Gafsi, M.; Favreau, J.L. Appropriate method to assess the sustainability of organic farming systems. In Proceedings of the 9th European IFSA Symposium, Vienna, Austria, 4–7 July 2010. [Google Scholar]
Binder, C.R.; Feola, G.; Steinberger, J.K. Considering the normative, systemic and procedural dimensions in indicator-based sustainability assessments in agriculture. Environ. Impact Assess. Rev. 2010, 30, 71–81. [Google Scholar] [CrossRef] [Scilit]
Schader, C.; Grenz, J.; Meier, M.S.; Stolze, M. Scope and precision of sustainability assessment approaches to food systems. Ecol. Soc. 2014, 19, 1–15. [Google Scholar] [CrossRef] [Scilit]
Pottiez, E.; Lescoat, P.; Bouvarel, I. AVIBIO: A method to assess the sustainability of the organic poultry industry. In Proceedings of the 10th European International Farming Systems Association (IFSA) Symposium, Aarhus, Denmark, 1–4 July 2012. [Google Scholar]
Helming, J.; Tabeau, A. The economic, environmental and agricultural land use effects in the European Union of agricultural labour subsidies under the Common Agricultural Policy. Reg. Environ. Change 2017, 18, 763–773. [Google Scholar] [CrossRef] [Scilit]
Gillum, M.; Johnson, P.; Hudson, D.; Williams, R. Fieldprint Calculator: A tool to evaluate the effects of management on physical sustainability. Crop. Soils 2016, 49, 26–29. [Google Scholar] [CrossRef] [Scilit]
Zahm, F. IDEA: Indicateurs de Durabilité des Exploitations Agricoles; Plate Forme d’évaluation Agrienvironnementale. 2008, Volume 3, pp. 1–12. Available online: https://hal.science/hal-02590517/ (accessed on 7 November 2023).
Marten, T. Towards Sustainable Agriculture: Dudley Smith Farm Revision, New. Bachelor’s Thesis, University of Illinois at Urbana-Champaign, Champaign, IL, USA, 2009. [Google Scholar]
Bechini, L.; Castoldi, N. On-farm monitoring of economic and environmental performances of cropping systems: Results of a 2-year study at the field scale in northern Italy. Ecol. Indic. 2009, 9, 1096–1113. [Google Scholar] [CrossRef] [Scilit]
Marta-Costa, A.A.; Silva, E. Approaches for sustainable farming systems assessment. In Methods and Procedures for Building Sustainable Farming Systems: Application in the European Context; Springer: Dordrecht, The Netherlands, 2013; pp. 21–29. [Google Scholar] [CrossRef] [Scilit]
Talukder, B.; Blay-Palmer, A. Comparison of methods to assess agricultural sustainability. In Sustainable Agriculture Reviews; Springer: Berlin/Heidelberg, Germany, 2017; pp. 149–168. [Google Scholar] [CrossRef] [Scilit]
Sattler, C.; Schuler, J.; Zander, P. Determination of trade-off-functions to analyse the provision of agricultural non-commodities. Int. J. Agric. Resour. Gov. Ecol. 2006, 5, 309–325. [Google Scholar] [CrossRef] [Scilit]
Eichler Inwood, S.E.; López-Ridaura, S.; Kline, K.L.; Gérard, B.; Monsalue, A.G.; Govaerts, B.; Dale, V.H. Assessing sustainability in agricultural landscapes: A review of approaches. Environ. Rev. 2018, 26, 299–315. [Google Scholar] [CrossRef] [Scilit]
Jawtusch, J.; Schader, C.; Stolze, M.; Baumgart, L.; Niggli, U. Sustainability monitoring and assessment routine: Results from pilot applications of the FAO SAFA guidelines. In Proceedings of the Symposium International sur L’Agriculture Biologique Méditerranénne et Les Signes Distinctifs de Qualité liée à l’Origine, Agadir, Morocco, 2–4 December 2013. [Google Scholar]
Paracchini, M.L.; Bulgheroni, C.; Borreani, G.; Tabacco, E.; Banterle, A.; Bertoni, D.; Rossi, G.; Parolo, G.; Origgi, R.; De Paola, C. A diagnostic system to assess sustainability at a farm level: The SOSTARE model. Agric. Syst. 2015, 133, 35–53. [Google Scholar] [CrossRef] [Scilit]
Keating, B.A.; Carberry, P.S.; Hammer, G.L.; Probert, M.E.; Robertson, M.J.; Holzworth, D.; Huth, N.I.; Hargreaves, J.N.; Meinke, H.; Hochman, Z.; et al. An overview of APSIM, a model designed for farming systems simulation. Eur. J. Agron. 2003, 18, 267–288. [Google Scholar] [CrossRef] [Scilit]
Grigg, N.; Mokany, K.; Woodward, E.; Pirzl, R.; Fletcher, C.; Ahmad, M.; Lemon, D. CSIRO’s Integrated National Prediction, Foresighting and Scenarios Capability; CSIRO: Canberra, Australia, 2020; p. 104.
