AgriPINN: A Process-Informed Neural Network for Interpretable and Scalable Crop Biomass Prediction under Water Stress
提出过程信息神经网络AgriPINN，嵌入作物生长方程，提升水分胁迫下生物量预测精度与可解释性。
小麦
小麦及冬春麦区相关生产与科研
71 篇内容清除全部筛选
Three-way debate – measurements, pedotransfer functions, and inverse modeling – input strategy for soil hydraulic parameters in wheat simulations
比较测量、传递函数和反演建模获取土壤水力参数对小麦模拟的影响。
Accurate prediction of wheat grain protein content via integration of genomic prediction and high-throughput phenotyping in breeding fields
结合基因组预测和高通量表型，提高小麦籽粒蛋白含量预测精度。
Full-season wheat phenotyping using UAV-based multi-source remote sensing: dynamic time-series modeling and high-throughput trait extraction
利用无人机多源遥感进行全季节小麦表型分析，通过动态时间序列建模提取高通量性状。
Hyperspectral Imaging for Disease Detection in Wheat Crops: A Comprehensive Survey
综述高光谱成像在小麦病害检测中的应用，涵盖方法、挑战与未来方向。
Unravelling the combined abiotic stress responses of wheat under heat and drought conditions
田间条件下研究小麦在热、旱及复合胁迫下的产量和生理响应，发现复合胁迫危害更大，并鉴定出耐性基因型DB
Estimation of the Comprehensive High Photosynthetic-Efficiency Phenotypic Index in Winter Wheat Based on UAV Multimodal Remote Sensing Data
基于无人机多模态遥感数据，构建综合高光效表型指数并精准估算，用于小麦育种材料筛选。
No-tillage straw mulching alters fallow rainfall use and improves long-term water balance and yield stability of winter wheat: A 38-year simulation on the Loess Plateau
No-tillage straw mulching alters fallow rainfall use and improves long-term water balance and yield stability of winter wheat: A 38-year simulation on the Loess Plateau。Agricultural Systems
Transfer learning and multi-branch intermediate fusion deep neural network for wheat nitrogen concentration monitoring using multi-scale multi-modal remote sensing information
提出迁移学习与多分支中间融合深度网络，利用多尺度多模态遥感监测小麦氮浓度。
基于UAV与地面高光谱的杜兰小麦氮肥分施策略评价
设置7组氮肥分施处理,对地面高光谱与UAV多光谱协同监测进行评估;N3分施方案在拔节期UAV-NDVI与籽粒产量相关性最强(r=0.717,p<0.01),实现产量最大化与叶养分动态同步。
Residual-corrected decision-level fusion model for collaborative irrigation-fertilization decision support in winter wheat
中国农业科学院农田灌溉研究所节水高效灌溉技术与装备团队融合冬小麦无人机多光谱遥感数据与田间水肥管理数据,研发出残差校正决策层融合模型(RC-DLF),为小麦关键生育期水肥协同高效利用提供智慧决策支撑。该模型依托田间定位试验采集小麦关键生育期无人机多光谱冠层信息,整合水肥管理指标构建多源数据集,创新构建RC-DLF,内嵌权重优化、二阶校准、残差校正模块有效消解单一模型预测偏差。田间试验结果显示,相较传统模型,小麦开花期、灌浆期产量预测决定系数R²分别提升至0.62、0.67,整体预测误差明显降低。