RAVEN: a foundation model-based approach for predicting avian influenza outbreak risk with multi-source geospatial data
December 2026
Avian Influenza Viruses (AIV) pose ongoing risks to the poultry industry, wildlife, and public health, with highly pathogenic avian influenza (HPAI) outbreaks causing substantial economic losses and...
An explainable deep learning approach based on a feature attention mechanism for maintaining SSC model performance in apples across interannual variability
Available online 3 November 2026
Model maintenance is crucial for mitigating performance degradation caused by variations in measurement conditions or samples. This study proposed a feature attention mechanism-based deep network updating...
A multi-source artificial intelligence framework for understanding climate effects on quality of agricultural products and supporting sustainable food systems
Available online 3 November 2026
Quality of agricultural products (QAP) underpins global food systems, economic value, and public health. Climate change is altering QAP with significant implications for global food security. Understanding...
A deep learning-based lightweight algorithm for multi-dairy cow daily behavior recognition and tracking
Available online 3 November 2026
The dairy farming industry is accelerating towards a new era of precise farming characterized by informatization and intelligence. However, current deep learning-based technologies for dairy cow behavior...
SPGrowing: an unsupervised individual plant segmentation pipeline from UAV-derived point clouds for high-throughput in-field maize phenotyping
Available online 2 November 2026
In-field plant phenotyping is essential for understanding gene–environment interactions and supporting crop breeding. While unmanned aerial vehicle (UAV)-based photogrammetry enables high-throughput...
Bi-temporal semantic change detection of rice disease and lodging based on difference token transformers and cross-branch distillation
Available online 2 November 2026
Semantic Change Detection (SCD) in high-resolution remote sensing imagery is essential for precision agriculture, particularly for timely monitoring of crop stresses. Recent studies have demonstrated...
Evaluating deep and machine learning models for irrigation prescription: Insights from aggregated and non-aggregated data
Available online 31 October 2026
Effective irrigation scheduling in corn is crucial for sustainable water management and crop productivity. This study proposes an early forecast of irrigation depths using artificial intelligence-based...
An agronomic-knowledge guided deep learning approach for plot-scale seed maize yield estimation using sentinel-2 satellite images
Available online 31 October 2026
Accurate yield estimation of seed maize is essential for ensuring agricultural productivity and food security. Seed maize yield is highly sensitive to the flowering synchrony between male and female...
A multi-indicator scoring-based method for optimal sensor insertion point decision of field soil sensing robot
Available online 30 October 2026
Soil information sensing is the foundation of precision agricultural management. Achieving automated, unmanned, and efficient acquisition of soil information is a critical step toward advancing agricultural...
A lightweight perception and decision framework for single-camera three-lane online apple defect sorting
Available online 21 October 2026
This study presents a lightweight visual perception and decision-making method for online apple defect sorting under a “single-camera, three-lane” imaging scenario. Challenges of detecting apple surface...
A meta-learning with adversarial domain adaptation method for few-shot cross-region maize height and yield joint prediction
Available online 17 October 2026
High accuracy phenotypic prediction driven by genotype (G), environment (E) and their interactions is the foundation for precision crop breeding. However, under cross-region few-shot scenarios with...
AI-IoT architectures for dairy welfare assessment: multimodal monitoring, deployment constraints, and the emerging role of digital twins
Available online 15 October 2026
The intensification of dairy production has increased the need for continuous, transparent, and scientifically grounded animal welfare assessment. Artificial intelligence (AI) and the Internet of Things...
End-effector picking-pose estimation for tomato harvesting: a fusion approach combining instance segmentation and optimised point-cloud fitting
Available online 15 October 2026
Owing to dense fruit distribution and asynchronous ripening, large-fruited tomatoes are typically harvested on a single-fruit basis; however, in dense clusters, pedicels are frequently occluded and...
Real-time, robust, and highly accurate robotic grasp detection of fruits with variable sizes and shapes
Available online 15 October 2026
Grasping objects is a fundamental yet important capability of robots, and many tasks such as sorting and picking rely on this skill. The prerequisite for stable grasping is the ability to correctly...
CropINSs: A multi-objective irrigation and nitrogen scheduling optimization framework for silage maize based on coupling remote sensing and crop models
Available online 15 October 2026
Developing efficient irrigation and nitrogen schedules (INSs) at regional scales remains challenging due to spatial heterogeneity in climate, soil conditions, and crop growth dynamics, which limits...
Self-supervised learning for crop yield prediction across diversified cropping systems
Available online 14 October 2026
Supervised learning models have shown promise for crop classification and yield prediction using RGB drone imagery. They require large, labeled datasets for training, but this remains challenging in...
Integrating large multi-modal models for automated powdery mildew phenotyping in grapevines
Available online 7 October 2026
Powdery mildew is a major fungal disease of grapevines, yet its field quantification remains constrained by subjective visual assessments, inconsistent scoring protocols, and the high cost of annotated...
Deep learning-based multi-view perception and adaptive grasp pose correction for cooperative dual-arm fruit harvesting under occlusion
Available online 1 October 2026
This study presents a failure-recovery cooperative harvesting pipeline for a dual-arm agricultural robot, where each arm harvests independently and switches to cooperative manipulation only when a single-view...
Research and trials on multi-pose picking of Sichuan pepper based on multi-task perception
Available online 1 October 2026
Compared to other fruits, Sichuan pepper is difficult to pick mechanically due to its long, sprawling branches, irregular growth pattern, prickly bark, and small fruit size. As a result, picking is...
UGV based multi-RGBD SLAM framework for high-throughput in-situ 3D phenotyping of field maize
Available online 1 October 2026
Accurate 3D reconstruction of maize populations under real-world field conditions is a prerequisite for individual-level trait in-situ extraction. Conventional visual mapping techniques frequently encounter...
Pixel-level high-throughput estimation of crop photosynthetic phenotyping parameters using a multi-task deep learning framework
Available online 1 October 2026
Hyperspectral remote sensing holds promise for estimating crop physiological and biochemical traits, yet conventional approaches are often constrained by small sample sizes, limited accuracy in multi-trait...
GLE-YOLOv11n: A lightweight network for real-time recognition of sheep behaviours in edge computing environments
Available online 1 October 2026
Real-time monitoring of sheep behaviour in large-scale sheep farms is crucial for precision livestock farming and can provide useful information for group-level welfare-related monitoring. Traditional...
Defect-aware dual-stream RGB-D perception for tomato pedicel cutting-point detection and 6D pose estimation in a robotic harvesting system
September 2026
Accurate 3D localization and pose estimation of tomato pedicel shearing points are prerequisites for stable, damage-free robotic harvesting in cluttered greenhouses. However, many existing pipelines...
Visual–tactile fusion for real-time weed detection in maize: Lightweight precision weed detection network with tactile-triggered keyframes
September 2026
Weeds severely threaten maize growth and yield, and accurate weed detection is essential but remains challenging for precision maize protection. Although vision-based methods for weed detection have...
Target-oriented spectral disentanglement improves cross-year robustness of UAV hyperspectral inversion of winter wheat agronomic parameters
September 2026
The hyperspectral reflectance of winter wheat canopy is jointly influenced by multiple agronomic parameters, including canopy structure, pigment status, and biomass accumulation. Shared spectral responses...