Jones, J.W.; Hoogenboom, G.; Porter, C.H.; Boote, K.J.; Batchelor, W.D.; Hunt, L.A.; Wilkens, P.W.; Singh, U.; Gijsman, A.J.; Ritchie, J.T. The DSSAT cropping system model. Eur. J. Agron. 2003, 18, 235–265. [Google Scholar] [CrossRef] [Scilit]
Stöckle, C.O.; Donatelli, M.; Nelson, R. CropSyst, a cropping systems simulation model. Eur. J. Agron. 2003, 18, 289–307. [Google Scholar] [CrossRef] [Scilit]
McMaster, G.S.; Ii, J.A.; Edmunds, D.A.; Andales, A.A.; Wagner, L.E.; Fox, F.A. Multi-crop plant growth modeling for agricultural models and decision support systems. In Proceedings of the MODSIM 2005 International Congress on Modelling and Simulation, Melbourne, Australia, 12–15 December 2005. [Google Scholar]
Brisson, N.; Gary, C.; Justes, E.; Roche, R.; Mary, B.; Ripoche, D.; Zimmer, D.; Sierra, J.; Bertuzzi, P.; Burger, P.; et al. An overview of the crop model STICS. Eur. J. Agron. 2003, 18, 309–332. [Google Scholar] [CrossRef] [Scilit]
Coleman, K.; Jenkinson, D.S. RothC-26.3—A Model for the turnover of carbon in soil. In Evaluation of Soil Organic Matter Models. NATO ASI Series; Springer: Berlin/Heidelberg, Germany, 1996; Volume 38, pp. 237–246. [Google Scholar] [CrossRef] [Scilit]
Lamboni, M.; Makowski, D.; Lehuger, S.; Gabrielle, B.; Monod, H. Multivariate global sensitivity analysis for dynamic crop models. Field Crop. Res. 2009, 113, 312–320. [Google Scholar] [CrossRef] [Scilit]
Parton, W.J.; Hartman, M.; Ojima, D.; Schimel, D. DAYCENT and its land surface submodel: Description and testing. Glob. Planet. Change 1998, 19, 35–48. [Google Scholar] [CrossRef] [Scilit]
Liu, Y.; Yu, Z.; Chen, J.; Zhang, F.; Doluschitz, R.; Axmacher, J.C. Changes of soil organic carbon in an intensively cultivated agricultural region: A denitrification–decomposition (DNDC) modelling approach. Sci. Total. Environ. 2006, 372, 203–214. [Google Scholar] [CrossRef] [Scilit]
Riedo, M.; Gyalistras, D.; Fuhrer, J. Net primary production and carbon stocks in differently managed grasslands: Simulation of site-specific sensitivity to an increase in atmospheric CO2 and to climate change. Ecol. Model. 2000, 134, 207–227. [Google Scholar] [CrossRef] [Scilit]
Johnson, I. Biophysical Pasture Model Documentation: Model Documentation for DairyMod. EcoMod and the SGS Pasture Model. IMJ Consultants: Armidale, NSW. Available online: www.imj.com.au/gmdocs (accessed on 14 March 2008).
Moore, A.; Donnelly, J.; Freer, M. GRAZPLAN: Decision support systems for Australian grazing enterprises. III. Pasture growth and soil moisture submodels, and the GrassGro DSS. Agric. Syst. 1997, 55, 535–582. [Google Scholar] [CrossRef] [Scilit]
Rickert, K.; Stuth, J.; McKeon, G. Modelling pasture and animal production. Field Lab. Methods Grassl. Anim. Prod. Res. 2000, 29–66. [Google Scholar] [CrossRef] [Scilit]
Thornley, J.H. Grassland Dynamics: An Ecosystem Simulation Model; CAB International: Wallingford, UK, 1998. [Google Scholar]
Bryant, J.R.; Snow, V.O. Modelling pastoral farm agro-ecosystems: A review. N. Z. J. Agric. Res. 2008, 51, 349–363. [Google Scholar] [CrossRef] [Scilit]
Lawes, R.; Renton, M. The Land Use Sequence Optimiser (LUSO): A theoretical framework for analysing crop sequences in response to nitrogen, disease and weed populations. Crop. Pasture Sci. 2010, 61, 835–843. [Google Scholar] [CrossRef] [Scilit]
Shalloo, L.; Dillon, P.; Rath, M.; Wallace, M. Description and Validation of the Moorepark Dairy System Model. J. Dairy Sci. 2004, 87, 1945–1959. [Google Scholar] [CrossRef] [Scilit]
Hughes, N.; Lu, M.; Soh, W.Y.; Lawson, K. Modelling the effects of climate change on the profitability of Australian farms. Clim. Change 2022, 172, 12. [Google Scholar] [CrossRef] [Scilit]
Jensen, F.V.; Nielsen, T.D. Bayesian Networks and Decision Graphs, 2nd ed.; Springer: Berlin/Heidelberg, Germany, 2007; Volume 2. [Google Scholar] [CrossRef] [Scilit]
Kamilaris, A.; Kartakoullis, A.; Prenafeta-Boldú, F.X. A review on the practice of big data analysis in agriculture. Comput. Electron. Agric. 2017, 143, 23–37. [Google Scholar] [CrossRef] [Scilit]
Jain, R.; Sharma, A.; Sharma, D. Mapping the Literature on Implementation of Blockchain in Agriculture: A Systematic Review. Smart Anal. Artif. Intell. Sustain. Perform. Manag. A Glob. Digit. Econ. 2023, 110, 131–144. [Google Scholar] [CrossRef] [Scilit]
