An interpretable wheat yield estimation model using an attention mechanism-based deep learning framework with multiple remotely sensed variables

作者：Mingqi Li, Pengxin Wang, Kevin Tansey, Yue Zhang, Fengwei Guo, Junming Liu, Hongmei Li · 发表于：International Journal of Applied Earth Observation and Geoinformation · 年份：2025 · DOI：10.1016/j.jag.2025.104579 · 被引用次数：7 · 研究领域：Smart Agriculture and AI、Remote Sensing in Agriculture、Food Supply Chain Traceability

• AM-CNN-LSTM captures key yield-affected variables during the growth of winter wheat. • FPAR is the most crucial variable in yield estimation, with LAI and VTCI following. • The estimation uncertainty decreased as time proceeded and stabilized around milk maturity. Accurate crop yield estimation enables informed decisions that support efficient and sustainable food production systems. Despite some success in crop yield estimation using deep learning models, they are often referred to as “black boxes” due to their lack of interpretability. Meanwhile, most current models are designed to provide yield estimations without assessing the uncertainty and verifying the contribution of components within the models. This work developed a novel deep learning approach to estimate winter wheat yield in the Guanzhong Plain, PR China by using three remotely sensed indices, vegetation temperature condition index (VTCI), leaf area index (LAI), and fraction of photosynthetically active radiation (FPAR) during main growth stages of winter wheat. The attention mechanism (AM) and an interpretable attribution method, backpropagation-based integrated gradients (IG), were incorporated into the deep learning approach to enhance interpretability. Additionally, to address uncertainty limitations the Monte Carlo (MC) dropout was applied to the deep learning approach to assess the uncertainty over time during data accumulation. The proposed approach (AM-CNN-LSTM) combined a one-dimensional convolutional...