Search Results (63)

Agriculture is the foundational industry for human survival, profoundly impacting economic, ecological, and social dimensions. In the face of global challenges such as rapid population growth, resource scarcity, and climate change, achieving technological innovation in agriculture and advancing smart farming have become increasingly critical. In recent years, deep learning and computer vision have developed rapidly. Key areas in computer vision—such as deep learning-based image processing, object detection, and multimodal fusion—are rapidly transforming traditional agricultural practices. Processes in agriculture, including planting planning, growth management, harvesting, and post-harvest handling, are shifting from experience-driven methods to digital and intelligent approaches. This paper systematically reviews applications of deep learning and computer vision in agricultural growth management over the past decade, categorizing them into four key areas: crop identification, grading and classification, disease monitoring, and weed detection. Additionally, we introduce classic methods and models in computer vision and deep learning, discussing approaches that utilize different types of visual information. Finally, we summarize current challenges and limitations of existing methods, providing insights for future research and promoting technological innovation in agriculture. Full article

The integration of computer vision (CV) and generative artificial intelligence (GenAI) into smart agriculture has revolutionised traditional farming practices by enabling real-time monitoring, automation, and data-driven decision-making. This review systematically examines the applications of CV in key agricultural domains, such as crop health monitoring, precision farming, harvesting automation, and livestock management, while highlighting the transformative role of GenAI in addressing data scarcity and enhancing model robustness. Advanced techniques, including convolutional neural networks (CNNs), YOLO variants, and transformer-based architectures, are analysed for their effectiveness in tasks like pest detection, fruit maturity classification, and field management. The survey reveals that generative models, such as generative adversarial networks (GANs) and diffusion models, significantly improve dataset diversity and model generalisation, particularly in low-resource scenarios. However, challenges persist, including environmental variability, edge deployment limitations, and the need for interpretable systems. Emerging trends, such as vision–language models and federated learning, offer promising avenues for future research. The study concludes that the synergy of CV and GenAI holds immense potential for advancing smart agriculture, though scalable, adaptive, and trustworthy solutions remain critical for widespread adoption. This comprehensive analysis provides valuable insights for researchers and practitioners aiming to harness AI-driven innovations in agricultural ecosystems. Full article

The change in the socio-political formation of Russia from a socialist planned system to a capitalist market system significantly influenced agriculture and one of its components—arable land. The loss of the sustainability of land management for arable land led to a reduction in sown areas by 38% (from 119.7 to 74.7 million ha) and a synchronous drop in gross harvests of grain and leguminous crops by 48% (from 117 to 61 million tons). The situation stabilized in 2020, with a sowing area of 80.2 million ha and gross harvests of grain and leguminous crops of 120–150 million tons. This process was not formalized legally, and the official (legal) area of arable land decreased by only 8% from 132.8 to 122.3 million ha. Legal conflict arose for 35 million ha for unused arable land, for which there was no classification of its condition categories and no monitoring of the withdrawal time of the arable land from actual agricultural use. The aim of this study was to resolve the challenges in the method of retrospective monitoring of soil–land cover, which allowed for the achievement of the aims of the investigation—to elucidate the history of land use on arable lands from 1985 to 2025 with a time step of 5 years and to obtain a detailed classification of the arable lands’ abandonment degrees. It was also established that on most of the abandoned arable land, carbon sequestration occurs in the form of secondary forests. In the course of this work, it was shown that the reasons for the formation of an array of abandoned arable land and the stabilization of agricultural production turned out to be interrelated. The abandonment of arable land occurred proportionally to changes in the soil’s natural fertility and the degree of land degradation. Economically unprofitable lands spontaneously (without centralized planning) left the sowing zone. The efficiency of land use on the remaining lands has increased and has allowed for the mass application of modern farming systems (smart, precise, landscape-adaptive, differentiated, no-till, strip-till, etc.), which has further increased the profitability of crop production. The prospect of using abandoned lands as a carbon sequestration zone in areas of forest overgrowth has arisen. Full article