Tian, H.; Wang, T.; Liu, Y.; Qiao, X.; Li, Y. Computer vision technology in agricultural automation—A review. Inf. Process. Agric. 2019, 7, 1–19. [Google Scholar] [CrossRef] [Scilit]
Barbedo, J.G.A. Data Fusion in Agriculture: Resolving Ambiguities and Closing Data Gaps. Sensors 2022, 22, 2285. [Google Scholar] [CrossRef] [Scilit]
Santos, L.; Santos, F.N.; Oliveira, P.M.; Shinde, P. Deep learning applications in agriculture: A short review. In Robot 2019: Fourth Iberian Robotics Conference: Advances in Robotics; Springer: Berlin/Heidelberg, Germany, 2020; Volume 1. [Google Scholar] [CrossRef] [Scilit]
Kumar, J.; Choudhary, A.K.; Solanki, R.K.; Pratap, A. Towards marker-assisted selection in pulses: A review. Plant Breed. 2011, 130, 297–313. [Google Scholar] [CrossRef] [Scilit]
Vibhute, A.D.; Gawali, B.W. Analysis and modeling of agricultural land use using remote sensing and geographic information system: A review. Int. J. Eng. Res. 2013, 3, 81–91. [Google Scholar]
Kim, W.-S.; Lee, W.-S.; Kim, Y.-J. A Review of the Applications of the Internet of Things (IoT) for Agricultural Automation. J. Biosyst. Eng. 2020, 45, 385–400. [Google Scholar] [CrossRef] [Scilit]
Liakos, K.G.; Busato, P.; Moshou, D.; Pearson, S.; Bochtis, D. Machine learning in agriculture: A review. Sensors 2018, 18, 2674. [Google Scholar] [CrossRef] [Scilit] [PubMed]
Talukder, B.; Hipel, K.W.; Vanloon, G.W. Using multi-criteria decision analysis for assessing sustainability of agricultural systems. Sustain. Dev. 2018, 26, 781–799. [Google Scholar] [CrossRef] [Scilit]
Kang, Y.; Cai, Z.; Tan, C.-W.; Huang, Q.; Liu, H. Natural language processing (NLP) in management research: A literature review. J. Manag. Anal. 2020, 7, 139–172. [Google Scholar] [CrossRef] [Scilit]
Sishodia, R.P.; Ray, R.L.; Singh, S.K. Applications of Remote Sensing in Precision Agriculture: A Review. Remote Sens. 2020, 12, 3136. [Google Scholar] [CrossRef] [Scilit]
Zujevs, A.; Osadcuks, V.; Ahrendt, P. Trends in Robotic Sensor Technologies for Fruit Harvesting: 2010-2015. Procedia Comput. Sci. 2015, 77, 227–233. [Google Scholar] [CrossRef] [Scilit]
Novák, J.; Benda, P.; Šilerová, E.; Vaněk, J.; Kánská, E. Sentiment analysis in agriculture. AGRIS OnLine Pap. Econ. Inform. 2021, 13, 121–130. [Google Scholar] [CrossRef] [Scilit]
Jang, J.-S.R. ANFIS: Adaptive-Network-Based Fuzzy Inference System. IEEE Trans. Syst. Man Cybern. 1993, 23, 665–685. [Google Scholar] [CrossRef] [Scilit]
Ghosh, S.; Biswas, D.; Biswas, S.; Sarkar, D.C.; Sarkar, P.P. Soil Classification from Large Imagery Databases Using a Neuro-Fuzzy Classifier. Can. J. Electr. Comput. Eng. 2016, 39, 333–343. [Google Scholar] [CrossRef] [Scilit]
Meshram, R.A.; Alvi, A.S. Plant Disease Detection by Using Adaptive Neuro-Fuzzy Inference System. Tamap J. Eng. 2021, 2021, 1–10. [Google Scholar] [CrossRef]
Khairunniza-Bejo, S.; Mustaffha, S.; Ismail, W.I.W. Application of artificial neural network in predicting crop yield: A review. J. Food Sci. Technol. 2014, 4, 1. [Google Scholar]
Sharma, R.; Kamble, S.S.; Gunasekaran, A.; Kumar, V.; Kumar, A. A systematic literature review on machine learning applications for sustainable agriculture supply chain performance. Comput. Oper. Res. 2020, 119, 104926. [Google Scholar] [CrossRef] [Scilit]
Chlingaryan, A.; Sukkarieh, S.; Whelan, B. Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review. Comput. Electron. Agric. 2018, 151, 61–69. [Google Scholar] [CrossRef] [Scilit]
Kamilaris, A.; Prenafeta-Boldú, F.X. Deep learning in agriculture: A survey. Comput. Electron. Agric. 2018, 147, 70–90. [Google Scholar] [CrossRef] [Scilit]
Haykin, S. Neural Networks: A Comprehensive Foundation; Prentice Hall: Hoboken, NJ, USA, 1998. [Google Scholar]
Rohani, A.; Abbaspour-Fard, M.H.; Abdolahpour, S. Prediction of tractor repair and maintenance costs using Artificial Neural Network. Expert Syst. Appl. 2011, 38, 8999–9007. [Google Scholar] [CrossRef] [Scilit]
Culclasure, A. Using Neural Networks to Provide Local Weather Forecasts. Master’s Thesis, Georgia Southern University, Statesboro, GA, USA, 2013. [Google Scholar]
Agrawal, R.; Imieliński, T.; Swami, A. Mining association rules between sets of items in large databases. In Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, Washington, DC, USA, 26–28 May 1993. [Google Scholar]
