Search Results (983)

Weather forecasts are crucial in agricultural decision-making. The first objective was to assess the performance of eight weather forecast models for predicting five key meteorological variables in agriculture: air temperature, humidity, wind speed, global radiation, and precipitation. The tested models were ICON-D2, AROME, HARMONIE, MAR, GFS, and three models from the ECMWF: the deterministic model (HRES), the ensemble model (ENS), and the deep learning-based model (AIFS). The forecasts were compared over a six-month period with observations from 22 weather stations located in Wallonia (Belgium). AIFS achieved the lowest RMSE for predicting global radiation. For lead times up to 48 h, ICON-D2 had the lowest RMSE for wind speed; ICON-D2 and AIFS showed the lowest RMSE for air temperature and humidity, and AIFS and HRES performed best at predicting rainy versus non-rainy days. For lead times beyond 48 h, AIFS had the lowest RMSE for predicting air temperature and humidity, and ENS had the lowest RMSE for predicting wind speed. The second objective was to evaluate the suitability of these forecasts to feed a simple agricultural decision-support tool, helping farmers identify the optimal time windows for spraying plant protection products. ICON-D2 and AIFS yielded the most reliable recommendations. Full article

Groundwater level fluctuations play a critical role in shaping hydrological extremes in flat sedimentary landscapes, where shallow water table depth (WTD) and strong surface-subsurface connectivity modulate the impacts of floods and droughts. The Western Pampean Plain (Argentina) exemplifies these dynamics; however, accurate modeling is often hindered by the lack of continuous in situ monitoring. In this context, manual WTD measurements collected by local farmers represent an underexploited source of information for modeling. In this study, we developed a Random Forest framework integrating farmer-operated observations with climatic and satellite-derived data and evaluated its ability to reconstruct and predict WTD. We tested seven modeling strategies, integrating: (i) climatic variables (including effects up to 15 months); (ii) high-resolution satellite-derived Surface Water Cover Index (SWCI) from Landsat; and (iii) coarse-resolution Terrestrial Water Storage Anomalies (TWSA) from GRACE. The best-performing model integrated climatic variables and SWCI, yielding strong reconstruction (R² = 0.861, RMSE = 0.266 m) and robust prediction (R² = 0.752, RMSE = 0.344 m) performances under cross-validation and rolling-origin validation, respectively. Model interpretation revealed SWCI as the dominant predictor, reflecting the strong surface-subsurface connectivity that characterizes this environment. This study provides a practical framework that integrates farmer-operated groundwater monitoring with freely available satellite observations to support agricultural decision-making in flood and drought risk management across flat sedimentary landscapes. Full article

Under the dual pressures of increasing fragmentation of farmland and profound changes in the agricultural labor force, the problem of abandoned farmland in rural China has become increasingly prominent, posing a serious threat to food security. Previous studies have mainly focused on the impact of socioeconomic factors on farmland abandonment behavior; however, there remains a lack of systematic investigations into the underlying mechanisms through which farmland fragmentation influences farmers’ land-use decisions. Therefore, this study applies behavioral theory to construct a “fragmentation–mechanization–abandonment” analytical framework to analyze the potential mechanisms of land-use decision-making. Using micro-level household survey data from multiple provinces across China, we conduct empirical tests through Probit models and Karlson Holm and Breen (KHB) mediation effect analysis. Our findings include: (1) Farmland fragmentation significantly increases the probability of farmland abandonment, which remains robust across multiple tests. (2) Farmland fragmentation indirectly influences abandonment behavior through the mediating variable of agricultural mechanization level, but this mechanism plays only a partial mediating role. (3) Heterogeneity tests indicate that the positive effect of farmland fragmentation is significantly stronger among households with low access to finance than among those with high access to finance. This influence is also stronger among households with high farmland accessibility. This study indicates that abandonment governance requires moving beyond a singular focus on land consolidation and shifting toward a synergistic approach that combines differentiated regional strategies with targeted support for smallholders. From a micro-mechanism perspective, this study provides empirical evidence for targeted implementation of land consolidation and livelihood support for smallholders, offering important policy implications for achieving agricultural modernization. Full article

