Search Results (597)

Cotton is an important economic crop, and its weed management directly affects yield and quality. In actual cotton fields, detection accuracy still faces challenges due to the complex types of weeds, variable morphologies, and environmental factors. Most existing models rely on the attention mechanism to improve performance, but channel attention tends to ignore spatial information, while full spatial attention brings high computational costs. Therefore, this paper proposes a grouped enhanced fusion attention mechanism (GEFA), which combines grouped convolution and local spatial attention to reduce complexity and parameter quantity while effectively enhancing feature expression ability. The GEFAY detection model constructed based on GEFA achieves good balance in efficiency, accuracy, and complexity on the CottonWeedDet12, VOC, and COCO datasets. Compared with classic attention methods, this model has the smallest increase in parameters and computational costs while significantly improving accuracy. It is more suitable for deployment on edge devices. The further designed end-to-end intelligent weed detection system and edge device deployment can achieve image detection on local maps and real-time cameras, with good practicality and scalability, providing effective technical support for intelligent visual applications in precision agriculture. Full article

Protecting groundwater against pollution from agricultural sources is a key aspect of sustainable management of soil and water resources. Implementation of sustainable strategies for agricultural production can be supported by modeling tools, which allow us to quantify the effects of different agricultural practices in the context of groundwater vulnerability to contamination. In this study we present a method to assess groundwater vulnerability to nitrate pollution based on a combination of the SWAT agro-hydrological model and the DRASTIC index method. SWAT modeling was applied to assess different scenarios of agricultural practices and identify solutions for sustainable management of soil and groundwater and reduction of nitrate pollution. The developed method was implemented for groundwater resources in a study area (Puck Bay region, southern Baltic coast), which represented a complex multi-aquifer system formed in Quaternary fluvioglacial deposits (sand and gravel) separated by moraine tills. In order to investigate the effects of different agricultural practices, 12 scenarios have been defined, which were grouped into four classes: crop type, fertilizer management, tillage, and grazing. An overlay index structure was applied, and ratings and weights to several factors were assigned. All analyses were processed using GIS tools, and the results are presented in the form of maps, which categorize groundwater vulnerability to nitrate pollution into five classes, ranging from very low to very high. The results reveal significant variability in groundwater vulnerability to nitrate pollution in the study area. Agricultural practices have a very strong influence on groundwater vulnerability by controlling both recharge rates and nitrogen losses from the soil profile. The most pronounced increases in vulnerability were associated with scenarios involving excessive fertilization and intensive grazing. Among crop types, potato cultivation appears to pose the greatest risk to groundwater quality. Full article

Weed competition in red beet (Beta vulgaris L. Conditiva Group) directly reduces crop yield and quality, making detection and eradication essential. This study proposed a three-phase experimental protocol for multi-class detection (cultivation and six types of weeds) based on RGB (red-green-blue) colour images acquired in a greenhouse, using state-of-the-art deep learning (DL) models (YOLO and RT-DETR family). The objective was to evaluate and optimise performance by identifying the combination of architecture, model scale and input resolution that minimises false negatives (FN) without compromising robust overall performance. The experimental design was conceived as an iterative improvement process, in which each phase refines models, configurations, and selection criteria based on performance from the previous phase. In phase 1, the base models YOLOv9s and RT-DETR-l were compared at 640 × 640 px; in phase 2, the YOLOv8s, YOLOv9s, YOLOv10s, YOLO11s, YOLO12s and RT-DETR-l models were compared at 640 × 640 px and the best ones were selected using the F1 score and the FN rate. In phase 3, the YOLOv9 (s = small, m = medium, c = compact, e = extended) and YOLOv10 (s = small, m = medium, l = large, x = extra-large) families were scaled according to the number of parameters (s/m/c-e/l-x sizes) and resolutions of 1024 × 1024 and 2048 × 2048 px. The best results were achieved with YOLOv9e-2048 (F1: 0.738; mAP@0.5 (mean Average Precision): 0.779; FN: 28.3%) and YOLOv10m-2048 (F1: 0.744; mAP@0.5: 0.775; FN: 27.5%). In conclusion, the three-phase protocol allows for the objective selection of the combination of architecture, scale, and resolution for weed detection in greenhouses. Increasing the resolution and scale of the model consistently reduced FNs, raising the sensitivity of the system without affecting overall performance; this is agronomically relevant because each FN represents an untreated weed. Full article