Almadhor, A.; Rauf, H.T.; Lali, M.I.U.; Damaševičius, R.; Alouffi, B.; Alharbi, A. AI-Driven Framework for Recognition of Guava Plant Diseases through Machine Learning from DSLR Camera Sensor Based High Resolution Imagery. Sensors 2021, 21, 3830. [Google Scholar] [CrossRef] [Scilit]
Shahhosseini, M.; Hu, G.; Huber, I.; Archontoulis, S.V. Coupling machine learning and crop modeling improves crop yield prediction in the US Corn Belt. Sci. Rep. 2021, 11, 1606. [Google Scholar] [CrossRef] [Scilit]
Aishwarya, K.; Jabbar, M. Data Mining Analysis for Precision Agriculture: A Comprehensive Survey. ECS Trans. 2022, 107, 17769–17781. [Google Scholar] [CrossRef] [Scilit]
Tabesh, M.; Roozbahani, A.; Roghani, B.; Faghihi, N.R.; Heydarzadeh, R. Risk Assessment of Factors Influencing Non-Revenue Water Using Bayesian Networks and Fuzzy Logic. Water Resour. Manag. 2018, 32, 3647–3670. [Google Scholar] [CrossRef] [Scilit]
Pearl, J. Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference; Morgan Kaufmann Publishers Inc.: San Francisco, CA, USA, 1988. [Google Scholar]
Preetha, M.K.S.; KanagaPriya, K.D.; Dharanipriya, S. Crop rotation and yield analysis using naive ratio classification. Int. J. Sci. Eng. Res. 2017, 8, 29. [Google Scholar]
Rasmussen, S.; Madsen, A.L.; Lund, M. Bayesian Network as a Modelling Tool for Risk Management in Agriculture; IFRO Working Paper; University of Copenhagen, Department of Food and Resource Economics (IFRO): Copenhagen, Denmark, 2013; Available online: http://hdl.handle.net/10419/204359 (accessed on 7 November 2023).
Friedman, N.; Koller, D. Being Bayesian About Network Structure. A Bayesian Approach to Structure Discovery in Bayesian Networks. Mach. Learn. 2003, 50, 95–125. [Google Scholar] [CrossRef] [Scilit]
Mishra, S.; Mishra, D.; Santra, G.H. Adaptive boosting of weak regressors for forecasting of crop production considering climatic variability: An empirical assessment. J. King Saud Univ. Comput. Inf. Sci. 2017, 32, 949–964. [Google Scholar] [CrossRef] [Scilit]
Rumelhart, D.E.; Hinton, G.E.; Williams, R.J. Learning representations by back-propagating errors. Nature 1986, 323, 533–536. [Google Scholar] [CrossRef] [Scilit]
Breiman, L.; Friedman, J.; Olshen, R.; Stone, C. Classification and Regression Trees; CRC Press: Boca Raton, FL, USA, 1984. [Google Scholar]
Kass, G.V. An Exploratory Technique for Investigating Large Quantities of Categorical Data. J. R. Stat. Soc. C Appl. Stat. 1980, 29, 119–127. [Google Scholar] [CrossRef] [Scilit]
Jain, A.K. Data clustering: 50 years beyond K-means. Pattern Recognit. Lett. 2010, 31, 651–666. [Google Scholar] [CrossRef] [Scilit]
LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef] [Scilit]
Shi, X.; Chen, Z.; Wang, H.; Yeung, D.Y.; Wong, W.K.; Woo, W.C. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In Proceedings of the NIPS’15: 28th International Conference on Neural Information Processing Systems—Volume 1, Montreal, QC, Canada, 7–12 December 2015; pp. 802–810. [Google Scholar]
Lippmann, R. An introduction to computing with neural nets. IEEE ASSP Mag. 1987, 4, 4–22. [Google Scholar] [CrossRef] [Scilit]
Salakhutdinov, R.; Hinton, G. Deep boltzmann machines. In Artificial Intelligence and Statistics; Department of ComputerScience, University of Toronto: Toronto, ON, Canada, 2009. [Google Scholar]
Hinton, G.E.; Osindero, S.; Teh, Y.-W. A Fast Learning Algorithm for Deep Belief Nets. Neural Comput. 2006, 18, 1527–1554. [Google Scholar] [CrossRef] [Scilit]
Quinlan, J.R. Induction of decision trees. Mach. Learn. 1986, 1, 81–106. [Google Scholar] [CrossRef] [Scilit]
Iniyan, S.; Jebakumar, R. Mutual Information Feature Selection (MIFS) Based Crop Yield Prediction on Corn and Soybean Crops Using Multilayer Stacked Ensemble Regression (MSER). Wirel. Pers. Commun. 2021, 126, 1935–1964. [Google Scholar] [CrossRef] [Scilit]
Sirsat, M.; Cernadas, E.; Fernández-Delgado, M.; Barro, S. Automatic prediction of village-wise soil fertility for several nutrients in India using a wide range of regression methods. Comput. Electron. Agric. 2018, 154, 120–133. [Google Scholar] [CrossRef] [Scilit]
Alibabaei, K.; Gaspar, P.D.; Lima, T.M.; Campos, R.M.; Girão, I.; Monteiro, J.; Lopes, C.M. A Review of the Challenges of Using Deep Learning Algorithms to Support Decision-Making in Agricultural Activities. Remote Sens. 2022, 14, 638. [Google Scholar] [CrossRef] [Scilit]