Shifting climatic conditions challenge simplified, yield-oriented agriculture, particularly in fragile mountain regions. In the Ecuadorian Andes, agriculture functions as a socio-ecological system shaped by biocultural relationships integrating production, agrobiodiversity, and farmer decision-making. This study examines how climate variability interacts with crop phenology and management practices within ancestral associated cropping systems (chakras). The analysis focuses on maize, common bean, faba bean, and potato during the 2024–2025 agricultural cycle in Imantag, Ecuador. A total of 30 native, introduced, and improved varieties were sown in traditional rows (wachos) and monitored within a single 420.8 m² Andean chakra. Using multiple ordinary least squares (OLS) regression (n = 30; R² = 0.440, adj. R² = 0.351, F (4,25) = 4.914, p = 0.005), results show that maize significantly outperformed the faba bean reference group (β = 20.34, p = 0.017), while common bean showed intermediate performance (β = 15.31, p = 0.048). Seed mass at planting was positively associated with relative yield (β = 6.71, p = 0.069), highlighting early-stage management decisions. Elevated maximum temperatures during maturation negatively affected yield (r = −0.42, p = 0.020), while accumulated precipitation had a positive effect (r = +0.45, p = 0.014). Model quality criteria, including VIF diagnostics (max. VIF = 3.37), Shapiro–Wilk residual normality test (W = 0.983, p = 0.896), and cross-validation using Ridge and Lasso regression, confirm the robustness of the statistical findings. These findings demonstrate that chakras function as adaptive socioecological systems that enhance productivity, agrobiodiversity conservation, and resilience under climate variability. Full article

Artificial intelligence (AI) is increasingly applied in agriculture to support data-driven decision-making, improve productivity, and enhance resource management. Small-scale farmers, who produce a significant share of the world’s food yet often operate under resource constraints, may particularly benefit from these technologies. However, it remains unclear how AI research addresses the needs of small-scale farming systems and the extent to which farmers directly interact with AI tools. This study conducts a systematic literature review to examine the applications, impacts, and challenges of AI in small-scale agriculture. The review followed the PRISMA 2020 guidelines and applied a structured review methodology, using the Web of Science, Scopus, and EBSCOhost databases. A total of 182 studies were identified and analyzed. The results show a rapid increase in publications after 2020, with research concentrated mainly in Africa and Asia. Most studies focus on technical AI applications such as plant disease detection, crop yield prediction, crop classification, and environmental monitoring, commonly using machine learning and deep learning techniques. However, only a small number of studies examine farmers’ direct interaction with AI systems, including adoption, perceptions, and practical usage. This imbalance indicates that the literature remains largely technology-driven rather than farmer-centred. The review highlights important research gaps, particularly in farmer engagement, integrated farm management applications, and the translation of AI prototypes into scalable solutions. Future research should prioritize participatory approaches and context-sensitive AI systems to ensure that technological advances effectively support small-scale farmers and sustainable agricultural development. Full article

Water scarcity critically constrains sustainable cotton production in arid Xinjiang, China. Conventional irrigation management often relies on empirical decision-making, resulting in a dynamic mismatch between water supply and the growth-stage-specific water demands of cotton, thereby constraining the full potential of agricultural water resources. A transition from experience-based irrigation to quantitative parameter-driven smart decision-making is urgently required. Smart irrigation requires soil moisture thresholds tailored to different growth stages to serve as irrigation decision parameters. To identify refined irrigation parameters that reconcile high yield with enhanced water productivity, this study conducted a two-year field experiment in northern Xinjiang, imposing distinct lower and upper soil moisture limits (expressed as % of field capacity, FC) across seedling, budding, flowering and boll, and boll opening stages. Treatment effects on soil moisture dynamics, plant growth, yield, water use efficiency (WUE), and irrigation water productivity (IWP) were systematically evaluated. Synergistic optimization of yield and WUE identified optimal thresholds: lower limits of 50–54% FC at seedling, 56–61% FC at budding, 74–76% FC at flowering and boll, and 53–57% FC at boll opening; upper limits were 100% FC for all stages except boll opening, set at 85% FC. Relative to conventional farmer irrigation decision-making, threshold-based irrigation saved 13.41% water, increased seed cotton yield by 10.72%, and enhanced WUE and IWP by 42.31% and 28.10%, respectively. This study provides irrigation decision parameters derived from soil moisture thresholds across different growth stages and planned wetted layer depths, offering directly embeddable engineering inputs for smart drip irrigation platforms to enable precise, demand-driven water management and establish a technical foundation for precision irrigation in the arid cotton fields of Xinjiang. Full article

