Search Results (2,918)

Accurate and timely prediction of diseases in water-intensive crops is critical for sustainable agriculture and food security. AI-based crop disease management tools are essential for an optimized approach, as they offer significant potential for enhancing yield and sustainability. This study centers on maize, training deep learning models on UAV imagery and satellite remote-sensing data to detect and predict disease. The performance of multiple convolutional neural networks, such as ResNet-50, DenseNet-121, etc., is evaluated by their ability to classify maize diseases such as Northern Leaf Blight, Gray Leaf Spot, Common Rust, and Blight using UAV drone data. Remotely sensed MODIS satellite data was used to generate spatial severity maps over a uniform grid by implementing time-series modeling. Furthermore, reinforcement learning techniques were used to identify hotspots and prioritize the next locations for inspection by analyzing spatial and temporal patterns, identifying critical factors that affect disease progression, and enabling better decision-making. The integrated pipeline automates data ingestion and delivers farm-level condition views without manual uploads. The combination of multiple remotely sensed data sources leads to an efficient and scalable solution for early disease detection. Full article

The thioredoxin system is crucial for maintaining redox balance and stress responses in plants, but its role in selenium hyperaccumulators remains poorly understood. To our knowledge, this study is the first to perform a genome-wide identification of the thioredoxin system in Se hyperaccumulator Cardamine hupingshanensis. We identified 74 ChTRX genes and 12 ChTR genes, among which ChTRX genes accounted for approximately 86.05% of the total identified thioredoxin system genes. Phylogenetic and structural analyses classified the ChTRXs into two types, typical (with the WCGPC active site) and atypical (with the XCXXC active site), with typical ChTRXs comprising about 48.65% and atypical ChTRXs about 51.35% of the total ChTRXs. Subcellular localization analysis revealed a diverse distribution, such as chloroplast, mitochondrion and cytoplasm. The chloroplast-localized ChTRXs are the most abundant, accounting for approximately 60% of all ChTRXs. Under Se stress, the expression of ChTRX genes exhibited significant tissue-specific differences: approximately 52.5% of ChTRX genes showed responsive expression in the roots, while only 31.25% responded in the leaves, suggesting that root-specific genes may play an important role in mitigating Se-induced oxidative damage. Through expression data and molecular docking analysis, we discovered that ChACHT4-1 can interact with the disulfide bonds of key Se metabolism related enzymes ChAPK and ChAPR, suggesting its potential reductive activity. Furthermore, we predicted stress-responsive ChTRXs regulated by multiple ChNTRs in TRX–TR regulatory pathway. Overall, our research indicates that the thioredoxin system influences Se metabolism in C. hupingshanensis through redox regulation, providing insights into the Se tolerance mechanisms of hyperaccumulating plants and offering perspectives for optimizing Se biofortification strategies in crops. Full article

This paper presents a novel hybrid and hierarchical architecture of a Convolutional Neural Network (CNN), based on MobileNetV2 and Support Vector Machines (SVM) for the classification of crop diseases (SVMobileNetV2). The system feeds from multispectral images captured by Unmanned Aerial Vehicles (UAVs) alongside data from IoT nodes. The primary objective is to improve classification performance in terms of both accuracy and precision. This is achieved by integrating contemporary Deep Learning techniques, specifically different CNN models, a prevalent type of artificial neural network composed of multiple interconnected layers, tailored for the analysis of agricultural imagery. The initial layers are responsible for identifying basic visual features such as edges and contours, while deeper layers progressively extract more abstract and complex patterns, enabling the recognition of intricate shapes. In this study, different datasets of tropical crop images, in this case banana crops, were constructed to evaluate the performance and accuracy of CNNs in detecting diseases in the crops, supported by transfer learning. For this, multispectral images are used to create false-color images to discriminate disease through spectra related to the blue, green and red colors in addition to red edge and near-infrared. Moreover, we used IoT nodes to include environmental data related to the temperature and humidity of the environment and the soil. Machine Learning models were evaluated and fine-tuned using standard evaluation metrics. For classification, we used fundamental metrics such as accuracy, precision, and the confusion matrix; in this study was obtained a performance of up to 86.5% using current deep learning models and up to 98.5% accuracy using the proposed hybrid and hierarchical architecture (SVMobileNetV2). This represents a new paradigm to significantly improve classification using the proposed hybrid CNN-SVM architecture and UAV-based multispectral images. Full article