Vigneswaran, E.E.; Selvaganesh, M. Decision Support System for Crop Rotation Using Machine Learning. In Proceedings of the 4th IEEE International Conference on Inventive Systems and Control (ICISC), Coimbatore, India, 8–10 January 2020; pp. 925–930. [Google Scholar] [CrossRef] [Scilit]
Niloofar, P.; Francis, D.P.; Lazarova-Molnar, S.; Vulpe, A.; Vochin, M.-C.; Suciu, G.; Balanescu, M.; Anestis, V.; Bartzanas, T. Data-driven decision support in livestock farming for improved animal health, welfare and greenhouse gas emissions: Overview and challenges. Comput. Electron. Agric. 2021, 190, 106406. [Google Scholar] [CrossRef] [Scilit]
Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016. [Google Scholar]
Bengio, Y.; Courville, A.; Vincent, P. Representation Learning: A Review and New Perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 2013, 35, 1798–1828. [Google Scholar] [CrossRef] [Scilit]
Huang, G.-B.; Zhou, H.; Ding, X.; Zhang, R. Extreme Learning Machine for Regression and Multiclass Classification. IEEE Trans. Syst. Man Cybern. Part B Cybern. 2012, 42, 513–529. [Google Scholar] [CrossRef] [Scilit]
Suchithra, M.; Pai, M.L. Improving the prediction accuracy of soil nutrient classification by optimizing extreme learning machine parameters. Inf. Process. Agric. 2019, 7, 72–82. [Google Scholar] [CrossRef] [Scilit]
Masri, D.; Woon, W.L.; Aung, Z. Soil property prediction: An extreme learning machine approach. In Proceedings of the Neural Information Processing: 22nd International Conference, ICONIP 2015, Istanbul, Turkey, 9–12 November 2015; Springer: Berlin/Heidelberg, Germany, 2015; pp. 18–27. [Google Scholar] [CrossRef] [Scilit]
Dietterich, T.G. Ensemble Methods in Machine Learning. In Proceedings of the International Workshop on Multiple Classifier Systems, Cagliari, Italy, 9–11 June 2000; pp. 1–15. [Google Scholar] [CrossRef] [Scilit]
Vásquez, R.P.; Aguilar-Lasserre, A.A.; López-Segura, M.V.; Rivero, L.C.; Rodríguez-Duran, A.A.; Rojas-Luna, M.A. Expert system based on a fuzzy logic model for the analysis of the sustainable livestock production dynamic system. Comput. Electron. Agric. 2019, 161, 104–120. [Google Scholar] [CrossRef] [Scilit]
Dos Reis, J.C.; Rodrigues, G.S.; de Barros, I.; de Aragão Ribeiro Rodrigues, R.; Garrett, R.D.; Valentim, J.F.; Kamoi, M.Y.T.; Michetti, M.; Wruck, F.J.; Rodrigues-Filho, S. Fuzzy logic indicators for the assessment of farming sustainability strategies in a tropical agricultural frontier. Agron. Sustain. Dev. 2023, 43, 8. [Google Scholar] [CrossRef] [Scilit]
Zadeh, L.A. Fuzzy sets. Inf. Control 1965, 8, 338–353. [Google Scholar] [CrossRef] [Scilit]
Holland, J.H. Genetic algorithms. Sci. Am. 1992, 267, 66–73. [Google Scholar] [CrossRef] [Scilit]
Hadi, M.H.S.; Gonzalez-Andujar, J. Comparison of fitting weed seedling emergence models with nonlinear regression and genetic algorithm. Comput. Electron. Agric. 2009, 65, 19–25. [Google Scholar] [CrossRef] [Scilit]
Friedman, J.H. Greedy function approximation: A gradient boosting machine. Ann. Stat. 2001, 29, 1189–1232. [Google Scholar] [CrossRef] [Scilit]
Reynolds, D.A. Gaussian mixture models. Encycl. Biom. 2009, 741, 659–663. [Google Scholar]
Domingos, P.; Pazzani, M. On the Optimality of the Simple Bayesian Classifier under Zero-One Loss. Mach. Learn. 1997, 29, 103–130. [Google Scholar] [CrossRef] [Scilit]
Zhu, S.; Yuan, X.; Xu, Z.; Luo, X.; Zhang, H. Gaussian mixture model coupled recurrent neural networks for wind speed interval forecast. Energy Convers. Manag. 2019, 198, 111772. [Google Scholar] [CrossRef] [Scilit]
Pinder, T.; Dodd, D. GPJax: A Gaussian Process Framework in JAX. J. Open Source Softw. 2022, 7, 4455. [Google Scholar] [CrossRef] [Scilit]
Mihoub, R.; Chabour, N.; Guermoui, M. Modeling soil temperature based on Gaussian process regression in a semi-arid-climate, case study Ghardaia, Algeria. Geomech. Geophys. Geo Energy Geo Resour. 2016, 2, 397–403. [Google Scholar] [CrossRef] [Scilit]
Shi, X.M. A Brief Review on Models of Animal Tracking in Video. Appl. Mech. Mater. 2013, 303–306, 1365–1368. [Google Scholar] [CrossRef] [Scilit]
Rabiner, L. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 1989, 77, 257–286. [Google Scholar] [CrossRef] [Scilit]