Coffee is a major export earner for Uganda, raking in over USD 2 billion in 2025. The global price of coffee is tagged to the perceived quality in the cup which in turn is affected by the chemical composition of the green bean. Breeding for market-preferred Arabica coffee varieties is a major objective of coffee breeding programs. Determination of coffee bean chemical constituents is routinely done through expensive, slow and tedious laboratory procedures, making it unsustainable of resource-limited public sector coffee breeding programs. Here, we demonstrate the use of near-infrared spectroscopy (NIRS) and the machine learning algorithms partial least squares (PLS), random forest (RF) and support vector machine (SVM) for the prediction of caffeine, protein and trigonelline in Arabica coffee. NIRS provides a fast, accurate and reliable method of simultaneously predicting multiple sample constituents. Ripe coffee cherries were picked from 172 farmers’ fields, air dried in the laboratory at room temperature and processed to green beans. NIRS spectra were taken on the milled green bean at 400–2500 nm, with a 0.5 nanometer (nm) step. Reference data for caffeine, protein and trigonelline were collected on the same sample scanned with NIRS. A set of 12 spectral pretreatments were applied prior to making calibrations with the PLS, RF and SVM algorithms and 70% of the data as a training set and 30% as a test set. Caffeine content of reference samples ranged from 1.94–3.0 g/100 g, protein content ranged from 11.16–15.94% while trigonelline ranged from 0.94–1.23 g/100 g. The best calibrations for all algorithms and analytes were obtained using raw (untreated) spectra, which gave the same results as the Savitzky–Golay (SG) pretreatment. For caffeine, the best model (R²p = 0.89, RMSEP = 0.007, RPD = 3.34) was obtained with the SVM algorithm, while for protein, the best model (R²p = 0.98, RMSEP = 0.14, RPD = 6.92) was obtained using the PLS algorithm. Finally, for trigonelline, all three models had very high prediction accuracies (R²p = 0.98–0.99, RMSEP = 0.007–0.009, RPD = 8.53–10.52). Collectively, these results demonstrate the potential of using NIRS for rapid and simultaneous prediction of coffee green bean constituents to aid selection decisions. Full article

The sustainable management of chemical fumigants in intensive horticulture represents one of the most complex challenges in European agricultural policy, requiring the integration of agronomic knowledge, regulatory frameworks, economic viability, and stakeholder perspectives. This study proposes and tests a multi-phase consultation methodology designed to bridge the gap between individual expert knowledge and collective, evidence-based consensus, moving from qualitative field-based elicitation to structured multidisciplinary engagement and incorporating both scientific data and practical experience. A total of 72 experts were involved across two phases. In phase 1, in-depth face-to-face interviews (n = 18) captured field-level knowledge on integrated pest management strategies, risk perception, and decision-making criteria, including the economic sustainability of production systems, a dimension prioritized in the European Commission’s Vision for Agriculture and Food. Phase 2 consisted of a one-day multistakeholder event (n = 54)—bringing together researchers, regulators, industry representatives, and farmers—to confront qualitative findings with experimental data on operator safety, groundwater protection, and consumer residues. This deliberate transition from individual perception to informed, shared consensus represents the methodological core of the approach and its most distinctive contribution. The phase 1 results showed that the majority of experts considered chemical fumigants currently indispensable, while recognizing complementary strategies—particularly solarization and natural substances—as valuable supporting tools. The phase 2 experimental data confirmed operator exposure below regulatory thresholds, no groundwater contamination under professional application conditions, and the absence of detectable residues in treated crops. The results demonstrate that this structured consultation can generate actionable knowledge for integrated nematode and soil-borne disease management, with a methodology replicable across other complex regulatory and agronomic contexts within the European framework. Full article

In sub-Saharan Africa, the sustainability of smallholder farming systems is threatened by climate change. Women farmers are often disproportionately affected. These disproportionate impacts are linked to gender-based inequities like limited decision-making power and resource constraints, which limit women’s adaptive capacity. Previous research has examined inequities in agriculture generally, as well as women farmers’ adaptation to climate change. However, relatively few studies have explicitly focused on the experiences of women who are the primary farmers. Intersectional research is also limited. This paper presents the results of a scoping review to identify how climate change affects women smallholder farmers and how they adapt. The review identified 41 studies between 2014 and 2024. The most frequently identified vulnerability factors were access to credit, social and cultural norms, and land issues (e.g., tenure issues). Few studies took an explicitly intersectional approach. The findings suggest the need for support that targets the challenges faced by women smallholders. More intersectional research is needed to examine how gendered impacts are shaped by other forms of inequality and inhibit sustainable livelihood options. The review revealed a pervasive patriarchal assumption in which dual-headed households are often described as “male-headed”. Revising such discourses can support women’s adaptive agency in the face of future climate challenges. These findings have direct implications for the sustainability of smallholder farming systems and rural livelihoods in the region, emphasizing the need for gender-responsive approaches to sustainable development in sub-Saharan Africa. Full article