High-precision monitoring of arid wetlands is vital for ecological conservation, yet traditional methods incur prohibitive labeling costs due to complex features. In this study, the wetland of Bosten Lake in Xinjiang is selected as a case area, where Pleiades and PlanetScope-3 multimodal remote sensing data are fused using the Gram–Schmidt method to generate imagery with high spatial and spectral resolution. Based on this dataset, we systematically compare the performance of fully supervised models (FCN, U-Net, DeepLabV3+, and SegFormer) with a weakly supervised learning model, One Model Is Enough (OME), for classifying 19 wetland–cropland mosaic types. Results demonstrate that: (1) SegFormer achieved the best overall performance (98.75% accuracy, 95.33% mIoU), leveraging its attention mechanism to enhance semantic understanding of complex scenes. (2) The weakly supervised OME, using only image-level labels, matched fully supervised performance (98.76% accuracy, 92.82% F1-score) while drastically reducing labeling effort. (3) Multimodal fusion boosted all models’ accuracy, most notably increasing U-Net’s mIoU by 63.39%. (4) Models exhibited complementary strengths: U-Net excelled in wetland vegetation segmentation, DeepLabV3+ in crop classification, and OME in preserving spatial details. This study validates a pathway integrating multimodal fusion with WSL to balance high accuracy and low labeling costs for arid wetland mapping. Full article

The increasing complexity of plant disease manifestations, especially in cases of multiple simultaneous infections, poses significant challenges to sustainable agriculture. To address this issue, we introduce the Apple Leaf Mixed Disease Recognition (ALMDR) model, a novel multi-task learning approach specifically designed for identifying and quantifying mixed disease infections in apple leaves. ALMDR comprises four key modules: a Group Feature Pyramid Network (GFPN) for multi-scale feature extraction, a Multi-Label Classification Head (MLCH) for disease type prediction, a Leaf Segmentation Head (LSH), and a Lesion Segmentation Head (LeSH) for precise delineation of leaf and lesion areas. The GFPN enhances the traditional Feature Pyramid Network (FPN) through differential sampling and grouping strategies, significantly improving the capture of fine-grained disease characteristics. The MLCH enables simultaneous classification of multiple diseases on a single leaf, effectively addressing the mixed infection problem. The segmentation heads (LSH and LeSH) work in tandem to accurately isolate leaf and lesion regions, facilitating detailed analysis of disease patterns. Experimental results on the Plant Pathology 2021-FGVC8 dataset demonstrate ALMDR’s effectiveness, outperforming state-of-the-art methods across multiple tasks. Our model achieves high performance in multi-label classification (F1-score of 93.74%), detection and segmentation (mean Average Precision (mAP) of 51.32% and 45.50%, respectively), and disease severity estimation ($R^2$ = 0.9757). Additionally, the model maintains this accuracy while processing 6.25 frames per second, balancing performance with computational efficiency. ALMDR demonstrates potential for real-time disease management in apple orchards, with possible applications extending to other crops. Full article

We present a novel framework for hyperspectral satellite image classification that explicitly balances spatial nearness with spectral similarity. The proposed method is trained on closed-set datasets, and it generalizes well to open-set agricultural scenarios that include both class distribution shifts and presence of novel and absence of known classes. This scenario is reflective of real-world agricultural conditions, where geographic regions, crop types, and seasonal dynamics vary widely and labeled data are scarce and expensive. The input data are projected onto a lower-dimensional spectral manifold, and a pixel-wise classifier generates an initial class probability saliency map. A kernel-based spectral-spatial weighting strategy fuses the spatial-spectral features. The proposed approach improves the classification accuracy by $7.22$–$15\%$ over spectral-only models on benchmark datasets. Incorporating an additional unsupervised learning refinement step further improves accuracy, surpassing several recent state-of-the-art methods. Requiring only 1–$10\%$ labeled training data and at most two tuneable parameters, the framework operates with minimal computational overhead, qualifying it as a data-efficient and scalable few-shot learning solution. Recent deep architectures although exhibit high accuracy under data rich conditions, often show limited transferability under low-label, open-set agricultural conditions. We demonstrate transferability to new domains—including unseen crop classes (e.g., paddy), seasons, and regions (e.g., Piedmont, Italy)—without re-training. Rice paddy fields play a pivotal role in global food security but are also a significant contributor to greenhouse gas emissions, especially methane, and extent mapping is very critical. This work presents a novel perspective on hyperspectral classification and open-set adaptation, suited for sustainable agriculture with limited labels and low-resource domain generalization. Full article