Patterson, T.A.; Basson, M.; Bravington, M.V.; Gunn, J.S. Classifying movement behaviour in relation to environmental conditions using hidden Markov models. J. Anim. Ecol. 2009, 78, 1113–1123. [Google Scholar] [CrossRef] [Scilit]
Gonzalez, R.; Woods, R.; Eddins, S. Segmentation Using the Watershed Algorithm; Pearson Prentice Hall: Upper Saddle River, NJ, USA, 2004; pp. 417–425. [Google Scholar]
Cover, T.; Hart, P. Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 1967, 13, 21–27. [Google Scholar] [CrossRef] [Scilit]
Suleymanov, A.; Tuktarova, I.; Belan, L.; Suleymanov, R.; Gabbasova, I.; Araslanova, L. Spatial prediction of soil properties using random forest, k-nearest neighbors and cubist approaches in the foothills of the Ural Mountains, Russia. Model. Earth Syst. Environ. 2023, 8, 3461–3471. [Google Scholar] [CrossRef] [Scilit]
Belkhiri, L. Spatial and temporal variability of water stress risk in the Kebir Rhumel Basin, Algeria. Agric. Water Manag. 2021, 253, 106937. [Google Scholar] [CrossRef] [Scilit]
Gargade, A.; Khandekar, S. Custard apple leaf parameter analysis, leaf diseases, and nutritional deficiencies detection using machine learning. In Advances in Signal and Data Processing: Select Proceedings of ICSDP 2019; Springer: Singapore, 2021. [Google Scholar] [CrossRef] [Scilit]
Garcia, R.; Aguilar, J.; Toro, M.; Jimenez, M. Weight-Identification Model of Cattle Using Machine-Learning Techniques for Anomaly Detection. In Proceedings of the 2021 IEEE Symposium Series on Computational Intelligence (SSCI), Orlando, FL, USA, 5–7 December 2021. [Google Scholar] [CrossRef] [Scilit]
Montgomery, D.C.; Peck, E.A.; Vining, G.G. Introduction to Linear Regression Analysis; John Wiley & Sons: Hoboken, NJ, USA, 2021. [Google Scholar]
Hosmer, D.W., Jr.; Lemeshow, S.; Sturdivant, R.X. Applied Logistic Regression; John Wiley & Sons: Hoboken, NJ, USA, 2013; Volume 398. [Google Scholar]
Park, S.-H.; Lee, B.-Y.; Kim, M.-J.; Sang, W.; Seo, M.C.; Baek, J.-K.; Yang, J.E.; Mo, C. Development of a Soil Moisture Prediction Model Based on Recurrent Neural Network Long Short-Term Memory (RNN-LSTM) in Soybean Cultivation. Sensors 2023, 23, 1976. [Google Scholar] [CrossRef] [Scilit]
Kong, Y.-L.; Huang, Q.; Wang, C.; Chen, J.; Chen, J.; He, D. Long Short-Term Memory Neural Networks for Online Disturbance Detection in Satellite Image Time Series. Remote Sens. 2018, 10, 452. [Google Scholar] [CrossRef] [Scilit]
Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef] [Scilit]
Puterman, M.L. Markov Decision Processes: Discrete Stochastic Dynamic Programming; John Wiley & Sons: Hoboken, NJ, USA, 2014. [Google Scholar]
Deb, K.; Pratap, A.; Agarwal, S.; Meyarivan, T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 2002, 6, 182–197. [Google Scholar] [CrossRef] [Scilit]
Hair, J.R.; Anderson, R.E.; Tatham, R.L.; Black, W.C. Multivariate Data Analysis; PrentiCe-Hall Inc.: Upper Saddle River, NJ, USA, 1998. [Google Scholar]
Rish, I. An empirical study of the naive Bayes classifier. In Proceedings of the IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, Seattle, WA, USA, 4–10 August 2001. [Google Scholar]
Kennedy, J.; Eberhart, R. Particle Swarm Optimization. In Proceedings of the ICNN’95—International Conference on Neural Networks, Perth, Australia, 27 November–1 December 1995; Volume 4, pp. 1942–1948. [Google Scholar] [CrossRef] [Scilit]
Jolliffe, I.T. Principal component analysis. Technometrics 2003, 45, 276. [Google Scholar]
Wold, S.; Esbensen, K.; Geladi, P. Principal component analysis. Chemom. Intell. Lab. Syst. 1987, 2, 37–52. [Google Scholar] [CrossRef] [Scilit]
Breiman, L. Random forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef] [Scilit]
Sutton, R.S.; Barto, A.G. Reinforcement Learning: An Introduction; MIT Press: Cambridge, MA, USA, 2017. [Google Scholar]
Manogaran, G.; Hsu, C.-H.; Rawal, B.S.; Muthu, B.A.; Mavromoustakis, C.X.; Mastorakis, G. ISOF: Information Scheduling and Optimization Framework for Improving the Performance of Agriculture Systems Aided by Industry 4.0. IEEE Internet Things J. 2020, 8, 3120–3129. [Google Scholar] [CrossRef] [Scilit]
Gao, G.; Wang, M.; Huang, H.; Tang, W. Agricultural Irrigation Area Prediction Based on Improved Random Forest Model. 2021. Available online: https://www.researchgate.net/publication/348965642_Agricultural_Irrigation_Area_Prediction_Based_on_Improved_Random_Forest_Model (accessed on 7 November 2023).