The rising global population has heightened food demand, placing pressure on agricultural systems, particularly in water-scarce regions such as South Africa. Smallholder farmers, essential to the sector, face climatic variability and resource constraints, necessitating innovative solutions to enhance sustainability and productivity. This study evaluates unmanned aerial vehicles (UAVs) for generating spatially explicit evapotranspiration (ET) estimates in a small-scale sugarcane field, supporting precision water management. Vegetation indices (VIs) derived from UAV-based multispectral imagery were used to predict actual ET (ET_a) and validated against eddy covariance measurements. Five models were assessed, including Normalised Difference Vegetation Index (NDVI)-based and Enhanced Vegetation Index (EVI)-based approaches. Machine learning was used to relate crop coefficients (K_c) to NDVI, enabling improved estimation. The two-band EVI (EVI2) model achieved the highest accuracy, with an R² of 0.63, an RMSE of 0.67, and an MAE of 0.52. ET-VI approaches, particularly EVI2, require lower data and technical complexity, making them suitable for smallholder systems. However, reducing dependence on in situ data remains essential to improve accessibility of remote sensing approaches for agricultural water management in resource-limited environments. These findings demonstrate the potential of UAV-based ET_a modelling to support field-scale irrigation decision-making while highlighting the need for further refinement to improve operational applicability across diverse smallholder farming contexts and beyond. Full article

Choosing the most suitable tractor is a complex and high-stakes decision where technical performance, financial capability, and sustainability considerations must be balanced. However, tractor selection in existing studies lacks objective, sustainability-oriented evaluation frameworks, leaving farmers vulnerable to potentially poor investments with long-term economic, operational, and environmental impacts. Therefore, this research proposes a software-based Decision Support System (DSS) that incorporates objective multi-criteria decision-making (MCDM) models within a management control perspective focused on sustainability and provides a clear, data-driven method for tractor selection for small farmers. Four popular tractor models in Egypt were selected for evaluation based on three criteria related to sustainability: power (C1), purchase price (C2), and availability of maintenance and spare parts (C3). Subsequently, a DSS was implemented using Python, and five MCDM methods—CRITIC, MEREC, Entropy, Standard Deviation (SD), and TOPSIS—were used to select the tractor that best meets sustainability objectives. The findings indicate that tractor T2, which had the lowest purchase price (USD 12,390) and enough power (60 HP), was the best-rated tractor. The impact of each criterion varied by method: C1 was the most important in the Entropy method (0.3657), while C2 was the most important in the CRITIC (0.5552), MEREC (0.3432), and SD (0.5938) weightings. The proposed DSS improves transparency and supports more informed, evidence-based decisions in agricultural mechanization. Overall, the system offers a practical and scalable tool that helps smallholder farmers and policymakers make sustainable tractor choices, contributing to progress toward SDGs 2, 7, 12, and 13. Full article

The shift to circular agrosystems necessitates using new ideas like sustainable biochar, which provides many eco-beneficial attributes like enhancing soil fertility, storing atmospheric carbon dioxide, and retaining soil moisture. However, there is still a small number of farmers worldwide (particularly those located in low-income countries) adopting biochar. Accordingly, this research is focused primarily on determining how factors affecting behavior will influence the decision of wheat producers in Marvdasht County, in Iran’s Fars Province, to use biochar as a circular technology for farming. The study will focus on addressing issues related to environmental challenges (e.g., degradation of soil and drought) through the implementation of resource-efficient, sustainable agricultural technologies. The intent of this paper was to research the behavioral characteristics associated with wheat farmers who choose to use biochar in the city of Marvdasht, Fars Region, Iran, using a new Theory of Planned Behavior (TPB). The model is theoretically enriched through the inclusion of personal norms and connectedness to the land, allowing for a more comprehensive understanding of pro-environmental decision-making. Data was collected from a total of 386 wheat farmers through the use of a structured survey. The data was analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with the software Smart-PLS 3.0. The results reveal that attitude (β = 0.342, p < 0.001) and personal norms (β = 0.278, p < 0.001) are the strongest predictors of behavioral intention, while perceived behavioral control showed a weaker but significant effect (β = 0.178, p = 0.049). Subjective norms do not have a significant direct effect (β = 0.115, p = 0.199) but significantly influence intention indirectly through personal norms (β = 0.100, p < 0.001). Furthermore, connectedness to the land strongly affects personal norms (β = 0.420, p < 0.001) and exerts a significant indirect effect on intention (β = 0.117, p < 0.001), highlighting the importance of emotional attachment to land. The findings are significant because they demonstrated that farmers’ biochar adoption decisions are shaped not only by rational evaluations but also by moral obligations and emotional relationships with land. This study makes significant theoretical contributions by extending TPB with moral and relational constructs and empirically demonstrating their mediating roles in agricultural innovation adoption. The novelty of this study lies in integrating personal norms and connectedness to the land into the TPB framework to explain biochar adoption behavior within the context of circular agriculture in a developing country. Practically, the findings provide evidence-based insights for designing policies that integrate cognitive, ethical, and emotional drivers to promote biochar adoption and advance circular agriculture. Specifically, policymakers and extension agencies should prioritize behavioral-level strategies such as awareness campaigns, farmer training programs, and community-based initiatives that strengthen positive attitudes, environmental responsibility, and farmers’ emotional connection to land in order to enhance biochar adoption. Full article

