Search Results (4,533)

The flavor and color profiles of vegetables are crucial in determining their nutritional value, health benefits, taste, and visual appeal. The genomic characteristics of plants control these traits. Components such as sugars, organic acids, amino acids, phenolic compounds, and essential oils, as well as color pigments like anthocyanin, chlorophyll, carotenoid, and betalain, are synthesized in plants based on their genetic structure. Environmental factors like temperature, water, light, and soil can affect the production and intensity of these components. Long-term environmental changes, such as climate change, can significantly alter the dynamics of these components. This comprehensive review focuses on the genetic and environmental interactions underlying the flavor and color profiles of vegetables, with particular emphasis on the analysis of quantitative trait loci (QTL) associated with these traits. The article discusses the identification of genes that regulate taste and color in vegetables and how these genes have been localized in QTL mapping studies. It also discusses the influence of environmental factors on taste and color, as well as gene–environment interactions. Furthermore, it focuses on how this information can be used to improve plant breeding and sustainable agriculture and emphasizes that data from QTL analyses provide valuable insights into the integration of genetic and environmental approaches to improve vegetable quality and meet consumer preferences. In conclusion, the review aims to be a valuable resource for both researchers and professionals interested in the genetic and environmental aspects of taste and color in vegetables. Full article

Localization and mapping remain critical challenges for Unmanned Ground Vehicles (UGVs) operating in unstructured natural environments, such as forests and agricultural fields. While Visual SLAM (VSLAM) and Visual–Inertial SLAM (VI-SLAM) have matured significantly in structured and urban scenarios, their extension to outdoor natural domains introduces severe challenges, including dynamic vegetation, illumination variations, a lack of distinctive features, and degraded GNSS availability. Recent advances in Deep Learning have brought promising developments to VSLAM- and VI-SLAM-based pipelines, ranging from learned feature extraction and matching to self-supervised monocular depth prediction and differentiable end-to-end SLAM frameworks. Furthermore, emerging methods for adaptive sensor fusion, leveraging attention mechanisms and reinforcement learning, open new opportunities to improve robustness by dynamically weighting the contributions of camera and IMU measurements. This review provides a comprehensive overview of Visual and Visual–Inertial SLAM for UGVs in unstructured environments, highlighting the challenges posed by natural contexts and the limitations of current pipelines. Classic VI-SLAM frameworks and recent Deep-Learning-based approaches were systematically reviewed. Special attention is given to field robotics applications in agriculture and forestry, where low-cost sensors and robustness against environmental variability are essential. Finally, open research directions are discussed, including self-supervised representation learning, adaptive sensor confidence models, and scalable low-cost alternatives. By identifying key gaps and opportunities, this work aims to guide future research toward resilient, adaptive, and economically viable VSLAM and VI-SLAM pipelines, tailored for UGV navigation in unstructured natural environments. Full article

Google Earth Engine (GEE) has revolutionised remote sensing. The GEE cloud platform lets users quickly analyse large satellite imagery datasets with custom programmes, enhancing global-scale analysis. Crop condition monitoring using GEE would greatly help in decision-making and precision agriculture. Estimating canopy chlorophyll content (CCC) is an effective way to monitor crops using remote sensing because leaf chlorophyll is a key indicator. A hybrid model that combines radiative transfer models (RTMs), such as PROSAIL, with Gaussian Process Regression (GPR) can effectively estimate crop biophysical parameters using remote sensing images. GPR has proven to be one of the best methods for this purpose. This study aimed to develop a hybrid model to estimate CCC from S2 imagery and transfer it to the GEE platform for efficient data processing. In this work, the CCC (g/cm²) data from the S2 biophysical processor toolbox for the S2 imagery of the ICAR-Indian Agricultural Research Institute (IARI) on 23 February 2023 were used as observation data to train the hybrid algorithm. The hybrid model was successfully validated against the 155 input data with an R2 of 0.94, RMSE of 10.02, and NRMSE of 5.04%. The model was integrated into GEE to successfully generate a CCC-estimated map of IARI using S2 imagery from 23 February 2023. An R2 value of 0.96 was observed when GEE-estimated CCC values were compared against CCC values estimated locally. This establishes that the GEE-based CCC estimation with the PROSAIL + GPR hybrid model is an effective and accurate method for monitoring vegetation and crop conditions over large areas and extended periods. Full article