Accurate stand count and growth stage detection are essential for crop monitoring, since traditional methods often overlook field variability, leading to poor management decisions. This study evaluated the performance of the YOLOv9-small model for detecting and counting corn plants under real field conditions. The model was tested across three soil background types, two flight heights (30 and 70 m), and four corn growth stages (V2, V3, V5, and V6). Unmanned aerial vehicle (UAV) imagery was collected from three distinct fields and cropped into 640 × 640 pixels. Datasets were split into training (70%), validation (20%), and testing (10%) datasets. Model performance was assessed using precision, recall, classification loss, and mean average precision of 50% and 50–90%. The results showed that the V3 and V5 stages yielded the highest detection accuracy, with mAP50 values exceeding 85% in conventional tillage fields and slightly lower performance in gray/red-brown conditions due to background interference. Increasing flight height to 70 m reduced accuracy by 8–12%, though precision remained high, particularly at V5, and performance was poorest for V2 and V6. In conclusion, YOLOv9-small is effective for early-stage corn detection, particularly at V3 and V5, with 30 m providing optimal results. However, 70 m may be acceptable at V5 to optimize mapping time. Full article

Phosphorus (P) characteristics significantly affect crop yield and P use efficiency (PUE). It is unclear whether different types of acidic phosphate fertilizers can enhance the availability of phosphorus in liming soil and soybean yields. In this field experiment in 2022 and 2023 in Xinjiang, China, four phosphate fertilization treatments, including no phosphate fertilization (CK), application of monoammonium phosphate (MAP), application of urea phosphate (UP), and application of a mixture of monoammonium phosphate and urea phosphate (8:2, M8U2), were designed. Then, the impacts of the four phosphate treatments on the PUE, growth, and yield of the high-oil soybean variety Kennong 23 under drip irrigation were explored. The results showed that the application of phosphate fertilizers significantly increased the soil inorganic P, available P, and total P content compared with CK, promoting the growth and yield formation of soybeans. The soil Ca2-P content of the UP treatment was higher than that of the MAP treatment. The soil Ca8-P content of the M8U2 treatment was higher than that of the MAP treatment, but the soil phosphorus fixation was lower. The soil available P content, soybean plant P accumulation, leaf photosynthetic capacity, and dry matter accumulation all reached the maximum in the M8U2 treatment. The soybean yield, net revenue, and PUE of the M8U2 treatment were 6.04%, 9.37%, and 14.16% higher than those of the MAP treatment, and 7.64%, 16.59%, and 23.50% higher than those of the UP treatment, respectively. Therefore, the combined application of acidic phosphate fertilizers (MAP and UP) can increase soil available P content and plant P absorption in liming soil and stimulate photosynthesis, enhancing soybean yield and PUE. This study will provide a technical reference for the P reduction and soybean yield enhancement in arid areas. Full article

This dataset presents field observations collected in the municipality of Goiatuba, Goiás State, Brazil, a consolidated and representative agricultural frontier of the Brazilian Cerrado biome. The region presents diverse land use dynamics, including annual cropping systems, irrigated fields with up to three harvests per year, and pasturelands. We conducted a field campaign from 3 to 7 November 2025, corresponding to the beginning of the 2025/2026 Brazilian crop season, when crops were at distinct early phenological stages. To ensure representativeness, we delineated 117 reference fields prior to the field campaign, and an additional 463 plots were surveyed during work. Geographic coordinates, crop types, and photographic records were obtained using the GPX Viewer application, a handheld GPS receiver, and the QField 3.7.9 mobile GIS application running on a tablet uploaded with Sentinel-2 true-color imagery and the municipal road network. Plot boundaries were subsequently digitized in QGIS Desktop 3.34.1 software, following a conservative mapping strategy to minimize edge effects and internal heterogeneity associated with trees and water catchment basins. In total, more than 26,000 hectares of agricultural fields were mapped, along with additional land use and land cover polygons representing water bodies, urban areas, and natural vegetation fragments. All reference fields were labeled based on in situ observations and linked to Sentinel-2 mosaics downloaded via the Google Earth Engine platform. This dataset is well-suited for training, testing, and validation of remote sensing classifiers, benchmarking studies, and agricultural mapping initiatives focused on the beginning of the agricultural season in the Brazilian Cerrado. Full article