Climate change intensifies hydrological variability and threatens agricultural water security. This review synthesizes literature on agricultural water system resilience under climate change through a structured critical narrative approach informed by PRISMA/SALSA reporting principles. We examine four linked domains: resilience concepts and indicators, assessment methods under uncertainty, climate impact and vulnerability evidence, and adaptation/governance pathways. The synthesis indicates a broad shift from engineering-centered water-supply approaches toward socio-ecological resilience frameworks that combine infrastructure, ecosystem processes, farmer behavior, and institutions. Methodologically, deterministic optimization is increasingly complemented by stochastic, robust, integrated-assessment, remote-sensing, and machine-learning approaches, although data requirements, uncertainty propagation, and interpretability remain important constraints. Evidence suggests that crop water demand and irrigation requirements may increase substantially under high-emission scenarios, with acute risks in arid and semi-arid regions. Effective adaptation is unlikely to rely on single technologies alone; precision irrigation, nature-based solutions, climate services, and infrastructure investments require complementary demand-side rules, water accounting, equity safeguards, and participatory governance to avoid maladaptation such as the irrigation-efficiency rebound effect. We identify priority research needs in transparent review protocols, uncertainty quantification, cross-scale governance, farmer decision-making, digital inclusion, and monitoring systems. The review provides a moderated conceptual framework and policy-oriented research agenda for strengthening agricultural water resilience. Full article

The advancement of rural urbanization has led to a steady increase in construction and demolition waste (CDW) in rural areas; its dispersed nature complicates management efforts, yet existing research has not sufficiently explored the synergistic effects of subsidies and transportation costs. In this paper, a Stackelberg game model is constructed among the government, farmers, and manufacturers within the framework of a reward–penalty mechanism (RPM), and rural governance efficiency is introduced to characterize regulatory enforcement losses. Furthermore, on the basis of existing research and discussions with experts in the construction industry, this study conducted numerical simulations of key parameters by integrating multiple data sources and calibrating parameters. The aim was to analyze the mechanisms through which key factors—such as differences in subsidy structures and transportation costs—influence the decision-making behavior of farmers and manufacturers, as well as the equilibrium outcomes of the supply chain. The results indicate that (1) the reward–penalty mechanism has a significant and nonlinear effect on the decision-making of the parties involved; (2) although subsidy intensity promotes technological investment, its impact on revenue and pricing varies because of transportation cost constraints; (3) the proportion of additional subsidies for farmers is key to policy coordination, and a reasonable subsidy structure can simultaneously improve both economic and environmental performance; and (4) as a key constraint, farmers’ transportation costs play a significant moderating role in the effectiveness of regulatory measures. This paper reveals the decision-making mechanisms of rural CDW resource recovery supply chains under multiple constraints from a farmer-led perspective, providing a reference for promoting rural CDW resource recovery. Full article

Climate change presents significant challenges to agriculture worldwide, leading to food insecurity and impacting rural livelihoods. Maize farming is especially vulnerable to extreme weather, such as heavy rainfall, high temperatures, soil acidity, humidity, and poor irrigation, which reduce crop yields and raise concerns about food security. The study aimed to develop a reliable and accurate machine learning method to predict maize crop yields using historical climate data to facilitate decision-making. This allows farmers and agronomists to forecast maize production based on past data for adaptation. A dataset from Meteo Rwanda and maize yield data from the Kayonza district, Rwanda, were used for training and testing. The weather data included annual mean temperature, maximum temperature, minimum temperature, rainfall, and soil temperature over the past thirteen years. The data were analyzed using machine learning techniques such as Random Forest regressor, Extreme Boost regressor, Gradient, Support Vector Machine, and LASSO (Least Absolute Shrinkage and Selection Operator). The results show that developing a high-yield crop depends on predicting and integrating climate variables, especially temperature and rainfall. Overall, Random Forest, Support Vector Machine, and Extreme Boost outperformed LASSO, with R² values of 0.957, 0.955, and 0.953, compared to 0.256 for LASSO. Full article