Unmanned aerial vehicles (UAVs) have become essential tools for monitoring crop condition, detecting early signs of plant stress, and supporting timely interventions in modern precision agriculture. However, real-time onboard image analysis remains challenging due to the limited computational and energy resources of small embedded UAV platforms. This work presents a deployment-aware neural architecture search (NAS) framework for discovering lightweight object detection networks explicitly optimized for edge hardware constraints. Building on the YOLOv8n baseline, the proposed NAS procedure yields detector architectures that substantially reduce computational load while preserving high detection accuracy for agricultural field monitoring tasks. The best-discovered model reduces GFLOPs by 37.0% and parameters by 61.3% compared to YOLOv8n, with only a 1.96% decrease in mAP@50. When deployed on an NVIDIA Jetson Nano, it achieves a 28.1% increase in inference speed and an 18.5% improvement in energy efficiency under ONNX Runtime, with additional gains using TensorRT FP16. Evaluation on wheat head and cotton seedling datasets demonstrates strong generalization across crop types and varying imaging conditions. By enabling highly efficient onboard inference, the proposed NAS framework supports practical UAV-based crop monitoring workflows and contributes to the development of responsive, field-ready remote sensing systems in resource-limited environments. Full article

Tea bud recognition and localization constitute a fundamental step toward enabling fine-grained tea plantation management and intelligent harvesting, offering substantial value in improving the picking quality of premium tea materials, reducing labor dependency, and accelerating the development of smart tea agriculture. However, most existing methods for detecting tea buds are built upon Artificial Neural Networks (ANNs) and rely extensively on floating-point computation, making them difficult to deploy efficiently on energy-constrained edge platforms. To address this challenge, this paper proposes an energy-efficient tea bud detection model, GAE-SpikeYOLO, which improves upon the Spiking Neural Networks (SNNs) detection framework SpikeYOLO. Firstly, Gated Attention Coding (GAC) is introduced into the input encoding stage to generate spike streams with richer spatiotemporal dynamics, strengthening shallow feature saliency while suppressing redundant background spikes. Secondly, the model incorporates the Temporal-Channel-Spatial Attention (TCSA) module into the neck network to enhance deep semantic attention on tea bud regions and effectively suppress high-level feature responses unrelated to the target. Lastly, the proposed model adopts the EIoU loss function to further improve bounding box regression accuracy. The detection capability of the model is systematically validated on a tea bud object detection dataset collected in natural tea garden environments. Experimental results show that the proposed GAE-SpikeYOLO achieves a Precision (P) of 83.0%, a Recall (R) of 72.1%, a mAP@0.5 of 81.0%, and a mAP@[0.5:0.95] of 60.4%, with an inference energy consumption of only 49.4 mJ. Compared with the original SpikeYOLO, the proposed model improves P, R, mAP@0.5, and mAP@[0.5:0.95] by 1.4%, 1.6%, 2.0%, and 3.3%, respectively, while achieving a relative reduction of 24.3% in inference energy consumption. The results indicate that GAE-SpikeYOLO provides an efficient and readily deployable solution for tea bud detection and other agricultural vision tasks in energy-limited scenarios. Full article

This paper presents the results of assessing the influence of siltation factors in 23 ponds in one of the most agriculturally developed macro-regions of European Russia—the Central Russian Upland. Key natural and anthropogenic factors determining the intensity of pond siltation have been identified, and a typification of ponds has been developed to predict the rate of accumulation of bottom sediments in them. For the typification, statistical methods such as correlation analysis (Spearman’s coefficient), cluster and factor analysis, and the Random Forest machine learning algorithm were used. Correlation analysis revealed that the percentage of catchment cultivation has a significant effect (r = 0.55, p < 0.01) on the volume of bottom sediments, while soil loss (r = 0.47, p < 0.05) and vertical terrain dissection (r = 0.43, p < 0.05) have a moderate effect. The most important factors in the siltation process are the average slope of the catchment (24.5%), the percentage of cultivated soils (18.8%), and the average annual soil loss (14.1%). All factors were grouped into three clusters, which explained 77.8% of the variance. As a result, four pond types were identified, differing in their dominant limiting factors: pond hydrological characteristics, catchment morphometry, and the degree of anthropogenic transformation of the catchment. Verification of the typification was carried out based on the calculation of annual soil losses considering the sediment delivery coefficient; the discrepancies between the calculated and actual pond sediment volumes were 1.2–10.0%. The proposed approach, which recommends a multi-scale assessment of potential sediment formation volumes using remote sensing data and thematic mapping, offers heuristic potential for identifying the most degraded water bodies. This enables the planning of priority sites and rehabilitation measures for their restoration within the framework of regional soil and water conservation programs. Full article