Current tomato harvesters rely primarily on external color as the sole indicator of ripeness. However, this approach often results in premature harvesting, leading to insufficient lycopene accumulation and a suboptimal nutritional content for human consumption. Such limitations are especially critical in controlled-environment agriculture (CEA) systems, where maximizing fruit quality and nutrient density is essential for both the yield and consumer health. To address that challenge, this study introduces a novel, multimodal harvest readiness framework tailored to nutrient film technology (NFT)-based smart farms. The proposed approach integrates plant-level stress diagnostics and fruit-level phenotyping using wearable biosensors, AI-assisted computer vision, and non-invasive physiological sensing. Key physiological markers—including the volatile organic compound (VOC) methanol, phytohormones salicylic acid (SA) and indole-3-acetic acid (IAA), and nutrients nitrate and ammonium concentrations—are combined with phenomic traits such as fruit color (a*), size, chlorophyll index (rGb), and water status. The innovation lies in a four-stage decision-making pipeline that filters physiologically stressed plants before selecting ripened fruits based on internal and external quality indicators. Experimental validation across four plant conditions (control, water-stressed, light-stressed, and wounded) demonstrated the efficacy of VOC and hormone sensors in identifying optimal harvest candidates. Additionally, the integration of low-cost electrochemical ion sensors provides scalable nutrient monitoring within NFT systems. This research delivers a robust, sensor-driven framework for autonomous, data-informed harvesting decisions in smart indoor agriculture. By fusing real-time physiological feedback with AI-enhanced phenotyping, the system advances precision harvest timing, improves fruit nutritional quality, and sets the foundation for resilient, feedback-controlled farming platforms suited to meeting global food security and sustainability demands. Full article

The acute shortage of agricultural labor necessitates the development of predictive models to optimize farm operations. This study investigates the effectiveness of artificial-intelligence-driven models to accurately forecast the timing and yield of persimmon harvests, using meteorological data alongside historical harvest records. An artificial neural network was designed to estimate peak harvest dates by analyzing key meteorological variables. The model was trained and validated using data from the JA Nara Prefecture Nishiyoshino Sorting Facility and Nara Prefecture Agriculture Research and Development Center. Its reliability was confirmed based on mean absolute error, demonstrating the ability to make predictions with an accuracy of approximately three days. Additionally, extreme gradient boosting models were developed to predict yields, incorporating elevation data to refine predictions at the field scale. The model was trained and validated using data from fields cultivated in the Gojo-Yoshino region. The effectiveness of these models was evaluated using root mean square error, demonstrating an improvement in prediction accuracy of up to 20% with the inclusion of elevation data, illustrating their capability to effectively capture yield variations across different orchards. These models can significantly improve labor management, harvest scheduling, and overall productivity within the realm of smart agriculture. Full article

Smart agriculture is transforming traditional farming by integrating advanced sensor-based systems, intelligent control technologies, and sustainable energy solutions to meet the growing global demand for food while reducing environmental impact. This review presents a comprehensive analysis of recent innovations in smart agriculture, focusing on the deployment of IoT-based sensors, wireless communication protocols, energy-harvesting methods, and automated irrigation and fertilization systems. Furthermore, the paper explores the role of artificial intelligence (AI), machine learning (ML), computer vision, and big data analytics in monitoring and managing key agricultural parameters such as crop health, pest and disease detection, soil conditions, and water usage. Special attention is given to decision-support systems, precision agriculture techniques, and the application of remote and proximal sensing technologies like hyperspectral imaging, thermal imaging, and NDVI-based indices. By evaluating the benefits, limitations, and emerging trends of these technologies, this review aims to provide insights into how smart agriculture can enhance productivity, resource efficiency, and sustainability in modern farming systems. The findings serve as a valuable reference for researchers, practitioners, and policymakers working towards sustainable agricultural innovation. Full article

Automating agricultural processes holds significant promise for enhancing efficiency and sustainability in various farming practices. This paper contributes to the automation of agricultural processes by providing a dedicated mushroom detection dataset related to automated harvesting, 3D pose estimation, and growth monitoring of the button mushroom produced using Agaricus Bisporus fungi. With a total of 2000 images for object detection, instance segmentation, and 3D pose estimation—containing over 100,000 mushroom instances—and an additional 3838 images for yield estimation featuring eight mushroom scenes covering the complete growth period, it fills the gap in mushroom-specific datasets and serves as a benchmark for detection and instance segmentation as well as 3D pose estimation algorithms in smart mushroom agriculture. The dataset, featuring realistic growth environment scenarios with comprehensive 2D and 3D annotations, is assessed using advanced detection and instance segmentation algorithms. This paper details the dataset’s characteristics, presents detailed statistics on mushroom growth and yield, evaluates algorithmic performance, and, for broader applicability, makes all resources publicly available, including images, code, and trained models, via our GitHub repository. (accessed on 22 March 2025). Full article