Fast and precise monitoring of soil organic matter (SOM) during maize growth periods is crucial for real-time assessment of soil quality. However, the big challenge we usually face is that many agricultural soils are covered by crops or snow, and the bare soil period is short, which makes reliable SOM prediction complex and difficult. In this study, an unmanned aerial vehicle (UAV) was utilized to acquire multi-temporal hyperspectral images of maize across the key growth stages at the field scale. The auxiliary predictors, such as spectral indices (I), field management (F), plant characteristics (V), and soil properties (S), were also introduced. We used stepwise multiple linear regression, partial least squares regression (PLSR), random forest (RF) regression, and XGBoost regression models for SOM prediction, and the results show the following: (1) Multi-temporal remote sensing information combined with multi-source predictors and their combinations can accurately estimate SOM content across the key growth periods. The best-fitting model depended on the types of models and predictors selected. With the I + F + V + S predictor combination, the best SOM prediction was achieved by using the XGBoost model (R² = 0.72, RMSE = 0.27%, nRMSE = 0.16%) in the R3 stage. (2) The relative importance of soil properties, spectral indices, plant characteristics, and field management was 55.36%, 26.09%, 9.69%, and 8.86%, respectively, for the multiple periods combination. Here, this approach can overcome the impact of the crop cover condition by using multi-temporal UAV hyperspectral images combined with valuable auxiliary variables. This study can also improve the field-scale farmland soil properties assessment and mapping accuracy, which will aid in soil carbon sequestration and soil management. Full article

Competition is a fundamental ecological interaction among plants, arising when species utilise the same limited resources such as light, water, nutrients, and space. Resource limitations reduce the growth and survival of less competitive species, altering ecosystem structure. In agroecosystems, weed–crop competition is a major challenge, reducing yield and quality. Weeds often exhibit greater adaptability and resource efficiency, enabling them to outcompete crops. Competition intensity is influenced by population density, morphology, phenology and survival strategies. Understanding plant competitive interactions is crucial for ecologists and agronomists to develop sustainable weed management and resource optimization strategies. Climate change further alters competitive dynamics, favoring resilient and plastic species. Mechanisms like allelopathy, aboveground and belowground competition and adaptive growth responses shape community structure. Strategies to reduce weed pressure include breeding competitive crops and integrating cultural practices such as optimal sowing density, narrow row spacing, and cover cropping. Future research should address plant responses to multiple simultaneous stressors, the ecological role of allelochemicals under varying conditions, and the genetic mechanisms of competitive adaptability. A comprehensive understanding of these interactions is essential for designing resilient, high-performing agroecosystems in changing environmental conditions. Full article

Few-shot image classification seeks to recognize novel categories from only a handful of labeled examples, but conventional metric-based methods that rely mainly on global image features often produce unstable prototypes under extreme data scarcity, while local-descriptor approaches can lose context and suffer from inter-class local-pattern overlap. To address these limitations, we propose a Global–Local Feature Fusion network that combines a frozen, pretrained global feature branch with a self-attention based multi-local feature fusion branch. Multiple random crops are encoded by a shared backbone (ResNet-12), projected to Query/Key/Value embeddings, and fused via scaled dot-product self-attention to suppress background noise and highlight discriminative local cues. The fused local representation is concatenated with the global feature to form robust class prototypes used in a prototypical-network style classifier. On four benchmarks, our method achieves strong improvements: Mini-ImageNet 70.31% ± 0.20 (1-shot)/85.91% ± 0.13 (5-shot), Tiered-ImageNet 73.37% ± 0.22/87.62% ± 0.14, FC-100 47.01% ± 0.20/64.13% ± 0.19, and CUB-200-2011 82.80% ± 0.18/93.19% ± 0.09, demonstrating consistent gains over competitive baselines. Ablation studies show that (1) naive local averaging improves over global-only baselines, (2) self-attention fusion yields a large additional gain (e.g., +4.50% in 1-shot on Mini-ImageNet), and (3) concatenating global and fused local features gives the best overall performance. These results indicate that explicitly modeling inter-patch relations and fusing multi-granularity cues produces markedly more discriminative prototypes in few-shot regimes. Full article