Accurate path planning was the prerequisite for autonomous navigation of agricultural vehicles. An Unmanned Aerial Vehicle (UAV)-based coverage path planning was developed in this research for automating guidance of agricultural vehicles and reducing the operator maneuver in the creation of navigation maps. High-resolution orthophoto maps of the field were constructed by using low-altitude UAV photogrammetry to obtain spatial information. Travel paths and working paths were automatically generated from anchor points selected by the operator under the image coordinate domain. The navigation path for unmanned agricultural vehicles was generated by Mercator projection-based conversion for the anchor pixel coordinates into latitude and longitude geographic coordinates. A Graphical User Interface (GUI) was developed for path generation, visualization, and performance evaluation, through which the proposed path planning method was implemented for autonomous agricultural vehicle navigation. Calculation accuracy tests demonstrated the mean planar coordinate error was 2.23 cm and the maximum error was 3.37 cm for path planning. Field tests showed that lateral navigation errors remained within ±5.5 cm for the unmanned high-clearance sprayer, which indicated that the developed UAV-based coverage path planning method was feasible and featured high accuracy. It provided an effective solution for achieving fully autonomous agricultural vehicle operations. Full article

The pressing need for sustainable, plant-based alternatives is highlighted by the growing resistance of agricultural pests to synthetic pesticides. This study examined the pesticidal potential of phytocompounds from C. tora discovered by GC–MS analysis against important tomato insect (T. absoluta) and fungal pathogen (A. solani). The binding stability and interaction dynamics of specific metabolites with fungal virulence (polygalacturonase, MAP kinase HOG1, and effector AsCEP50) and insect neuromuscular (ryanodine receptor and sodium channel protein) targets were assessed using molecular docking and 100 ns molecular dynamics simulations. Among the screened compounds, squalene and 4,7,10,13,16,19-docosahexaenoic acid, methyl ester (DHAME) exhibited the strongest binding affinities and conformational stability, with MM-GBSA binding free energies of −38.09 kcal·mol⁻¹ and −52.81 kcal·mol⁻¹ for squalene complexes in T. absoluta and A. solani, respectively. Persistent hydrophobic and mixed hydrophobic–polar contacts that stabilised active-site residues and limited protein flexibility were found by ProLIF analysis. These lively and dynamic profiles imply that DHAME and squalene may interfere with calcium signalling and stress-response pathways, which are essential for the survival and pathogenicity of pests. Hydrophobic interactions were further confirmed as the primary stabilising force by the preponderance of van der Waals and nonpolar solvation energies. The findings show that C. tora metabolites, especially squalene and DHAME, are promising environmentally friendly biopesticide candidates that have both insecticidal and antifungal properties. Their development as sustainable substitutes in integrated pest management systems are supported by their stability, binding efficacy and predicted biosafety. Full article

Brazil nut (Bertholletia excelsa Bonpl.) is a major non-timber forest product in the Amazon, supporting extractivist communities in Brazil, Bolivia, and Peru and contribute to forest conservation. Unlike other extractive products, Brazil nut production has not declined under commercial use and is recognized for its socioeconomic and environmental importance. Precision agriculture has been transformed by the use of unmanned aerial vehicles (UAVs) and artificial intelligence (AI), which enable monitoring efficiency and yield estimation in several crops, including the Brazil nut. This study assessed the potential of using UAV-based imagery combined with YOLOv8 object detection model to identify and quantify Brazil nut fruits in a native forest fragment in eastern Acre, Brazil. A UAV was used to capture canopy images of 20 trees with varying diameters at breast height. Images were manually annotated and used to train the YOLOv8 with an 80/20 split for training and validation/testing. Model performance was evaluated using precision, recall, F1-score, and mean Average Precision (mAP). The model achieved recall above 90%, with an F1-score of 0.88, despite challenges from canopy complexity and partial occlusion. These results indicate that UAV-based imagery combined with AI detection provides an approach for estimating Brazil nut yield, reducing manual effort and improving market strategies for extractivist communities. This technology supports sustainable forest management and socioeconomic development in the Amazon. Full article

Accurate and timely agricultural mapping is essential for supporting sustainable agricultural development, resource management, and food security. Despite its importance, Vietnam lacks detailed and consistent large-scale agricultural maps. In this study, we produced the first national-scale agricultural map of Vietnam for 2024 using a UNet++ deep learning architecture that integrates multi-temporal Sentinel-1 and Sentinel-2 imagery with Global-30 DEM data. The resulting product includes 15 land-cover categories, eight of which represent the most popular agricultural types in Vietnam. We further evaluate the model’s transferability by applying the 2024 trained model to generate a corresponding map for 2020. The approach achieves overall classification accuracies of $83.01\%\pm 1.37\%$ (2020) and $80.09\%\pm 0.76\%$ (2024). To address class imbalance within the training dataset, we introduced an adaptive weight combined loss function that automatically adjusts the weight of dice loss and cross-entropy loss within a combined loss function during the model training process. Full article