This study aimed to assess the impact of climatic alteration on food security in Saudi Arabia. Date productivity, temperature, and precipitation represent the data which were collected from various sources linked to the study subject and cover the period from 1980 to 2023. The Engle–Granger two-step procedure, the VECM, and forecast analysis were applied to test the long-term relationship, short-term integration, and forecasting, respectively. Moreover, qualitative analysis was used to reveal the influence of climatic change on food security. The results discovered long-term co-integration between date productivity and temperature. Additionally, the results revealed that there has been long-running co-integration between date productivity and the precipitation series. Temperature and precipitation negatively and significantly impacted date productivity during the study period. With reference to forecast results, the graph was validated using various forecast indicators: the Alpha, Gamma, Beta, and Mean Square Error equivalents were 1.0, 0.0, 0.0, and 5.47, respectively. Moreover, the growth rates of date productivity were equal to 0.82 and 0.08 for the periods from 1980 to 2022 and 2023 to 2034 (forecast), respectively, indicating that there is a decrease in the growth rate of date productivity (0.08) during the forecast period. From these results, the conclusion is that climatic change (temperature and precipitation) negatively impacts date productivity. In addition, the growth rate during the forecast period decreased, indicating that climatic change is affecting food security currently and will continue to do so in the future. This study recommended specific policy interventions and innovations in agricultural practices, including developing and implementing a national framework focused on climate-smart agriculture, balancing productivity, adaptation, and mitigation. This could be aligned with Vision 2030 and the Saudi Green Initiative. Additionally, this could include investing in research and development by increasing public–private partnerships to support agricultural R&D in arid regions, with a focus on heat- and drought-resistant crop varieties and water-efficient farming systems. Regarding agricultural innovations, these could include the use of renewable energy, particularly solar energy, the expansion of rainwater harvesting infrastructure, recycling treated wastewater for agriculture, and reducing reliance on groundwater sources. Full article

Underground winter bamboo shoots, prized for their high nutritional value and economic significance, face harvesting challenges owing to inefficient manual methods and the lack of specialized detection technologies. This review systematically evaluates current detection approaches, including manual harvesting, microwave detection, resistivity methods, and biomimetic techniques. While manual methods remain dominant, they suffer from labor shortages, low efficiency, and high damage rates. Microwave-based technologies demonstrate high accuracy and good depths but are hindered by high costs and soil moisture interference. Resistivity methods show feasibility in controlled environments but struggle with field complexity and low resolution. Biomimetic approaches, though innovative, face limitations in odor sensitivity and real-time data processing. Key challenges include heterogeneous soil conditions, performance loss, and a lack of standardized protocols. To address these, an integrated intelligent framework is proposed: (1) three-dimensional modeling via multi-sensor fusion for subsurface mapping; (2) artificial intelligence (AI)-driven harvesting robots with adaptive excavation arms and obstacle avoidance; (3) standardized cultivation systems to optimize soil conditions; (4) convolution neural network–transformer hybrid models for visual-aided radar image analysis; and (5) aeroponic AI systems for controlled growth monitoring. These advancements aim to enhance detection accuracy, reduce labor dependency, and increase yields. Future research should prioritize edge-computing solutions, cost-effective sensor networks, and cross-disciplinary collaborations to bridge technical and practical gaps. The integration of intelligent technologies is poised to transform traditional bamboo forestry into automated, sustainable “smart forest farms”, addressing global supply demands while preserving ecological integrity. Full article

