Search Results (450)

Cadmium (Cd) contamination in soil poses a serious threat to crop quality. Biochar is widely regarded as an effective amendment that can reduce Cd bioavailability and limit Cd uptake by crops. However, studies on the rapid and nondestructive evaluation of crop physiological responses under biochar-mediated alleviation of Cd stress remain insufficient. Spectral modeling methods can enable rapid and nondestructive monitoring of crop physiological status. In this preliminary experiment, Zhengdan 958 maize seedlings grown in Cd-contaminated soil were subjected to five biochar application rates: 0, 10, 30, 50, and 70 g/pot, designated as CK, A1, A3, A5, and A7, respectively. The study established a non-destructive spectral detection model for relative chlorophyll content expressed as SPAD values of maize leaves to achieve spectral inversion of leaf physiological information. The alleviating effect of biochar on Cd stress was evaluated by analyzing SPAD values and Cd accumulation in roots, stems, and leaves. The original spectral data underwent preprocessing steps including multivariate scattering correction, standard normal variable transformation, normalization, trend removal, first-order derivative transformation, and second-order derivative transformation. The effectiveness of different preprocessing methods was compared using partial least squares regression. Feature bands were identified via Pearson correlation analysis, and support vector regression models were established based on genetic algorithm (GA), particle swarm optimization (PSO), and grid search optimization. The results demonstrated that biochar application significantly increased the SPAD values of corn leaves (r = 0.879) and reduced the proportion of bioavailable Cd in soil, with the A7 treatment showing the most substantial decrease (30%). This indicates that biochar effectively mitigates Cd’s inhibitory effect on chlorophyll synthesis, with the alleviation effect enhancing as biochar application rates increased. Validation of the partial least squares regression model revealed that detrended spectra achieved optimal predictive performance (R²c = 0.94, RMSEC = 0.82, R²p = 0.88, RMSEP = 1.15), leading to the development of three optimized support vector regression models: GA-SVR, PSO-SVR, and GS-SVR. The GA-SVR model with a sigmoid kernel demonstrated the best internal validation performance for predicting SPAD values in maize leaves (R²c = 0.95, RMSEC = 0.24; R²p = 0.75, RMSEP = 1.63). This study provides preliminary theoretical support and technical reference for rapid spectral detection of the physiological status of maize under biochar-mediated mitigation of cadmium stress. Full article

Soybean is a strategic crop for global protein and vegetable oil supply chains; however, genetic improvement remains constrained by genotype-dependent regeneration, variable transformation efficiency, and regulatory concerns regarding stable transgene integration. This review synthesizes emerging DNA-free and genotype-independent genome-editing frameworks for soybean, where genotype independence is defined as the ability to recover fertile, non-chimeric edited plants across elite germplasm. We critically examine the soybean genome-editing toolbox, including CRISPR-Cas9, Cas12a, multiplex editing systems, base editing, and prime editing, and discuss persistent bottlenecks associated with target selection, off-target assessment, editability, and plant recovery. Particular emphasis is placed on artificial intelligence (AI)-assisted approaches that integrate genomic, epigenomic, chromatin-accessibility, and multi-omics datasets to improve target prioritization, guide RNA design, off-target prediction, and locus- and genotype-specific editability assessment. We further evaluate DNA-free genome-editing technologies, including CRISPR-Cas ribonucleoproteins, transient RNA-based systems, and nanocarrier-mediated delivery platforms, highlighting their potential to generate non-integrative edits while reducing prolonged nuclease exposure. In addition, we discuss regeneration reprogramming strategies based on developmental regulators and morphogenic modules, including BBM-WUS, GRF-GIF, de novo meristem induction, and somatic embryogenesis, as enabling technologies for overcoming cultivar-dependent regeneration barriers. Importantly, this review proposes an integrated AI-to-field framework that connects target discovery, editability prediction, DNA-free editing, regeneration reprogramming, phenotypic validation, and breeding deployment into a unified soybean improvement pipeline. We further highlight emerging opportunities in multi-omics-guided target discovery, genotype-aware prediction models, regeneration-aware editing strategies, and closed-loop machine-learning systems that continuously improve editing decisions through experimental feedback. Collectively, these convergent innovations provide a practical foundation for accelerating the development of climate-resilient, nutritionally enhanced, and industry-ready soybean cultivars. Full article