Saline-alkali stress seriously affects the growth and development of crops. Sorghum bicolor (L.), a C4 plant, is an important cereal crop in the world, and its growth and geographical distribution are limited by alkali conditions. In this study, sorghum genotypes with different alkaline resistance (alkaline-sensitive Z1 and alkaline-tolerant Z14) were used as experimental materials to explore the effects of alkali on sorghum seedlings. RNA-seq technology was used to examine the differentially expressed genes (DEGs) in alkali-tolerant Z14 to reveal the molecular mechanism of sorghum response to alkali stress. The results showed that plant height, root length, and biomass of both cultivars decreased with time under 80 mM NaHCO₃ treatment, but Z14 showed better water retention abilities. The photosynthetic fluorescence parameters and chlorophyll content also decreased, but the Fv/Fm, ETH, ΦPSII, and chlorophyll content of Z14 were significantly higher than those of Z1. The level of reactive oxygen species (ROS) increased in both sorghum varieties under alkali stress, while the enzyme activities of SOD, POD, CAT, and APX were also significantly increased, especially in Z14, resulting in lower ROS compared with Z1. Transcriptome analysis revealed around 6000 DEGs in Z14 sorghum seedlings under alkali stress, among which 267 DEGs were expressed in all comparison groups. KEGG pathways were enriched in the MAPK signaling pathway, plant hormone signal transduction, and RNA transport. bHLHs, ERFs, NACs, MYBs, and other transcription factor families are actively involved in the response to alkali stress. A large number of genes involved in photosynthesis and the antioxidant system were found to be significantly activated under alkali stress. In the stress signal transduction cascades, Ca²⁺ signal transduction pathway-related genes were activated, about 23 PP2Cs in ABA signaling were upregulated, and multiple MAPK and other kinase-related genes were triggered by alkali stress. These findings will help decipher the response mechanism of sorghum to alkali stress and improve its alkali tolerance. Full article

Manure-based anaerobic digestion (AD) systems serve multiple functions, including waste treatment, energy recovery, and nutrient cycling. However, they also entail additional energy consumption and pollutant emissions. Life cycle assessment (LCA) methodology is typically used to holistically quantify the actual environmental impacts of these systems. Nevertheless, comprehensive reviews synthesizing LCA studies in this field remain limited. Following PRISMA guidelines, this study conducted a systematic literature review of LCA studies on manure-based AD systems, focusing on advancements, inconsistencies, and limitations in LCA methodologies and environmental impact results. The findings indicate considerable variability in functional units, allocation methods, system boundaries, and inventory analysis methods across the literature. These methodological discrepancies and the lack of standardized protocols result in remarkable variability in environmental impact potentials. Additionally, there is lack of consensus on the environmental benefits of AD systems compared to traditional manure management, and co-digestion with energy crops or food waste compared to mono-digestion of manure. Consequently, the environmental impacts of manure-based AD systems remain inconclusive due to methodological heterogeneity and data inconsistencies. Future research should develop scientific and standardized approaches and focus on the completeness of system boundaries, selection of key environmental impact categories, environmental load allocation, inventory data quality, and the transparency of the analysis. Full article

Plant growth-promoting bacteria (PGPBs) offer a sustainable alternative for enhancing crop productivity in low-fertility tropical soils. In this study, 30 bacterial isolates were screened in vitro for multiple PGP traits, including phosphate solubilization (from aluminum phosphate—AlPO₄ and thermophosphate), potassium release from phonolite rock, siderophore production, indole-3-acetic acid (IAA) synthesis, ACC deaminase activity, and antagonism against Fusarium spp. Statistical analysis revealed significant differences (p < 0.05) among the isolates. The most efficient isolates demonstrated a solubilization capacity ranging from 24.0 to 45.2 mg L⁻¹ for thermophosphate and 21.7 to 23.5 mg L⁻¹ for potassium from phonolite. Among them, Pseudomonas azotoformans K22 showed the highest AlPO₄ solubilization (16.6 mg L⁻¹). IAA production among the isolates varied widely, from 1.34 to 9.65 µg mL⁻¹. Furthermore, 17 isolates produced carboxylate-type siderophores, and only Pseudomonas aeruginosa SS183 exhibited ACC deaminase activity, coupled with strong antifungal activity (91% inhibition). A composite performance index identified P. azotoformans K22, E. hormaechei SS150, S. sciuri SS120, and B. cereus SS18 and SS17 as the most promising isolates. This study provides a valuable foundation for characterizing plant growth-promoting traits and identifies key candidates for future validation and the development of microbial consortia. Full article