Monitoring agricultural land in regions undergoing rapid change is essential for supporting management, policy development, and biodiversity conservation. Dam construction and associated irrigation systems drive land use change transitions from annual to permanent crops and intensify cultivation systems. Mapping crop types at the parcel level, particularly permanent crops, is therefore critical. The EU Crop Map 2018, the first attempt to map annual crops across the European Union using remote sensing and machine learning, aggregates permanent crops into the generic class “shrublands and woodlands”. This study refines the EU Crop Map classification by distinguishing permanent crop types using an automated machine learning model integrating Sentinel S1 and S2 imagery. The study area surrounds the Alqueva reservoir in southern Portugal, one of the Europe’s largest artificial lakes, where recent irrigation system expansion has driven rapid permanent crop adoption. The model achieved 91% overall accuracy, demonstrating strong performance in distinguishing permanent crops, forests, and other occupations. It effectively identified almond groves (F1 score = 0.90), and distinguished three major olive grove cultivation systems (F1-score ≥ 0.78), though performance was lower for vineyards (0.71) and other permanent crops (0.48). Comparison with the Portuguese official land use product COS 2018 showed strong overall spatial alignment, despite several inconsistencies, and lower F1 scores (0.60) in the direct comparison the new mapping produced. This study used a large reference dataset, enabling the assessment of the effect of training set size on classification accuracy. While overall accuracy remained above 83%, even with only 5% of the training data, underrepresented classes experienced significant performance degradation, highlighting the critical need to address class imbalance in agricultural land cover mapping. Full article

Plant tissues exhibit a layered architecture that makes spatial context decisive for interpreting transcriptional changes. This review explains why the location of gene expression is as important as its magnitude and synthesizes advances uniting single-cell/nucleus RNA-seq with spatial transcriptomics in plants. Surveyed topics include platform selection and material preparation; plant-specific sample processing and quality control; integration with epigenomic assays such as single-nucleus Assay for Transposase-Accessible Chromatin using sequencing (ATAC) and Multiome; and computational workflows for label transfer, deconvolution, spatial embedding, and neighborhood-aware cell–cell communication. Protoplast-based single-cell RNA sequencing (scRNA-seq) enables high-resolution profiling but introduces dissociation artifacts and cell-type biases, whereas ingle-nucleus RNA sequencing (snRNA-seq) improves the representation of recalcitrant lineages and reduces stress signatures while remaining compatible with multiomics profiling. Practical guidance is provided for mitigating ambient RNA, interpreting organellar and intronic metrics, identifying doublets, and harmonizing batches across chemistries and studies. Spatial platforms (Visium HD, Stereo-seq, bead arrays) and targeted imaging (Single-molecule fluorescence in situ hybridization (smFISH), Hairpin-chain-reaction FISH (HCR-FISH), Multiplexed Error-Robust Fluorescence In Situ Hybridization (MERFISH)) are contrasted with plant-specific adaptations and integration pipelines that anchor dissociated profiles in anatomical coordinates. Recent atlases in Arabidopsis, soybean, and maize illustrate how cell identities, chromatin accessibility, and spatial niches reveal developmental trajectories and stress responses jointly. A roadmap is outlined for moving from atlases to interventions by deriving gene regulatory networks, prioritizing cis-regulatory targets, and validating perturbations with spatial readouts in crops. Together, these principles support a transition from descriptive maps to mechanism-informed, low-pleiotropy engineering of agronomic traits. Full article

Accurately mapping crop distribution is important for environmental and food security applications. The success of machine learning algorithms (MLs) applied to mapping crops is partly dependent on the acquisition of sufficient training samples. However, since minor crops typically cover only few areas within agricultural landscapes, opportunities for collecting training data for those classes are often constrained. This problem is particularly acute in high-elevation regions, where fields tend to be small and heterogeneous in shape. This often leads to imbalanced training datasets, where the proportions of samples for each class differ greatly. To address this issue, a novel resampling algorithm, i.e., the adaptive synthetic and repeat oversampling technique (ASROT), was proposed by coupling two existed algorithms: adaptive synthetic sampling (ADASYN) and density-based spatial clustering of applications with noise (DBSCAN). Then, we explored the application of the proposed ASROT approach and compared it with six commonly used alternative algorithms, using 13 imbalanced datasets generated from GF-6 images of a high-elevation region. The imbalanced training datasets as well as balanced versions produced by ASROT and the comparison algorithms were used with two classifiers (i.e., random forest (RF) and a stacking classifier) to map crop types. The results showed a negative correlation between overall accuracy and the imbalance degree of datasets, illustrating the latter does affect the models in calibrating the crop classification. The balanced datasets produced higher accuracy for crop classification than the original imbalanced datasets for both the RF and stacking classifiers. The classification accuracy of almost all the crop classes and the overall classification accuracy (OA) increased. Most notably, the accuracy for minor crops (e.g., highland barley and broad beans) increased by approximately 30%. Overall, the proposed ASROT algorithm provides an effective method for balancing training datasets, simultaneously improving classification accuracy of both major and minor crops in high-elevation regions. Full article