Zhang, Y.; Sui, B.; Shen, H.; Ouyang, L. Mapping stocks of soil total nitrogen using remote sensing data: A comparison of random forest models with different predictors. Comput. Electron. Agric. 2019, 160, 23–30. [Google Scholar] [CrossRef] [Scilit]
Elavarasan, D.; Vincent, P.M.D.R. A reinforced random forest model for enhanced crop yield prediction by integrating agrarian parameters. J. Ambient. Intell. Humaniz. Comput. 2021, 12, 10009–10022. [Google Scholar] [CrossRef] [Scilit]
Paul, R.K.; Yeasin; Kumar, P.; Kumar, P.; Balasubramanian, M.; Roy, H.S.; Paul, A.K.; Gupta, A. Machine learning techniques for forecasting agricultural prices: A case of brinjal in Odisha, India. PLoS ONE 2022, 17, e0270553. [Google Scholar] [CrossRef] [Scilit]
Schmidhuber, J. Deep Learning in Neural Networks: An Overview. Neural Netw. 2015, 61, 85–117. [Google Scholar] [CrossRef] [Scilit]
Cortes, C.; Vapnik, V. Support-vector networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef] [Scilit]
Safavi, H.R.; Esmikhani, M. Conjunctive Use of Surface Water and Groundwater: Application of Support Vector Machines (SVMs) and Genetic Algorithms. Water Resour. Manag. 2013, 27, 2623–2644. [Google Scholar] [CrossRef] [Scilit]
Shams, M.Y.; Elzeki, O.M.; Elfattah, M.A.; Abouelmagd, L.M.; Darwish, A.; Hassanien, A.E. Impact of COVID-19 Pandemic on Diet Prediction and Patient Health Based on Support Vector Machine. In Advanced Machine Learning Technologies and Applications. AMLTA 2021. Advances in Intelligent Systems and Computing; Springer: Cham, Switzerland, 2021; Volume 1339. [Google Scholar] [CrossRef] [Scilit]
Behmann, J.; Mahlein, A.-K.; Rumpf, T.; Römer, C.; Plümer, L. A review of advanced machine learning methods for the detection of biotic stress in precision crop protection. Precis. Agric. 2014, 16, 239–260. [Google Scholar] [CrossRef] [Scilit]
Shafiee, S.; Lied, L.M.; Burud, I.; Dieseth, J.A.; Alsheikh, M.; Lillemo, M. Sequential forward selection and support vector regression in comparison to LASSO regression for spring wheat yield prediction based on UAV imagery. Comput. Electron. Agric. 2021, 183, 106036. [Google Scholar] [CrossRef] [Scilit]
Drucker, H.; Burges, C.J.; Kaufman, L.; Smola, A.; Vapnik, V. Support vector regression machines. In Proceedings of the NIPS’96: 9th International Conference on Neural Information Processing Systems, Denver, CO, USA, 3–5 December 1996; pp. 155–161. [Google Scholar]
Kok, Z.H.; Shariff, A.R.M.; Alfatni, M.S.M.; Khairunniza-Bejo, S. Support Vector Machine in Precision Agriculture: A review. Comput. Electron. Agric. 2021, 191, 106546. [Google Scholar] [CrossRef] [Scilit]
Chen, J.; Zhang, D.; Nanehkaran, Y.A. Identifying plant diseases using deep transfer learning and enhanced lightweight network. Multimed. Tools Appl. 2020, 79, 31497–31515. [Google Scholar] [CrossRef] [Scilit]
Olsson, S.; Ameen, M.; Bajpai, S.; Gudasalamani, G.; Gajjar, C.; Gupta, S.; Hvilshøj, S.; Krishnakumar, J.; Lobo, C.; Mukherjee, R.; et al. Framework for a Collective Definition of Regenerative Agriculture in India. Ecol. Econ. Soc. INSEE J. 2022, 5, 23–30. [Google Scholar] [CrossRef] [Scilit]
Gordon, E.; Davila, F.; Riedy, C. Regenerative agriculture: A potentially transformative storyline shared by nine discourses. Sustain. Sci. 2023, 18, 1833–1849. [Google Scholar] [CrossRef] [Scilit]
Burns, E.A. Regenerative Agriculture: Farmer motivation, environment and climate improvement. Policy Q. 2021, 17, 54–60. [Google Scholar] [CrossRef] [Scilit]
Montgomery, D.R.; Biklé, A.; Archuleta, R.; Brown, P.; Jordan, J. Soil health and nutrient density: Preliminary comparison of regenerative and conventional farming. PeerJ 2022, 10, e12848. [Google Scholar] [CrossRef] [Scilit]
Sangjan, W.; Carpenter-Boggs, L.A.; Hudson, T.D.; Sankaran, S. Pasture Productivity Assessment under Mob Grazing and Fertility Management Using Satellite and UAS Imagery. Drones 2022, 6, 232. [Google Scholar] [CrossRef] [Scilit]
Bell, L.W.; Moore, A.D. Integrated crop–livestock systems in Australian agriculture: Trends, drivers and implications. Agric. Syst. 2012, 111, 1–12. [Google Scholar] [CrossRef] [Scilit]
