This paper reviews recent literature concerning a wide range of processes through which climate change could potentially impact global-scale agricultural productivity, and presents projections of changes in relevant meteorological, hydrological and plant physiological quantities from a climate model ensemble to illustrate key areas of uncertainty. Few global-scale assessments have been carried out, and these are limited in their ability to capture the uncertainty in climate projections, and omit potentially important aspects such as extreme events and changes in pests and diseases. There is a lack of clarity on how climate change impacts on drought are best quantified from an agricultural perspective, with different metrics giving very different impressions of future risk. The dependence of some regional agriculture on remote rainfall, snowmelt and glaciers adds to the complexity. Indirect impacts via sea-level rise, storms and diseases have not been quantified. Perhaps most seriously, there is high uncertainty in the extent to which the direct effects of CO2 rise on plant physiology will interact with climate change in affecting productivity. At present, the aggregate impacts of climate change on global-scale agricultural productivity cannot be reliably quantified.
Across the tropics, smallholder farmers already face numerous risks to agricultural production. Climate change is expected to disproportionately affect smallholder farmers and make their livelihoods even more precarious; however, there is limited information on their overall vulnerability and adaptation needs. We conducted surveys of 600 households in Madagascar to characterize the vulnerability of smallholder farmers, identify how farmers cope with risks and explore what strategies are needed to help them adapt to climate change. Malagasy farmers are particularly vulnerable to any shocks to their agricultural system owing to their high dependence on agriculture for their livelihoods, chronic food insecurity, physical isolation and lack of access to formal safety nets. Farmers are frequently exposed to pest and disease outbreaks and extreme weather events (particularly cyclones), which cause significant crop and income losses and exacerbate food insecurity. Although farmers use a variety of risk-coping strategies, these are insufficient to prevent them from remaining food insecure. Few farmers have adjusted their farming strategies in response to climate change, owing to limited resources and capacity. Urgent technical, financial and institutional support is needed to improve the agricultural production and food security of Malagasy farmers and make their livelihoods resilient to climate change.
Conventional wisdom holds that Sub-Saharan African farmers use few modern inputs despite the fact that most poverty-reducing agricultural growth in the region is expected to come largely from expanded use of inputs that embody improved technologies, particularly improved seed, fertilizers and other agro-chemicals, machinery, and irrigation. Yet following several years of high food prices, concerted policy efforts to intensify fertilizer and hybrid seed use, and increased public and private investment in agriculture, how low is modern input use in Africa really? This article revisits Africa’s agricultural input landscape, exploiting the unique, recently collected, nationally representative, agriculturally intensive, and cross-country comparable Living Standard Measurement Study-Integrated Surveys on Agriculture (LSMS-ISA) covering six countries in the region (Ethiopia, Malawi, Niger, Nigeria, Tanzania, and Uganda). Using data from over 22,000 households and 62,000 agricultural plots, we offer ten potentially surprising facts about modern input use in Africa today.
Promoting low-carbon agriculture is vital for climate action and food security. State farms serve as crucial agricultural production bases in China and are essential in reducing China’s carbon emissions and boosting emission efficiency. This study calculates the carbon emissions of state farms across 29 Chinese provinces using the IPCC method from 2010 to 2022. It also evaluates emission efficiency with the Super-Slack-Based Measure (Super-SBM model) and analyzes influencing factors using the Logarithmic Mean Divisia Index (LMDI) method. The findings suggest that the three largest carbon sources are rice planting, chemical fertilizers, and land tillage. Secondly, agricultural carbon emissions in state farms initially surge, stabilize with fluctuations, and ultimately decline, with higher emissions observed in northern and eastern China. Thirdly, the rise of agricultural carbon emission efficiency is driven primarily by technological progress. Lastly, economic development and industry structure promote agricultural carbon emissions, while production efficiency and labor scale reduce them. To reduce carbon emissions from state farms in China and improve agricultural carbon emission efficiency, the following measures can be taken: (1) Improve agricultural production efficiency and reduce carbon emissions in all links; (2) Optimize the agricultural industrial structure and promote the coordinated development of agriculture; (3) Reduce the agricultural labor scale and promote the specialization, professionalization, and high-quality development of agricultural labor; (4) Accelerate agricultural green technology innovation and guide the green transformation of state farms. This study enriches the theoretical foundation of low-carbon agriculture and develops a framework for assessing carbon emissions in Chinese state farms, offering guidance for future research and policy development in sustainable agriculture.