From adaptation to building effective resilience to climate change is critical for transforming West and Central Africa (WCA) agricultural system. Climate-Smart Agriculture (CSA) is an approach initiated by leading international organizations to ensure food security, increased adaptation to climate change and mitigation. Its application spans from innovative policies, practices, technologies, innovations and financing. However, CSA initiatives lack scientific-based assessment prior to implementation to ensure their effectiveness. To fill this gap, future interventions should not only be assessed using rigorous methodology but should also be built on lessons learned from previous initiatives. Although there are a lot of climate related agricultural initiatives in WCA, most of them have not been analyzed through a CSA lens and criteria to capitalize on their experiences to improve future interventions. In this study we mapped previous climate-related initiatives in WCA, highlighted their gaps and lessons learned to accelerate the implementation of CSA in the region. The study covered 20 countries in WCA: Benin, Burkina Faso, Cameroon, Cape Verde, Central African Republic, Chad, Côte d’Ivoire, Congo, Gabon, Gambia, Ghana, Guinea, Liberia, Mali, Mauritania, Niger, Nigeria, Senegal, Sierra Leone, Togo. CSA initiatives were reviewed using a three-steps methodology: (i) national data collection, (ii) regional validation of the national database, (iii) data analysis including spatial mapping. Data was collected from the websites of international, regional and national organizations working in the field of agricultural development in the region. Each initiative was analyzed using a multicriteria analysis based on CSA principles. A total of 1629 CSA related initiatives were identified in WCA. Over 75% of them were in the form of projects/programs with more of a focus on the first CSA pillar (productivity and food security), followed by adaptation. The mitigation pillar is less covered by the initiatives. Animal production, fisheries, access to markets, and energy are poorly included. More than half of these initiatives have already been completed, calling for more new initiatives in the region. Women benefit very little from the implementation of the identified CSA initiatives, despite the substantial role they play in agriculture. CSA initiatives mainly received funding from technical and financial partners and development partners (45%), banks (22%), and international climate financing mechanisms (20%). Most of them were implemented by government institutions (48%) and development partners (23%). In total, more than 600 billion EUR have been disbursed to implement 83 of the 1629 initiatives identified. These initiatives contributed to reclaiming and/or rehabilitating almost 2 million ha of agricultural land in all countries between 2015 and 2025. Future initiatives should ensure the consideration of the three CSA pillars right from their formulation to the implementation. These initiatives should consider investing in mixed production systems like crop-animal-fisheries. Activities should be built around CSA innovation platforms to encourage networking among actors for more sustainability. Full article

Assessment of crop water requirements (ETc) and their meteorological driving mechanisms are critical for irrigation management in arid inland river basins. Taking the Tailan River Irrigation District (Xinjiang, China) as a case study, temporal changes in cropping structure, crop-specific ETc, and irrigation-district–scale agricultural water demand, as well as the meteorological controls on ETc, were quantified for the period 2000–2024 using Google Earth Engine-based crop mapping, the CROPWAT model, and path analysis. The results demonstrated that the 2024 random forest classification model achieved high accuracy (overall accuracy = 0.902; Kappa = 0.876), and validation against statistical yearbook data confirmed the reliability of crop-area estimation. Cotton dominated the cropping structure (228.6–426.0 km²), while the orchard area expanded markedly from 206.5 km² in 2000 to 393.2 km² in 2024; wheat exhibited strong interannual variability, and maize occupied a relatively small area. Crop-specific ETc differed markedly among crop types, following the order orchard > cotton > maize > wheat, with orchards maintaining the highest water requirement across all growth stages. Total agricultural water demand, estimated by integrating crop-specific ETc with remotely sensed planting areas, increased from approximately 260 million m³ to over 500 million m³ after 2010, mainly due to orchard expansion and cotton cultivation. Path analysis indicated that interannual ETc variability exhibited a stronger statistical association with wind speed than with other meteorological variables. These results provide a quantitative basis for cropping-structure optimization and water-saving irrigation management under changing climatic conditions. Full article