Soil temperature (ST) is a key regulator of crop growth, microbial activity, and soil biogeochemical processes, making its accurate estimation critical for agricultural monitoring. Focusing on the Huang-Huai-Hai (HHH) Plain, a major grain-producing region of China, we developed a monthly ST prediction framework for two depths (0–5 cm and 5–15 cm) using Random Forest and recursive feature elimination with cross-validation. Based on ~3000 in situ records (2003–2020) and 19 geo-environmental covariates, we generated 1 km monthly cropland ST maps and examined their spatiotemporal dynamics. The models achieved consistently high accuracy (R² ≥ 0.80; RMSE ≤ 1.9 °C; MAE ≤ 1.1 °C; NSE ≥ 0.8, Bias ≤ ±0.3 °C). Feature selection revealed clear month-to-month shifts in predictor importance: environmental variables dominated overall but followed a U-shaped pattern (decreasing then increasing importance), soil properties became more influential in spring–summer, and topography gained importance in autumn–winter. Interannually, cropland ST declined during 2003–2012 (−0.60 °C/decade at 0–5 cm; −0.52 °C/decade at 5–15 cm) but increased more rapidly during 2012–2020 (1.04 and 0.84 °C/decade, respectively). Seasonally, the largest amplitudes occurred in spring–summer (±0.5 °C at 0–5 cm; ±0.4 °C at 5–15 cm), with there being moderate fluctuations in autumn (±0.1 °C) and negligible changes in winter. These temporal dynamics exhibited pronounced spatial heterogeneity shaped by latitude, elevation, and soil type. Collectively, this study produces high-resolution monthly maps and a transparent variable-selection framework for cropland ST, providing new insights into soil thermal regimes and supporting precision agriculture and sustainable land management in the HHH Plain. Full article

Accurate global crop type mapping is essential to ensure food security. However, large-scale crop-type mapping still poses challenges to commonly used classification strategies. Specifically, variation within crop types downgrades classification performance due to unbalanced samples with different levels of difficulty. Recent studies have focused on adaptive classification models based on sample difficulty to address challenges associated with complex crops grown under diverse conditions. However, these models still face challenges, as intra-class variability and imbalanced training samples lead to intra-class long tail distribution issues that affect performance. We propose the Difficulty-based Mixture of Experts Vision Transformer (DMoE-ViT) framework, which utilizes stratified sample partitioning, a multi-expert mechanism, and uncertainty quantification to address the long tail problem within a class and enhance classification accuracy. By assigning samples of varying difficulty to specialized expert networks, DMoE-ViT mitigates overfitting and enhances robustness, resulting in superior crop classification performance in complex agricultural environments. The DMoE-ViT framework outperforms baseline deep learning models, achieving an accuracy of 96.40%, a Recall of 0.964, an F1-score of 0.964, and a Kappa Coefficient of 0.960 in Study Area 1. Qualitative analysis of sample outputs and uncertainties, alongside quantitative evaluation of sample imbalance effects, demonstrates the framework’s robustness in complex agricultural environments. Full article

Soybean is rich in protein and oil and serves as the most important legume crop globally. Soybean mosaic virus (SMV) is a severe threat to soybean production worldwide. MutMap, a gene-mapping technology based on map-based cloning and whole-genome resequencing, is utilized to clone key regulatory genes for agronomic traits in plants. However, no relevant studies have reported the cloning of genes resistant to SMV. We used an M3 mutant population derived from ethyl methanesulfonate mutagenesis of Williams 82, and conducted field inoculation experiments involving the SMV-SC3 strain. After field validation, two lines with high resistance to SMV were finally identified. Using MutMap, we initially screened candidate genes for SMV resistance and found that the G-to-A transitions of one candidate resistance gene, Glyma.13G194900, were at base positions 122 and 166. These transitions resulted in the substitution of glycine with glutamic acid (GGA→GAA) and valine with aspartic acid (GTT→GAT), respectively. Transgenic functional validation in soybean showed that the mutant allele of Glyma.13G194900 (designated Glyma.13G194900^M) substantially enhanced resistance to SMV-SC3, in contrast to the wild-type allele, which did not enhance resistance. Our results demonstrate that MutMap can rapidly identify SMV resistance-related genes to provide a genetic resource that accelerates the breeding of new SMV-resistant soybean. Full article