Statistical analysis of agricultural experiments is based on structured experimental designs such as randomized block, factorial, split-plot, and multi-environment trials. While the theoretical bases of these approaches are sound, their implementation in modern programming frameworks usually involves manual specification of statistical models, choice of error terms, and subjective interpretation of interaction effects. This divide between experimental design and computational implementation opens the door to misleading inference and inconsistent reporting. We introduce AgroDesign, a Python framework that makes experimental design the central specification of statistical analysis. The framework translates specified experimental designs directly into valid linear models, automatically identifies error strata, conducts hypothesis testing and mean separation, checks assumptions of linear models, and provides decision-focused interpretations. The framework integrates fixed-effect ANOVA, hierarchical designs, linear mixed models, and genotype-by-environment stability analysis into a single declarative framework. AgroDesign is validated on canonical designs in agricultural statistics and shows consistency with traditional statistical analysis while strictly enforcing correct interpretation constraints, especially in interaction-dominant and multi-stratum designs. By integrating design semantics into computation, the framework minimizes analyst-driven modeling choices and enhances reproducibility.
Primula forbesii Franch. is a biennial ornamental species increasingly used in flower landscape design, potted displays, and cut flower production. Nevertheless, studies on its flowering regulation remain limited. This study investigated the effects of gibberellin (GA3) and spermidine (Spd) on the flowering performance of P. forbesii, using flowering time, scape morphology, and physiological parameters as key evaluation indices. At the onset of floral bud differentiation, 15 foliar spray treatments were applied. The most effective treatment contained 200 mg·L-1 GA3 and 0.01 mmol·L-1 Spd, which extended flowering duration by 5 days and promoted earlier bud emergence. Notably, this treatment significantly enhanced scape traits compared to the distilled water treatment, increasing internode length between floral whorls, the main scape height, and diameter. The scape number was increased by 361.54%. At the full flowering stage, the combination of 200 mg·L-1 GA3 and 0.01 mmol·L-1 Spd reduced malondialdehyde content and peroxidase activity in petals, while enhancing superoxide dismutase and catalase activities, along with soluble protein and soluble sugar accumulation. Endogenous hormone profiling showed that the treatment significantly raised levels of GA3, indole-3-acetic acid, and zeatin riboside, while reducing abscisic acid content. These results demonstrate that the combined application of 200 mg·L-1 GA3 and 0.01 mmol·L-1 Spd effectively enhances ornamental quality and delays senescence in P. forbesii. The findings provide valuable insights into the hormonal regulation of flowering senescence in ornamental plants and may help guide future strategies for cut‑flower preservation and quality maintenance.
Digital innovation in agriculture has become a powerful force in the modern world as it revolutionizes the agricultural sector and improves the sustainability and efficacy of farming practices. In this context, the study examines the effects of digital technology, as reflected by the digital economy and society index (DESI), on key agricultural performance metrics, including agricultural output and real labor productivity per person. The paper develops a strong analytical method for quantifying these associations using predictive models, such as exponential smoothing, ARIMA, and artificial neural networks. The method fully illustrates how economic and technological components interact, including labor productivity, agricultural output, and GDP per capita. The results demonstrate that digital technologies significantly impact agricultural output and labor productivity. These findings illustrate the importance of digital transformation in modernizing and improving agriculture’s overall efficacy. The study’s conclusion highlights the necessity of integrating digital technology into agricultural policy to address productivity problems and nurture sustainable growth in the sector.