Operational crop mapping requires classifiers capable of robust generalization across years. While feature importance is routinely used for model optimization, its temporal stability has rarely been systematically investigated, creating a critical gap in deploying reliable monitoring systems. This study moves beyond identifying “most important” features to systematically evaluate and quantify their inter-annual stability for enabling automated classification. Using six agricultural years (2018, 2019, 2020, 2023, 2024 and 2025) of Sentinel-1 and Sentinel-2 data over Morocco, we extracted 156 multi-sensor features across 12 monthly composites and analyzed their importance stability through statistical metrics, clustering, and novel composite indices: the Reliability Index (RI) and Automatic Selection Score (AuSS). This framework automates feature selection by ranking features with RI and AuSS and then applying Pareto optimization to identify a minimal stable feature set—without requiring annual retraining or expert intervention. Our analysis confirms a fundamental tension: the most discriminative features (e.g., NDVI, VH, VV) are also the most volatile, while stable features (e.g., NDRE, MSI, NDMI) offer modest predictive power. Hierarchical clustering revealed four behavioral typologies (Dominant Stable, Performant Volatile, Stable Minor, and Noise), guiding strategic feature management. Crucially, a Pareto analysis demonstrated that a refined portfolio of 6 indices (VH, VV, NDVI, NDRE, GCVI, RVI) captures 57.2% of cumulative predictive importance, filtering out inter-annual noise while preserving discriminative signal. The Voting Ensemble leveraging this Stable Portfolio maintained consistent high accuracy (87.4% accuracy, 87.2% F1-score) with minimal performance degradation during temporal transfer, while models based on volatile top features exhibited significant drops. Entropy analysis confirmed that all features in the Stable Portfolio provide consistent informational certainty, indicating that stability-driven selection does not increase model uncertainty. We conclude that feature stability is not merely a diagnostic metric but a foundational criterion for operational design. We propose a practical, metrics-driven framework for constructing automated crop classification systems that are more resilient to inter-annual climate variability. Full article

Climate change threatens global food security through shifts in temperature and precipitation regimes, greater frequency of extreme weather events, and cascading effects on agricultural input markets and institutional capacity. Policymakers require nationally comparable diagnostic tools that are reproducible, transparent, and grounded in open data. This study presents an interpretable machine learning framework for country-level crop yield prediction and climate sensitivity screening, using publicly available FAOSTAT-derived panel data spanning 101 countries and 10 staple crop types over 1990–2013. A gradient-boosted decision tree model (XGBoost 2.1.4) is trained on observations from 1990 to 2008 and evaluated on a strictly held-out temporal window (2009–2013), using annual mean temperature, annual precipitation, total pesticide use (as a rough proxy for agricultural input management intensity), crop type and country identifiers, and temporally lagged yield values as predictive features. The optimized model yields high predictive accuracy on held-out data (R² = 0.982; RMSE = 11,183 hg/ha; MAE = 4396 hg/ha). Ablation analysis reveals that model performance depends primarily on temporal yield persistence and crop identity, with performance declining to R² = 0.940 when lagged features are omitted, while climate-only variables explain limited variation (R² = 0.119). Notably, an ordinary least squares (OLS) baseline achieves comparable performance (R² = 0.984), suggesting that the dominant predictive signals arise from a stable temporal–cross-sectional structure rather than nonlinear modeling flexibility. SHAP-based feature attribution identifies regime-dependent temperature effects, with larger (more negative) marginal contributions under high-temperature conditions. Stylized sensitivity perturbations (+1 °C, +2 °C, −20% pesticide inputs) indicate modest mean yield changes (−1.3% to −1.6%) but substantial cross-national heterogeneity. Systematic residual analysis identifies countries exhibiting consistent over- or under-prediction patterns, offering diagnostic signals for further institutional investigation. This framework is designed as a transparent, scalable screening tool for evidence-based prioritization rather than a validated causal or forecasting instrument. It complements localized agronomic expertise and supports SDG 2 (Zero Hunger) and SDG 13 (Climate Action). Full article