Moore, A.D. Opportunities and trade-offs in dual-purpose cereals across the southern Australian mixed-farming zone: A modelling study. Anim. Prod. Sci. 2009, 49, 759–768. [Google Scholar] [CrossRef] [Scilit]
Liang, M.; Liang, C.; Hautier, Y.; Wilcox, K.R.; Wang, S. Grazing-induced biodiversity loss impairs grassland ecosystem stability at multiple scales. Ecol. Lett. 2021, 24, 2054–2064. [Google Scholar] [CrossRef] [Scilit]
Guardia, G.; Tellez-Rio, A.; García-Marco, S.; Martin-Lammerding, D.; Tenorio, J.L.; Ibáñez, M.; Vallejo, A. Effect of tillage and crop (cereal versus legume) on greenhouse gas emissions and Global Warming Potential in a non-irrigated Mediterranean field. Agric. Ecosyst. Environ. 2016, 221, 187–197. [Google Scholar] [CrossRef] [Scilit]
Lal, R. Carbon sequestration in dryland agriculture. Chall. Strateg. Dryland Agric. 2004, 32, 315–334. [Google Scholar] [CrossRef] [Scilit]
Kirkegaard, J.A.; Conyers, M.K.; Hunt, J.R.; Kirkby, C.A.; Watt, M.; Rebetzke, G.J. Sense and nonsense in conservation agriculture: Principles, pragmatism and productivity in Australian mixed farming systems. Agric. Ecosyst. Environ. 2013, 187, 133–145. [Google Scholar] [CrossRef] [Scilit]
Thomas, D.T.; Flohr, B.M.; Monjardino, M.; Loi, A.; Llewellyn, R.S.; Lawes, R.A.; Norman, H.C. Selecting higher nutritive value annual pasture legumes increases the profitability of sheep production. Agric. Syst. 2021, 194, 103272. [Google Scholar] [CrossRef] [Scilit]
Bell, L.; Moore, A.; Thomas, D. Diversified crop-livestock farms are risk-efficient in the face of price and production variability. Agric. Syst. 2021, 189, 103050. [Google Scholar] [CrossRef] [Scilit]
Donnelly, J.R.; Simpson, R.J.; Salmon, L.; Moore, A.D.; Freer, M.; Dove, H. Forage-livestock models for the Australian livestock industry. In Agricultural System Models in Field Research and Technology Transfer; CRC Press: Boca Raton, FL, USA, 2016; pp. 9–32. [Google Scholar]
Moore, A.; Holzworth, D.; Herrmann, N.; Huth, N.; Robertson, M. The Common Modelling Protocol: A hierarchical framework for simulation of agricultural and environmental systems. Agric. Syst. 2007, 95, 37–48. [Google Scholar] [CrossRef] [Scilit]
Hughes, N.; Soh, W.Y.; Lawson, K.; Lu, M. Improving the performance of micro-simulation models with machine learning: The case of Australian farms. Econ. Model. 2022, 115, 105957. [Google Scholar] [CrossRef] [Scilit]
Thomas, D.T.; Sanderman, J.; Eady, S.J.; Masters, D.G.; Sanford, P. Whole Farm Net Greenhouse Gas Abatement from Establishing Kikuyu-Based Perennial Pastures in South-Western Australia. Animals 2012, 2, 316–330. [Google Scholar] [CrossRef] [Scilit]
Schreefel, L.; de Boer, I.; Timler, C.; Groot, J.; Zwetsloot, M.; Creamer, R.; Schrijver, A.P.; van Zanten, H.; Schulte, R. How to make regenerative practices work on the farm: A modelling framework. Agric. Syst. 2022, 198, 103371. [Google Scholar] [CrossRef] [Scilit]
Jayasinghe, S.L.; Kumar, L.; Sandamali, J. Assessment of Potential Land Suitability for Tea (Camellia sinensis (L.) O. Kuntze) in Sri Lanka Using a GIS-Based Multi-Criteria Approach. Agriculture 2019, 9, 148. [Google Scholar] [CrossRef] [Scilit]
Al-Adhaileh, M.H.; Aldhyani, T.H. Artificial intelligence framework for modeling and predicting crop yield to enhance food security in Saudi Arabia. PeerJ Comput. Sci. 2022, 8, e1104. [Google Scholar] [CrossRef] [Scilit] [PubMed]
Gambelli, D.; Bruschi, V. A Bayesian network to predict the probability of organic farms’ exit from the sector: A case study from Marche, Italy. Comput. Electron. Agric. 2010, 71, 22–31. [Google Scholar] [CrossRef] [Scilit]
Lawes, R.; Mata, G.; Richetti, J.; Fletcher, A.; Herrmann, C. Using remote sensing, process-based crop models, and machine learning to evaluate crop rotations across 20 million hectares in Western Australia. Agron. Sustain. Dev. 2022, 42, 120. [Google Scholar] [CrossRef] [Scilit]
Kingwell, R.; Pannell, D. Economic trends and drivers affecting the Wheatbelt of Western Australia to 2030. Aust. J. Agric. Res. 2005, 56, 553–561. [Google Scholar] [CrossRef] [Scilit]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

Article Metrics

Citations

Article Access Statistics

Journal Statistics

Multiple requests from the same IP address are counted as one view.