Agricultural commercialization is often promoted as a key driver of development in Sub-Saharan Africa, yet its benefits may not extend equally to all farmers. Using longitudinal household data from the LSMS-ISA and a two-way Mundlak fixed effects estimator, we examine the relationship between farmers' gender and agricultural commercialization in Ethiopia, Nigeria, and Tanzania. In Ethiopia and Nigeria, women-headed households and those with a higher share of women-managed land face substantial disadvantages in market engagement, particularly in households oriented towards self-consumption. Interestingly, in both countries, women-headed households that do engage in sales are more likely to sell to market buyers and less likely to sell to individual buyers compared to men-headed households. In contrast, in Tanzania, the negative associations between gender and commercialization are weaker and less robust across outcomes. Overall, these findings demonstrate that gender gaps in commercialization are highly context-specific rather than universal, highlighting the need for country-tailored policies that address the institutional and market constraints faced by women farmers.
This article exemplifies the design of a fruit detection and classification system using Convolutional Neural Networks (CNN). The goal is to develop a system that automatically assesses fruit quality for farm inventory management. Specifically, a method for mango fruit classification was developed using image processing, ensuring both accuracy and efficiency. Resnet-18 was selected as the preliminary architecture for classification, while a cascade detector was used for detection, balancing execution speed and computational resource consumption. Detection and classification results were displayed through a graphical interface developed in MatLab App Designer, streamlining system interaction. The integration of convolutional neural networks and cascade detectors proffers a reliable solution for fruit classification and detection, with potential applications in agricultural quality control.
Vision-language models (VLMs) are increasingly proposed as general-purpose solutions for visual recognition tasks, yet their reliability for agricultural decision support remains poorly understood. We benchmark a diverse set of open-source and closed-source VLMs on 27 agricultural image classification datasets from the AgML collection (https://github.com/Project-AgML), spanning 162 classes and 248,000 images across plant disease, pest and damage, and plant and weed species identification. Across all tasks, zero-shot VLMs substantially underperform a supervised task-specific baseline (YOLO11), which consistently achieves markedly higher accuracy than any foundation model. Under multiple-choice prompting, the best-performing VLM (Gemini-3 Pro) reaches approximately 62% average accuracy, while open-ended prompting yields much lower performance, with raw accuracies typically below 25%. Applying LLM-based semantic judging increases open-ended accuracy (e.g., from ~21% to ~30% for top models) and alters model rankings, demonstrating that evaluation methodology meaningfully affects reported conclusions. Among open-source models, Qwen-VL-72B performs best, approaching closed-source performance under constrained prompting but still trailing top proprietary systems. Task-level analysis shows that plant and weed species classification is consistently easier than pest and damage identification, which remains the most challenging category across models. Overall, these results indicate that current off-the-shelf VLMs are not yet suitable as standalone agricultural diagnostic systems, but can function as assistive components when paired with constrained interfaces, explicit label ontologies, and domain-aware evaluation strategies.
The financialization of agricultural commodities and its impact on food security has become an increasing concern. This study empirically investigates the role of financialization in global food markets and its policy implications for a stable and secure food system. Using panel data regression models, moderating effects models, and panel regression with a threshold variable, we analyze wheat, maize, and soybean futures traded on the Chicago Board of Trade. We incorporate data on annual trading volume, open interest contracts, and their ratio. The sample consists of five developed countries (United States, Australia, Canada, France, Germany) and seven developing countries (China, Russia, India, Indonesia, Brazil, Vietnam, Thailand), covering the period 2000 to 2021. The Human Development Index (HDI) serves as a threshold variable to differentiate the impact across countries. Our findings indicate that the financialization of agricultural commodities has negatively affected global food security, with wheat and soybean showing a greater adverse impact than maize. The effects are more pronounced in developing countries. Additionally, we find that monetary policy has the potential to mitigate these negative effects. These results provide insights for policymakers to design strategies that ensure a secure and accessible global food supply.
Mohamed Ohamouddou, Said Ohamouddou, Abdellatif El Afia
et al.