The deployment of machine learning models on mobile platforms has ushered in a new era of innovation across diverse sectors, including agriculture, where such applications hold immense promise for empowering farmers with cutting-edge technologies. In this context, the threat posed by insects to crop yields during harvest has escalated, fueled by factors such as evolution and climate change-induced shifts in insect behavior. To address this challenge, smart insect monitoring systems and detection models have emerged as crucial tools for farmers and IoT-based systems, enabling interventions to safeguard crops. The primary contribution of this study lies in its systematic investigation of model optimization techniques for edge deployment, including Post-Training Quantization, Quantization-Aware Training, and Data Representative Quantization. As such, we address the crucial need for efficient, on-site pest detection tools in agricultural settings. We provide a detailed analysis of the trade-offs between model size, inference speed, and accuracy across different optimization approaches, ensuring practical applicability in resource-constrained farming environments. Our study explores various methodologies for model development, including the utilization of Mobile-ViT and EfficientNet architectures, coupled with transfer learning and fine-tuning techniques. Using the Dangerous Farm Insects Dataset, we achieve an accuracy of 82.6% and 77.8% on validation and test datasets, respectively, showcasing the efficacy of our approach. Furthermore, we investigate quantization techniques to optimize model performance for on-device inference, ensuring seamless deployment on mobile devices and other edge devices without compromising accuracy. The best quantized model, produced through Post-Training Quantization, was able to maintain a classification accuracy of 77.8% while significantly reducing the model size from 33 MB to 9.6 MB. To validate the generalizability of our solution, we extended our experiments to the larger IP102 dataset. The quantized model produced using Post-Training Quantization was able to maintain a classification accuracy of 59.6% while also reducing the model size from 33 MB to 9.6 MB, thus demonstrating that our solution maintains a competitive performance across a broader range of insect classes. Full article

This study investigates the application of hyperspectral imaging (HSI) combined with machine learning (ML) models for the dynamic mapping of total phenolic content (TPC) and total flavonoid content (TFC) in sunflower microgreens. Spectral data were collected across different cultivation durations (Days 5, 6, and 7) to assess the secondary metabolite distribution in leaves and stems. Overall, the results indicate that TFC in leaves peaked on Day 5, followed by a decline on Days 6 and 7, while stems exhibited an opposite trend. However, TPC did not show a consistent pattern. Spectral reflectance analysis revealed higher near-infrared reflectance in leaves compared to stems. The variation in trait and spectral data among the collected samples was sufficient to develop models predicting the TPC and TFC content. K-nearest neighbours provided the highest predictive accuracy for TPC ($R^2$ = 0.95 and 1.6 mg GAE/100 g) and ridge regression performed best for TFC ($R^2$ = 0.97 and 6.1 mg QE/100 g). Dimensionality reduction via principal component analysis (PCA) proved effective for TPC and TFC prediction, with PC1 alone achieving performance comparable to the full spectral dataset. This integrated HSI-ML approach offers a non-destructive, real-time method for monitoring bioactive compounds, supporting sustainable agricultural practices, optimising harvest timing, and enhancing crop management. The findings can be further developed for smart microgreen farming to enable real-time secondary metabolite quantification, with future research recommended to explore other microgreen varieties for broader applicability. Full article

Agricultural runoff ranks second only to atmospheric deposition as a source of nitrogen pollution to streams in the southeastern United States. Climate-smart practices such as irrigation have the potential to reduce these impacts and provide resilience in the face of climate change. The purpose of this study is to evaluate the impact of irrigation amounts and fertilizer application strategies on surface nitrate export to surrounding steams. Data from an existing experiment on corn nitrogen fertilization in the Southeastern US was utilized and a crop simulation model was employed to simulate the water and nitrogen dynamics within the soil with particular emphases on nutrient uptake and residual nutrients. left in the soil after harvest under varying fertilization scenarios. A hydrologic and nutrient export model was developed to run in conjunction with the crop model to simulate lateral export from the fields. The results of this study indicate that climate and nutrient management are the dominant factors in determining surface nutrient transport under both rain fed and irrigated conditions, confirming previous studies. The overall results show that irrigation, on average, reduced nutrient export from the surface, especially in dry years. The effect is even greater if the nutrients are applied later in the year while irrigation is on-going. While this present study provides an initial look at the potential impacts of irrigation on nutrient export in humid areas, the available on-farm observational data is limited in its content. However, the results obtained support existing literature and provide further evidence on the impact of irrigation as a climate resilient practice and will help direct future studies in the region. Full article