The escalating crisis of herbicide-resistant weeds threatens global wheat production. While key mutations are well-documented in weeds, the principles governing their interactions in wheat remain largely unknown. Here, we first developed a novel wheat germplasm carrying the acetolactate synthase (TaALS) Ser-627-Asn (S627N) mutation via ethyl methanesulfonate (EMS) mutagenesis. We then employed a computational design strategy to explore its synergy with the prevalent Trp-548-Leu (W548L) mutation—a combination not yet reported in nature. Integrated molecular dynamics (MD) simulations and free energy landscape analysis revealed that the in silico W548L/S627N double mutant triggers synergistic global destabilization of the herbicide–enzyme complex. Binding affinity progressively weakened from wild-type (−25.54 ± 2.05 kcal/mol) to the double mutant (−18.13 ± 2.76 kcal/mol), driven by a polarity inversion at the Arg-347 anchor. Comparative transcriptomic profiling of the S627N germplasm confirmed the absence of deleterious metabolic feedback in the branched-chain amino acid biosynthesis pathway. This work exemplifies a paradigm shift from mimicking natural variation to predictive crop design via multiplex gene editing. Full article

Mycotoxin contamination of cereal crops poses escalating food safety risks across the Central and Balkan European (CBE) corridor under climate change, yet no PRISMA 2020-compliant synthesis of remote sensing (RS) and machine learning (ML) evidence for this region exists. We conducted an AI-augmented systematic review applying a four-stage automated pipeline—PICO domain scoring, SBERT semantic deduplication, and Thompson-sampling reinforcement learning—to 36,038 corpus records (2010–2025), yielding 156 included studies (inter-rater κ = 0.81 (95% CI: 0.74–0.88)). Logistic growth modelling identified a 56-fold corpus expansion with inflection at t₀ = 2024.8 (R² = 0.981). Satellite multispectral imaging dominated the literature (91.7% of studies); random forest and gradient boosting models achieved R² = 0.74–0.80 for aflatoxin B1 and deoxynivalenol prediction in CBE maize and wheat when integrating vegetation indices, land surface temperature, and precipitation covariates. Deep learning surpassed classical ML in annual study count from 2021, reaching ~60% relative share by 2025, though the performance advantage narrows at field scale relative to laboratory hyperspectral benchmarks (98–99% accuracy). A five-percentage-point CBE–global performance gap is largely consistent with differences in sample size and multi-toxin design scope rather than algorithmic access. The country × mycotoxin gap matrix identifies zero eligible studies for four CBE nations and for T-2/HT-2 toxins across the Balkan states. Climate-driven satellite mycotoxin prediction emerges as the field’s active research frontier. Full article

As the core actuation component of intelligent precision spraying systems, the variable-rate nozzle is essential for achieving on-demand agricultural spraying; improving the use efficiency of water, fertilizers and pesticides; and reducing environmental pollution. This paper systematically reviews the development of agricultural variable-rate nozzles, from early mechanical profiling structures to modern intelligent control technologies based on Pulse Width Modulation (PWM). First, the existing variable-rate nozzles are classified into three major categories: electromagnetic-integrated type, centrifugal type, and variable-diameter type. A comparative analysis is conducted from three dimensions of working principle, performance characteristics and application scenarios, to delineate the respective advantages and limitations of each nozzle category. Second, the paper examines key technological advances in three areas: high-frequency solenoid valves, PWM control, and pressure and flow stabilization. It identifies the nonlinear response of solenoid valves, flow distortion under low duty cycles, and water hammer pressure fluctuation induced by high-speed switching as the three core technical bottlenecks at the current stage. Subsequently, the latest achievements and typical methodologies of variable-rate nozzles in structural design, simulation and experimental analysis are systematically reviewed, and their application performance in scenarios including field crops, orchards, protected agriculture and beyond are summarized. Finally, the remaining open issues in this field are put forward. It is suggested that future research should focus on key breakthroughs in the development of corrosion and wear-resistant high-frequency solenoid valves, the formation mechanism and suppression methods of pressure fluctuation, as well as adaptive algorithms based on machine learning or Model Predictive Control (MPC), to promote the leapfrog development of agricultural variable-rate nozzle technology from single variable control to multi-factor coupling optimization. All references cited in this paper are from articles published after the year 2000. Among them, the literature published in the last decade accounts for 86.6%, and literature published in the last five years accounts for 58.9%. Full article

