Structural Reorganization of Water Use Efficiency Drivers in the Hanjiang River Basin Under the South-to-North Water Diversion: Spatiotemporal Deep Learning and Pixel-Level Attribution
用ConvGRU与积分梯度量化南水北调后汉江流域WUE驱动因子的像素级重组。
← 主题
#深度学习
LIGHTWEIGHT FEATURE FUSED ATTENTION DRIVEN MULTI LEVEL HYBRID MOBILENET V2 FRAMEWORK FOR EARLY TOMATO LEAF DISEASE DETECTION
提出轻量注意力多级混合MobileNet-V2框架，融合手工纹理与深度学习特征实现番茄叶片病害早期检
A Comprehensive Review of Deep Learning and Computer Vision Techniques for Fruit Quality Assessment and Classification
系统综述深度学习与计算机视觉在水果品质评估与分级中的全流程方法。
Enhanced Convolutional Neural Network Architecture with Attention-Guided Feature Refinement for Robust Image Classification
提出注意力引导细化网络AGR-Net，在CIFAR-10上兼顾精度与参数效率。
A smart agriculture-oriented cross-attention multiscale CNN for sugarcane disease diagnosis
提出交叉注意力多尺度并行CNN，实现甘蔗叶病自动分类。
Proximal Remote Sensing of Oil Palm Basal Stem Rot Using Deep Learning Vision Algorithms and Ground-based Images
用手机拍摄油棕树干图像，结合深度学习检测与分类，实现基腐病严重度诊断。
Lightweight Hybrid CNN-Transformer Network for Robust Maize Leaf Disease Detection and Edge Deployment
构建轻量MobileNetV3-Small框架实现玉米叶片病害分类并评估边缘部署。
BGDNet: a boundary-guided deformable network for accurate farmland parcel segmentation in high-resolution remote sensing imagery
提出边界引导可变形网络BGDNet，实现高分辨率遥感耕地地块精准分割。
MSFANet: a multi-scale feature aggregation network for tobacco pest recognition
提出MSFANet多尺度特征聚合网络，实现复杂田间背景下烟草害虫的自动识别。
Detection of yam leaf diseases and pest damage under complex field conditions using LIMN-YOLO
提出轻量级LIMN-YOLO模型，在复杂田间条件下检测山药叶部病害与虫害。
Modeling runoff, sediment, and nutrient dynamics in the Ganjiang River Basin, China: A hierarchical SWAT-BiLSTM framework
提出SWAT-BiLSTM分层混合框架，高精度模拟赣江流域径流、泥沙与营养物动态。
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN·10月12日 · 周一75 分 论文农业AI与大模型农业人工智能与决策模型阅读 2
Deep Learning Approaches for Plant Disease Detection: A Review of Convolutional Neural Networks and Emerging Techniques
综述深度学习在植物病害检测中的应用，涵盖CNN、混合Transformer、注意力机制与生成式数据增
An Interpretable Deep Learning Framework for Spatial Prediction of Soil Salinity Using Multi-Source Remote Sensing and Environmental Data: A Case Study of Cangzhou, Hebei Province, China
构建融合多源遥感与环境变量的可解释深度学习框架，预测沧州土壤盐分空间分布。
Explainable deep learning framework for real-time insect pest detection in smart agriculture
提出可解释深度学习框架CPSA-RIPD-CSTGCN，实现智慧农业中害虫实时检测。
An empirical performance comparison of deep learning models for apple leaf disease recognition
用UNet++分割苹果病叶并融合多种CNN与ViT分类，实现98.85%识别准确率。
Hybrid CNN-LSTM Techniques for Plant Leaf Disease Detection and Farmer-Based Agricultural Practice Analysis in Western Tamil Nadu
结合CNN-LSTM混合模型检测植物叶片病害，并调查印度泰米尔纳德邦农户的农业实践与技术采纳情况。
A hybrid DeepGR4J and regionalization framework for lake water balance assessment in data-scarce regions: Application to Lake Tana, Ethiopia
提出DeepGR4J与区域化混合框架，评估数据稀缺的埃塞俄比亚塔纳湖水量平衡。
FUSING DEEP LEARNING AND REMOTE SENSING DATA TO ESTIMATE NON-OPTICALLY ACTIVE WATER QUALITY VARIABLES
融合深度学习与遥感及实地数据，估算湖泊非光学活性水质变量（溶解氧和pH）。
Zenodo (CERN European Organization for Nuclear Research)·10月4日 · 周日67 分 论文果树数字乡村与农业信息化2 个信源同时报道 阅读 1
Detection of Apple Plant Diseases Using Leaf Images through Convolutional Neural Network
提出ResNet+GA+CNN混合模型，用苹果叶片图像检测病害并计算病斑面积占比。
A Feature Engineering Framework for High-Precision Land Use and Land Cover Classification Using Remote Sensing Images
提出EODFE-HPLULC框架，结合YOLOv12、EfficientNet-B5和深度信念网络实