Acetolactate synthase (ALS) is an important enzyme in plant branched-chain amino acid biosynthesis and the target of several major herbicide classes. Despite its agronomic importance, the role of ALS genes in stress adaptation in the invasive weed Amaranthus palmeri remains unstudied. In this study, four ApALS genes with high motif conservation were identified and analyzed in A. palmeri. Phylogenetic analysis classified ApALS and other plant ALS proteins into two distinct clades, and the ApALS proteins were predicted to localize to the chloroplast. Gene expression analysis demonstrated that ApALS genes are responsive to multiple stresses, including salt, heat, osmotic stress, glufosinate ammonium, and the ALS-inhibiting herbicide imazethapyr, suggesting roles in both early and late stress responses. Herbicide response analysis using an Arabidopsis thaliana ALS mutant (AT3G48560) revealed enhanced imazethapyr resistance, associated with higher chlorophyll retention. Furthermore, high sequence homology between AT3G48560 and ApALS1 suggests a conserved role in protecting photosynthetic function during herbicide stress. This study provides the first comprehensive analysis of the ALS gene family in A. palmeri and offers important insights into its contribution to stress resilience. These findings establish a vital foundation for developing novel strategies to control this pervasive agricultural weed and present potential genetic targets for engineering herbicide tolerance in crops. Full article

This study aims to investigate the multifaceted effects of e-commerce-led digital chain engagement on the income of Chinese crop farmers, distinguishing between participation status and participation depth. The analysis uses data from the China Rural Revitalization Survey (CRRS) conducted in 2020, with 1815 crop-farming households as the sample. To estimate causal effects, treatment effect models and instrumental variable strategies are employed. Results show that e-commerce-led digital chain participation significantly enhances household income, and deeper digital chain engagement amplifies this effect. Mechanism analyses reveal that deep engagement promotes income through multiple channels, including improved digital preparedness, enhanced product sales performance, and increased participation in digital financial services. Heterogeneity analysis indicates that the income gains mainly stem from agricultural revenue, and are more pronounced among cooperative members, though marginal benefits from deeper engagement appear limited. Quantile regressions uncover a pronounced Matthew effect: higher-income households benefit more from digital chain embedding, thereby widening the income gap. Moreover, e-commerce-led digital chain participation also improves farmers’ income satisfaction and their expectations of income sustainability. These findings suggest that policymakers should not only promote basic e-commerce participation but also implement targeted support for deep digital chain embedding to foster inclusive growth while mitigating the Matthew effect. By shifting the focus from binary participation to embedded intensity, this study provides new insights into how e-commerce-led digital transformation shapes rural income structures, offering theoretical and empirical contributions to the literature on agricultural modernization and digital inclusion. Full article

Crack monitoring in concrete structures is essential to maintaining structural integrity. Therefore, this paper proposes a mobile ground robot equipped with a 2-DoF manipulator and stereo vision sensors for autonomous crack monitoring and mapping. To facilitate crack detection over large areas, a 2-DoF motorized manipulator providing linear and rotational motions, with a stereo vision sensor mounted on the end effector, was deployed. In combination with a manual rotation plate, this configuration enhances accessibility and expands the field of view for crack monitoring. Another stereo vision sensor, mounted at the front of the robot, was used to acquire point cloud data of the surrounding environment, enabling tasks such as SLAM (simultaneous localization and mapping), path planning and following, and obstacle avoidance. Cracks are detected and segmented using the deep learning algorithms YOLO (You Only Look Once) v6-s and SFNet (Semantic Flow Network), respectively. To enhance the performance of crack segmentation, synthetic image generation and preprocessing techniques, including cropping and scaling, were applied. The dimensions of cracks are calculated using point clouds filtered with the median absolute deviation method. To validate the performance of the proposed crack-monitoring and mapping method with the robot system, indoor experimental tests were performed. The experimental results confirmed that, in cases of divided imaging, the crack propagation direction was predicted, enabling robotic manipulation and division-point calculation. Subsequently, total crack length and width were calculated by combining reconstructed 3D point clouds from multiple frames, with a maximum relative error of 1%. Full article