The voluntary carbon market (VCM) has emerged as a promising mechanism for climate mitigation; however, farmer participation in developing countries remains limited. This study combines the Theory of Planned Behavior (TPB) and the Capability–Opportunity–Motivation–Behavior (COM-B) framework to investigate factors associated with Thai farmers’ intention and self-reported stage of participation in VCM. Data were collected through face-to-face interviews with 240 farmers across multiple crop systems in Thailand and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The model explained substantial variance in intention and behavior (R² = 0.610 and 0.555, respectively), although PLS-Predict indicated limited predictive performance. Perceived behavioral control (PBC) showed the strongest positive association with reported participation behavior (β = 0.493, p < 0.001), followed by intention (β = 0.343, p < 0.001). Access to extension and technical support (AES) was positively associated with intention (β = 0.624, p < 0.001) and PBC (β = 0.338, p < 0.001). Knowledge was positively associated with PBC (β = 0.324, p < 0.001) but negatively associated with intention (β = −0.106, p = 0.045). No significant association was observed between attitude and intention; however, subjective norms were negatively associated with intention (β = −0.336, p < 0.001). Indirect associations through intention and PBC were also observed. Overall, the findings suggest that capability-, opportunity-, and trust-related factors are associated with farmers’ reported participation in VCM and may inform the design of future policies and support programs. Although the model demonstrated useful explanatory capability, its predictive performance was limited, indicating that the findings should be interpreted primarily as explanatory rather than predictive. Full article

In large-scale rice farming systems, the design of efficient cropping schedules is essential for improving labor management and operational efficiency. However, climate change, including rising temperatures and increased frequency of extreme weather events, has altered crop growth dynamics, making it difficult to achieve optimal management using conventional experience-based scheduling. In addition, the need to distribute operations across numerous fields and optimize labor allocation has increased the complexity of schedule design. In this study, we propose a decision-support method for designing rice cropping schedules using a heading date prediction model and climatological temperature data. The method adjusts transplanting dates based on predicted heading and maturity dates and determines operation periods through both forward and backward scheduling. A case study conducted on a large-scale farming system in Chiba Prefecture demonstrated that the proposed method effectively dispersed the distribution of heading and maturity dates, leading to improved temporal distribution of operations. The standard deviation of heading dates decreased from 11.7 to 8.7 days, indicating a reduction in peak labor demand. The novelty of this study lies in extending a heading date prediction model from growth prediction to practical applications in cropping schedule design and visualization. This approach enables a transition from experience-based planning to data-driven decision-making and contributes to labor distribution in large-scale farming under climate change conditions. Full article

The use of sophisticated software for greenhouse microclimate analysis often requires advanced modelling expertise and significant computational effort, which may not always be available to greenhouse designers. This study proposes an integrated and modular workflow aimed at supporting greenhouse design through coupled thermal and evapotranspiration simulations. The design methodology is based on three steps. In the initial phase, the greenhouse environmental conditions are evaluated through the implementation of a dynamic thermal analysis, which is conducted by the DesignBuilder software (version 4.2). Subsequently, a plant evapotranspiration model is employed in MATLAB/Simulink (version R2025b) to evaluate crop transpiration, moisture production, and irrigation water consumption. In the final phase, the simulated moisture production is used to estimate the required ventilation rates and to support the sizing of greenhouse systems, including irrigation and HVAC components. Plant moisture production is a crucial factor in determining the sizing of greenhouse subsystems, such as the irrigation system, the ventilation rate, and the HVAC system. Nonetheless, the implementation of the evapotranspiration model necessitates a bespoke calibration to a case study. Indeed, the proposed models are more generally applicable and must be adapted to real-world applications. The methodology was applied to a small greenhouse used for the cultivation of aeroponic lettuce (Lactuca sativa cv. Romana) in a Mediterranean environment. The aim of the study was to explore the potential of the proposed integrated modelling framework to estimate annual irrigation water demand and the minimum ventilation rate required to mitigate excess moisture production, using a coupled MATLAB/Simulink implementation. The proposed approach should be interpreted as an exploratory design-support methodology rather than a fully validated predictive model, intended to investigate system behaviour under the specific conditions of the case study. Full article