The development of urban green infrastructures (UGI) is considered among the main nature-based solutions for climate mitigation in cities; however, the role of soils in the carbon (C) balance of UGI ecosystems remains largely overlooked. Urban green spaces are typically dominated by constructed Technosols, created by adding organic materials on top of former natural or agricultural subsoils. The combined effects of land-use history and current UGI management result in a high spatial variation of soil organic carbon (SOC) stocks and soil CO₂ emissions. Our study aimed to explore this variation for the case of Wageningen University campus. Developed on a former agricultural land, the campus area includes green spaces dominated by trees, shrubs, lawns, and herbs, with well-documented management practices for each vegetation type. Across the campus area (~32 ha), a random stratified topsoil sampling (n = 90) was conducted to map the spatial variation of topsoil (0–10 cm) SOC stocks. At the key sites (n = 8), representing different vegetation types and time of development (old, intermediate, and recent), SOC profile distribution was analyzed including SOC fractionation in surface and subsequent horizons, as well as the dynamics in soil CO₂ emissions, temperature, and moisture. Topsoil SOC contents on campus ranged from 1.1 to 5.5% (95% confidence interval). On average, SOC stocks under trees and shrubs were 10–15% higher than those under lawns and herbs. The highest CO₂ emissions were observed from soil under lawns and coincided with a high proportion of labile SOC fraction. Temporal dynamics in soil CO₂ emissions were mainly driven by soil temperature, with the strongest relation (R² = 0.71–0.88) observed for lawns. Extrapolating this relationship to the calendar year and across the campus area using high-resolution remote sensing data on surface temperatures resulted in a map of the CO₂ emissions/SOC stocks ratio, used as a spatial proxy for C turnover. Areas dominated by recent and intermediate lawns emerged as hotspots of rapid C turnover, highlighting important differences in the role of various UGI types in the C balance of urban green spaces. Full article

The mapping of vineyard cultivars presents a substantial challenge in digital agriculture due to the crop’s high intra-class heterogeneity and low inter-class variability. High-dimensional spectral datasets, such as hyperspectral or spectrometry data, can overcome these difficulties. However, research has yet to fully address the need for optimal spectral feature subsets tailored for grapevine cultivar discrimination, while few studies have systematically examined waveband subsets that transfer effectively across different learning algorithms. This study sets out to address these gaps by introducing a Partial Least Squares (PLS)-based ensemble feature selection framework with Weighted Borda Count aggregation for cultivar discrimination. Using in-field spectrometry data, collected for six cultivars, and 18 PLS-based feature selection methods spanning filter, wrapper, and hybrid approaches, the PLS–ensemble identified 100 wavebands most relevant for cultivar discrimination, reducing dimensionality by ~95%. The efficacy and transferability of this subset were evaluated using five classification algorithms: Oblique Random Forest (oRF), Multinomial Logistic Regression (Multinom), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and a 1D Convolutional Neural Network (CNN). For oRF, Multinom, SVM, and MLP, the PLS–ensemble subset improved accuracy by 0.3–12% compared with using all wavebands. The subset was not optimal for the 1D-CNN, where accuracy decreased by up to 5.7%. Additionally, this study investigated waveband binning to transform narrow hyperspectral bands into broadband spectral features. Using feature multicollinearity and wavelength position, the 100 selected wavebands were condensed into 10 broadband features, which improved accuracy over both the full dataset and the original subset, delivering gains of 4.5–19.1%. The SVM model with this 10-feature subset outperformed all other models (F1: 1.00; BACC: 0.98; MCC: 0.78; AUC: 0.95). Full article

Arid and semi-arid regions are highly vulnerable to drought and depend heavily on rainfed agriculture. To minimize the impact of drought, a transition from crisis management to risk management is necessary, which requires a comprehensive risk assessment that accounts for not only drought hazard but also drought vulnerability and population exposure. However, integrated studies that account for socio-economic, agricultural, demographic, and climate factors are currently lacking in Iran. The objective of this study is to comprehensively assess the spatio-temporal changes in drought risk from 2000 to 2019 across Iran. We used the standardized precipitation evapotranspiration index (SPEI) and multiple socio-economic and demographic data to compute drought risk. In particular, we used the SPEI to map drought hazard, an analytical hierarchical process method to assess drought vulnerability, and population density data to compute population exposure. Drought risk increased in 57% of the area of Iran, mainly in the northwest, west, and central regions, at a rate of up to 10% per year. In 21% of the area of Iran, drought risk declined by up to 10% per year, predominantly in the northern and southern regions of the Alborz Mountains, encompassing the provinces of Tehran, Gilan, Mazandaran, and Khorasan Razavi. Our results show that the spatial patterns of drought risk vary across Iran and are modulated by the interaction between climatic and socio-economic factors. The results of this study provide useful information for drought risk management and intervention in Iran. Full article