Plants have evolved a complex, multilayered immune system that integrates molecular recognition, signaling pathways, epigenetic regulation, and small RNA-mediated control. Recent studies have shown that DNA-level regulatory mechanisms, such as RNA-directed DNA methylation (RdDM), histone modifications, and chromatin remodeling, are critical for modulating immune gene expression, allowing for rapid and accurate pathogen-defense responses. The epigenetic landscape not only maintains immunological homeostasis but also promotes stress-responsive transcription via stable chromatin modifications. These changes contribute to immunological priming, a process in which earlier exposure to pathogens or abiotic stress causes a heightened state of preparedness for future encounters. Small RNAs, including siRNAs, miRNAs, and phasiRNAs, are essential for gene silencing before and after transcription, fine-tuning immune responses, and inhibiting negative regulators. These RNA molecules interact closely with chromatin features, influencing histone acetylation/methylation (e.g., H3K4me3, H3K27me3) and guiding DNA methylation patterns. Epigenetically encoded immune memory can be stable across multiple generations, resulting in the transgenerational inheritance of stress resilience. Such memory effects have been observed in rice, tomato, maize, and Arabidopsis. This review summarizes new findings on short RNA biology, chromatin-level immunological control, and epigenetic memory in plant defense. Emerging technologies, such as ATAC-seq (Assay for Transposase-Accessible Chromatin using Sequencing), ChIP-seq (Chromatin Immunoprecipitation followed by Sequencing), bisulfite sequencing, and CRISPR/dCas9-based epigenome editing, are helping researchers comprehend these pathways. These developments hold an opportunity for establishing epigenetic breeding strategies that target the production of non-GMO, stress-resistant crops for sustainable agriculture. Full article

Crops nitrogen supply through the in situ mineralization of soil organic matter is a critical process for plant nutrition. However, accurately estimating the contribution of mineralization remains challenging. The complexity of biological, chemical, and physical processes in the soil, influenced by environmental conditions, makes it difficult to precisely quantify the amount of nitrogen available for crops. In this study, we created a database by collecting results from 121 mineralization monitoring experiments carried out between 2015 and 2021 on different experimental plots across Wallonia, Southern Belgium, and assessed the efficiency of predictive mineralization methods. The most impactful analytical parameters on in situ mineralization (ISM), determined using LIXIM program, appeared to be potentially mineralizable nitrogen (PMN) (r = 0.79). PMN, estimated by anaerobic soil incubation, also allowed the effective consideration of the after-effects of grassland termination and manure inputs. A multiple linear regression (MLR) combining PMN, POxC, pH, TOC:N, and TOC:clay significantly improved the prediction of soil nitrogen mineralization available for crops, achieving r = 0.87 (vs. r = 0.58 for the current method), while reducing dispersion by 41% (RMSE 56.35 → 33.13 kg N·ha⁻¹). The use of a more flexible Bootstrap Forest model (BFM) further enhanced performance, reaching r = 0.92 and a 50.8% reduction in dispersion compared to the current method (RMSE 56.35 → 27.76 kg N·ha⁻¹), i.e., about 16% lower RMSE than the MLR. Those models provided practical and efficient tools to better manage nitrogen resources in temperate agricultural systems. Full article

Tillage practices can significantly impact soil structure and pore size distribution and connectivity, consequently affecting the shape of the soil water retention curve (SWRC) and its related estimated hydraulic parameters in the top layer of soil. This study investigated the effect of no-tillage (NT) and conventional tillage (CT) practices on SWRCs and their soil hydraulic parameters, estimated by the Brooks–Corey (BC) function at 0–15 and 15–30 cm depths within sugarbeet and corn planting rows in clay loam and sandy loam soils, respectively. Soil water retention curves were measured using the evaporative method (HYPROP). Measured SWRC results were modeled for both untilled and tilled soils using the BC function for each depth in both soils. In clay loam, results indicated that all soil parameters of the BC function, water contents at 330 (θ₃₃₀) and 15,000 (θ_15,000) hPa, and plant available soil water content (AW) were not significantly affected by the type of tillage at either soil depth. The lack of difference in results between NT and CT may be due to considerable soil disturbance, primarily by the harvest process of sugarbeet roots. However, in sandy loam, results indicated that differences occurred in SWRC’s estimated parameters between the NT and CT practices. Averaged across 4 years and two soil depths, the pore size distribution index (λ) and saturated water content (θ_s) were significantly larger under CT than under NT due to greater soil loosening and disturbance caused by multiple passes of the CT process, thereby developing more soil macroporosity. However, the θ₃₃₀ and AW were significantly larger in NT than in CT due to reduced soil disturbance and improved soil structure under NT compared to CT practices. Regardless of tillage, measurements of SWRC are important for determining better irrigation management practices, enabling producers to optimize crop productivity, while saving water and sustaining water quality. Full article