Plant phenotyping based on unmanned aerial vehicles still faces challenges regarding the direct correlation between spectral information with field-collected variables, due to the influence of environmental factors and the considerable variation among maize phenological stages. Therefore, the objectives of this research were: I) to evaluate the interaction of nitrogen doses and evaluation environments (phenological stages and growing seasons) and variance components for field variables and vegetation indices; II) to identify the most suitable indices according to the evaluation environments; and III) to predict field variables based on relevant vegetation indices identified through the proposed methodology. The study was conducted using a randomized complete block design with four repetitions, in which treatments consisted of six nitrogen (N) topdressing doses (0, 50, 100, 200, 300, and 400 kg ha⁻¹) during the 2022/2023 and 2023/2024 growing seasons. Evaluations of agronomic variables and image acquisition were performed in five distinct phenological stages throughout the maize crop cycle. The data were analyzed using deviance analysis and variance components, principal component analysis (PCA), and multivariate linear modeling for the prediction of field variables. Our results demonstrated that all indices were affected by the interaction between N doses and evaluation environments (phenological stages and growing seasons). Additionally, the most reliable were EXGRaw, TGI, GNDVI, NDRE, CIRE, GVI, CVI, BNDVI, PanNDVI, SRNIRRe, SFDVI, RGBindex, NDVI, SAVI, MSAVI, and OSAVI, which showed clustering patterns according to growing season condition and phenological stage. Finally, the variables predicted using the proposed methodology achieved coefficients of determination above 0.80, except for shoot biomass and 100-grain weight. Therefore, it can be concluded that vegetation indices are influenced by the evaluated environment; however, the proposed framework based on the deduction of fixed and random effects enables the prediction of field variables with high accuracy using relatively simple models. Full article

The optimisation design of agricultural machinery is shifting from offline, experience-driven engineering towards adaptive, data-driven, and closed-loop intelligent optimisation. Conventional approaches based on computer-aided engineering (CAE), empirical testing, mathematical modelling, and static multi-objective optimisation have provided an important engineering foundation, but they remain limited under unstructured field conditions involving soil heterogeneity, crop variability, climatic disturbance, and nonlinear machinery–environment interactions. This review systematically examines the evolution of intelligent optimisation design for agricultural machinery from conventional simulation-based methods to artificial intelligence (AI)- and digital twin (DT)-enabled paradigms. First, mathematical modelling, response surface methodology, discrete element method (DEM), computational fluid dynamics (CFD), multi-body dynamics (MBD), heuristic algorithms, and early AI-assisted surrogate optimisation are reviewed to clarify their contributions and limitations. Second, frontier enabling technologies are analysed, including agriculture-specific large models, generative AI, lightweight edge intelligence, deep reinforcement learning (DRL), embodied AI, federated learning (FL), and privacy-preserving computing. Third, system-level applications integrating DT and AI are discussed, with emphasis on full-lifecycle machinery optimisation, device–edge–cloud collaborative control, multi-agent fleet coordination, predictive maintenance, and Agriculture 5.0-oriented intelligent equipment systems. Key deployment bottlenecks are further identified, including sim-to-real inconsistency, virtual–physical mismatch in DTs, edge-side trade-offs among accuracy, latency, energy consumption, and cost, insufficient validation standards, and economic adoption barriers. Finally, a 2025–2030 roadmap is proposed, highlighting large-model–DT closed loops, control biomimetics, green low-carbon optimisation, and trustworthy human–machine symbiosis for sustainable Agriculture 5.0. Full article

Genomic prediction is now routine in crop improvement, but its main bottleneck has shifted from marker density to environmental complexity. Breeders rarely need predictions for one fixed environment; they need to rank genotypes across target populations of environments that differ in weather, soils, management, and stress timing. This makes genotype-by-environment interaction a primary breeding problem rather than a secondary statistical nuisance. This review examines how genomic, environmental, and phenomic information can be integrated to improve multi-environment prediction in crop breeding pipelines. The review is narrative rather than PRISMA-style, but the literature search and selection logic were structured and explicitly defined. Peer-reviewed English-language studies were identified through structured searches of Web of Science Core Collection and Scopus, supplemented by backward citation screening, with emphasis on literature published from January 2023 to March 2026. Four conclusions emerge. First, environmental information is most useful when it is developmentally aligned, biologically interpretable, and matched to the target population of environments. Second, strong structured statistical baselines remain highly competitive, especially in moderate-sized or highly unbalanced datasets, whereas gains from more flexible machine-learning and deep-learning approaches are most evident in large, sparse, heterogeneous, and multimodal settings. Third, phenomic markers often improve prediction for complex traits, especially yield, because they capture realized crop responses not fully represented by markers alone. Fourth, practical value depends less on isolated gains in predictive accuracy than on evaluation under realistic deployment scenarios, including untested genotype and untested environment settings. Progress therefore requires transparent reporting, benchmark design, stage-aware envirotyping, multimodal integration, uncertainty reporting, and cost-aware deployment. Full article