This study proposes ATMS-KD (Adaptive Temperature and Mixed-Sample Knowledge Distillation), a novel framework for developing lightweight CNN models suitable for resource-constrained agricultural environments. The framework combines adaptive temperature scheduling with mixed-sample augmentation to transfer knowledge from a MobileNetV3 Large teacher model (5.7\,M parameters) to lightweight residual CNN students. Three student configurations were evaluated: Compact (1.3\,M parameters), Standard (2.4\,M parameters), and Enhanced (3.8\,M parameters). The dataset used in this study consists of images of \textit{Rosa damascena} (Damask rose) collected from agricultural fields in the Dades Oasis, southeastern Morocco, providing a realistic benchmark for agricultural computer vision applications under diverse environmental conditions. Experimental evaluation on the Damascena rose maturity classification dataset demonstrated significant improvements over direct training methods. All student models achieved validation accuracies exceeding 96.7\% with ATMS-KD compared to 95--96\% with direct training. The framework outperformed eleven established knowledge distillation methods, achieving 97.11\% accuracy with the compact model -- a 1.60 percentage point improvement over the second-best approach while maintaining the lowest inference latency of 72.19\,ms. Knowledge retention rates exceeded 99\% for all configurations, demonstrating effective knowledge transfer regardless of student model capacity.
The governance of frontier artificial intelligence (AI) systems--particularly those capable of catastrophic misuse or systemic failure--requires institutional structures that are robust, adaptive, and innovation-preserving. This paper proposes a novel framework for governing such high-stakes models through a three-tiered insurance architecture: (1) mandatory private liability insurance for frontier model developers; (2) an industry-administered risk pool to absorb recurring, non-catastrophic losses; and (3) federally backed reinsurance for tail-risk events. Drawing from historical precedents in nuclear energy (Price-Anderson), terrorism risk (TRIA), agricultural crop insurance, flood reinsurance, and medical malpractice, the proposal shows how the federal government can stabilize private AI insurance markets without resorting to brittle regulation or predictive licensing regimes. The structure aligns incentives between AI developers and downstream stakeholders, transforms safety practices into insurable standards, and enables modular oversight through adaptive eligibility criteria. By focusing on risk-transfer mechanisms rather than prescriptive rules, this framework seeks to render AI safety a structural feature of the innovation ecosystem itself--integrated into capital markets, not external to them. The paper concludes with a legal and administrative feasibility analysis, proposing avenues for statutory authorization and agency placement within existing federal structures.
Unmanned Aircraft Systems (UAS) and satellites are key data sources for precision agriculture, yet each presents trade-offs. Satellite data offer broad spatial, temporal, and spectral coverage but lack the resolution needed for many precision farming applications, while UAS provide high spatial detail but are limited by coverage and cost, especially for hyperspectral data. This study presents a novel framework that fuses satellite and UAS imagery using super-resolution methods. By integrating data across spatial, spectral, and temporal domains, we leverage the strengths of both platforms cost-effectively. We use estimation of cover crop biomass and nitrogen (N) as a case study to evaluate our approach. By spectrally extending UAS RGB data to the vegetation red edge and near-infrared regions, we generate high-resolution Sentinel-2 imagery and improve biomass and N estimation accuracy by 18% and 31%, respectively. Our results show that UAS data need only be collected from a subset of fields and time points. Farmers can then 1) enhance the spectral detail of UAS RGB imagery; 2) increase the spatial resolution by using satellite data; and 3) extend these enhancements spatially and across the growing season at the frequency of the satellite flights. Our SRCNN-based spectral extension model shows considerable promise for model transferability over other cropping systems in the Upper and Lower Chesapeake Bay regions. Additionally, it remains effective even when cloud-free satellite data are unavailable, relying solely on the UAS RGB input. The spatial extension model produces better biomass and N predictions than models built on raw UAS RGB images. Once trained with targeted UAS RGB data, the spatial extension model allows farmers to stop repeated UAS flights. While we introduce super-resolution advances, the core contribution is a lightweight and scalable system for affordable on-farm use.