Japan faces a significant labor shortage due to an aging population, particularly in the agricultural sector. The rising average age of farmers and the declining participation of younger individuals threaten the sustainability of farming practices. These trends reduce the availability of agricultural labor and pose a risk to lowering Japan’s food self-sufficiency rate. The reliance on food imports raises concerns regarding price fluctuations and sanitation standards. Moreover, the challenging working conditions in agriculture and a lack of technological innovation have hindered productivity and increased the burden on the existing workforce. To address these challenges, “smart agriculture” presents a promising solution. By leveraging advanced technologies such as sensors, drones, the Internet of Things (IoT), and automation, smart agriculture aims to optimize farm operations. Real-time data collection and AI-driven analysis play a crucial role in monitoring crop growth, assessing soil conditions, and improving overall efficiency. This study proposes enhancements to the YOLO (You Only Look Once) object detection model to develop an automated tomato harvesting system. This system uses a camera to detect tomatoes and assess their ripeness for harvest. Our objective is to streamline the harvesting process through AI technology. Our improved YOLO model integrates two novel loss functions to enhance detection accuracy. The first, “VSR”, refines the model’s ability to classify tomatoes and determine their harvest readiness. The second, “SBCE”, enhances the detection of small tomatoes by training the model to recognize a range of object sizes within the dataset. These improvements have significantly increased the system’s detection performance. Our experimental results demonstrate that the mean Average Precision (mAP) of YOLOv7-tiny improved from 61.81% to 70.21%. Additionally, the F1 score increased from 0.61 to 0.71 and the mean Intersection over Union (mIoU) rose from 65.03% to 66.44% on the tomato dataset. These findings underscore the potential of our proposed system to enhance efficiency in agricultural practices. Full article

The conventional linear system of global food production and consumption is unsustainable as it is responsible for a substantial share of greenhouse gas emissions, biodiversity declines due land use change, agricultural water stress due resource-intensive water consumption patterns and land degradation. During the last decade (1994–2014), for example, the greenhouse emissions from agriculture in Africa were reported to increase at an average annual rate of between 2.9% and 3.1%, equivalent to 0.44 Gt and 0.54 Gt CO₂ per annum, respectively. Between 2000 and 2020, the greenhouse gas emissions from agrifood systems were shown to decrease in all major regions of the world, except in Africa and Asia, where they grew by 35 and 20 percent, respectively. With most of the circular agricultural practices still central to food production in the developing African countries, the continent can spearhead a global return to circular agriculture. Using a descriptive review approach, we explore the literature to examine the extent to which African agriculture is deploying these practices, the potential areas for improvement and lessons for the world in embracing sustainable food production. We underscore that the farming communities in sub-Saharan Africa have, for decades, been using some of the most effective circular agricultural principles and practices in agricultural production. We further show that practices and strategies akin to sustainable agricultural production include agronomic practices, smart irrigation options, renewable energy harvesting and waste-to-fertilizer technologies. All of these technologies, which are central to sustainable agricultural production, are not new to Africa, although they may require packaging and advocacy to reach a wider community in sub-Saharan Africa. Full article

Agriculture plays a significant role in global water consumption, accounting for approximately 70% of the world’s freshwater usage. This makes this sector a critical factor in the depletion of water resources. Accordingly, this paper explores potential mitigatory impacts of climate-smart water management (CSWM) technologies in sub-Saharan Africa. About 70% of the population in sub-Saharan Africa is dependent on agriculture for sustaining their livelihoods. This is despite the low agricultural output in smallholder farming systems (SFS) due to water scarcity. This has spurred several attempts to promote the adoption of climate-smart agriculture (CSA) to raise agricultural outputs and improve smallholder farmers’ livelihoods. However, there has not been a comprehensive analysis of data categorised by various aspects of climate-smart water management technologies. In this systematic literature review, climate-smart water management technologies in sub-Saharan Africa’s agricultural sector were identified and analysed to determine strategies that could enhance their adoption and impact. To this end, academic articles reporting on the adoption of climate-smart water management technologies in databases were reviewed. Four significant literature databases were used. These were limited to Springer Link, ScienceDirect, MDPI, Wiley Online, and Google Scholar. The findings demonstrate that rainwater harvesting and micro-irrigation are the primary climate-smart water management technologies used by smallholder farmers. The literature review shows that adoption of CSWM practices is constrained by inadequate technological infrastructure, financial implications, unsuitable policies, and low user skills, particularly. It is therefore recommended that government agricultural departments and relevant advocates of CSA should incentivise and subsidise smallholder farmers to encourage CSWM technology adoption. This can be achieved through the implementation of suitable policies directed at technological infrastructure development, financial support for adoption, and technical skills training. Full article