Climate change continues to threaten global food security. Climate-smart agriculture (CSA) offers a solution to addressing this challenge in urban agriculture (UA). This paper addresses a gap in the empirical literature on decision-making about the adoption of CSA practices by examining the determinants of CSA adoption among small-scale urban crop (SSUC) farmers in eThekwini (ETH) Municipality, South Africa. Grounded in a utility theory framework, the paper draws on 412 respondents (Cochran-estimated) from a multi-stage sample design across four wards, providing reasonable coverage of SSUC farmers in ETH Municipality. While the sample size is statistically representative of SSUC farmers in ETH Municipality, it is a single metropolitan case rather than universal. The results show strong complementarities among these CSA practices, for example, between OM and CD (r ≈ 0.70, p < 0.001) and M and CD (r ≈ 0.61, p < 0.001). The multivariate probit (MVP) model predicts that the socio-economic and institutional factors age, gender, marital and employment status, education, credit access, extension contact, land tenure, and location (distance from home to farm plots) (p < 0.05) were significant determinants of adopting CSA practices by SSUC farmers. The findings contribute to the global literature on the UA–CSA nexus, demonstrating that socio-economic and institutional factors shape the adoption of bundled CSA practices. While the findings underscore the need for integrated, custom, and UA context-specific policy and extension interventions to strengthen urban food system resilience, UA farmers, practitioners, researchers, and policymakers should apply these insights elsewhere with caution. Full article

Tomato (Solanum lycopersicum) cultivation is highly vulnerable to fungal, bacterial, and viral leaf diseases that can significantly reduce crop yield and fruit quality when not detected at early stages. Although recent deep learning approaches have achieved remarkable performance in plant disease classification, many state-of-the-art architectures remain computationally expensive and therefore difficult to deploy on resource-constrained edge devices commonly used in smart agriculture environments. To address this challenge, this paper introduces EcoTomHybridNet, an adaptive resource-aware CNN–Transformer framework designed for efficient tomato leaf disease classification under edge-computing constraints. The proposed architecture combines a lightweight convolutional backbone with a dual-branch inference mechanism composed of a fast convolutional branch for computationally efficient prediction and a Transformer-enhanced branch with local self-attention for richer contextual feature extraction. Unlike conventional lightweight hybrid models relying on static inference pipelines, EcoTomHybridNet integrates a lightweight policy-guided routing mechanism that dynamically allocates inputs between the fast convolutional branch and the Transformer-enhanced branch according to input complexity. This adaptive inference strategy dynamically reduces unnecessary Transformer computations for simpler samples while preserving strong predictive performance on more challenging inputs through policy-guided branch allocation. To further improve representation capability without significantly increasing computational complexity, the proposed student network is trained using knowledge distillation from a ViT-Tiny teacher model. Experimental results on the PlantVillage tomato dataset demonstrate that EcoTomHybridNet achieves 99.42% test accuracy and 99.0% validation accuracy under the full hybrid inference configuration. Additional validation strategies, including 5-fold cross-validation and robustness evaluation under Gaussian noise and motion blur perturbations, indicate stable performance across different data splits and moderate image degradations, suggesting improved generalization capability beyond simple dataset memorization. Furthermore, adaptive routing experiments using a lightweight threshold-based policy mechanism achieved 99.20% test accuracy while reducing computational complexity from 0.36 GFLOPs to 0.25 GFLOPs per image, corresponding to approximately 30% computational savings. These results demonstrate the effectiveness of policy-guided adaptive inference for balancing predictive performance and computational efficiency in edge-oriented plant disease classification. Overall, EcoTomHybridNet provides an efficient and adaptive framework for intelligent plant disease monitoring in IoT-enabled smart agriculture systems. Full article