Efficient nutrient management is critical for crop growth and sustainable resource consumption (e.g., nitrogen, energy). Current approaches require lengthy analyses, preventing real-time optimization; similarly, imaging facilitates rapid phenotyping but can be computationally intensive, preventing deployment under resource constraints. This study proposes a flexible, tiered pipeline for anomaly detection and status estimation (fresh weight, dry mass, and tissue nutrients), including a comprehensive energy analysis of approaches that span the efficiency-accuracy spectrum. Using a nutrient depletion experiment with three treatments (T1-100%, T2-50%, and T3-25% fertilizer strength) and multispectral imaging (MSI), we developed a hierarchical pipeline using an autoencoder (AE) for early warning. Further, we compared two status estimation modules of different complexity for more detailed analysis: vegetation index (VI) features with machine learning (Random Forest, RF) and raw whole-image deep learning (Vision Transformer, ViT). Results demonstrated high-efficiency anomaly detection (73% net detection of T3 samples 9 days after transplanting) at substantially lower energy than embodied energy in wasted nitrogen. The state estimation modules show trade-offs, with ViT outperforming RF on phosphorus and calcium estimation (R2 0.61 vs. 0.58, 0.48 vs. 0.35) at higher energy cost. With our modular pipeline, this work opens opportunities for edge diagnostics and practical opportunities for agricultural sustainability.
Betaine has been proposed as a low-cost source of methyl groups in poultry feed, replacing methionine and choline. The present study aimed to investigate the effect of betaine on growth performance, methionine metabolism, and methyl transfer in broilers aged 1 to 21 days fed a low-methionine diet. A total of 960 one-day-old male broilers were randomly divided into four groups: positive control (0.62% methionine in the diet), negative control (0.37% methionine in the diet), and two treatment groups (0.37% methionine in the diet plus either 1500 or 3000 mg betaine/kg diet). Chicks fed the 1500 mg betaine/kg diet had the highest feed-to-gain ratio (P < 0.05), but no significant difference in final body weight, average daily gain, average daily feed intake, or mortality. Serum S-adenosyl-L-methionine and total homocysteine were higher at 1500 mg betaine/kg diet; whereas serum S-adenosylhomocysteine exhibited the opposite trend. Except for DNA methyltransferase 1, key enzymes and metabolites involved in the hepatic single-carbon pathway showed the highest levels at 1500 mg betaine/kg diet and declined thereafter. Furthermore, betaine promoted dose-dependent mRNA and protein expression of enzymes involved in the hepatic single-carbon metabolic cycle and methyl transferase pathways in chicks fed methionine-deficient diets. In conclusion, while the addition of betaine did not significantly improve the growth performance of chicks aged 1–21 days, inclusion of 1500 mg betaine/kg diet effectively stabilized methionine metabolism and methyl transfer in methionine-deficient diets.
Vaishali Swaminathan, J. Alex Thomasson, Robert G. Hardin
et al.
Radiometric accuracy of data is crucial in quantitative precision agriculture, to produce reliable and repeatable data for modeling and decision making. The effect of exposure time and gain settings on the radiometric accuracy of multispectral images was not explored enough. The goal of this study was to determine if having a fixed exposure (FE) time during image acquisition improved radiometric accuracy of images, compared to the default auto-exposure (AE) settings. This involved quantifying the errors from auto-exposure and determining ideal exposure values within which radiometric mean absolute percentage error (MAPE) were minimal (< 5%). The results showed that FE orthomosaic was closer to ground-truth (higher R2 and lower MAPE) than AE orthomosaic. An ideal exposure range was determined for capturing canopy and soil objects, without loss of information from under-exposure or saturation from over-exposure. A simulation of errors from AE showed that MAPE < 5% for the blue, green, red, and NIR bands and < 7% for the red edge band for exposure settings within the determined ideal ranges and increased exponentially beyond the ideal exposure upper limit. Further, prediction of total plant nitrogen uptake (g/plant) using vegetation indices (VIs) from two different growing seasons were closer to the ground truth (mostly, R2 > 0.40, and MAPE = 12 to 14%, p < 0.05) when FE was used, compared to the prediction from AE images (mostly, R2 < 0.13, MAPE = 15 to 18%, p >= 0.05).