【摘要】 准确及时地估测作物产量对保障我国粮食安全和促进农业可持续发展具有重要意义。本文以陕西省关中平原作为研究区域，选取与冬小麦长势密切相关的条件植被温度指数(VTCI)、叶面积指数(LAI)、光合有效辐射吸收比率(FPAR)作为遥感特征参数，结合长短期记忆网络(LSTM)在时序数据处理上的优势，以及注意力机制(AM)对关键信息提取的能力，构建了LSTM-AM深度学习模型，用于冬小麦单产估测。结果表明，LSTM-AM模型决定系数(R~2)为0.65,均方根误差(RMSE)为496.43 kg/hm~2,平均绝对百分比误差(MAPE)为7.31%,归一化均方根误差(NRMSE)为0.11,相较于LSTM模型(R~2=0.60,RMSE为527.81 kg/hm~2,MAPE为7.85%,NRMSE为0.15),LSTM-AM模型具有更高的模型估测精度，且对于LSTM模型存在的低产高估及高产低估现象均有所改善。为进一步提高模型可解释性，利用置换特征重要性方法(PFI)对模型估测结果进行了进一步的解释研究。结果表明，4月下旬和5月上旬的FPAR、3月下旬至5月上旬VTCI、4月下旬至5月下旬的LAI对冬小麦最终产量影响较大。因此，LSTM-AM模型不仅有着较高的估测精度，同时通过PFI方法提升了模型可解释性，可为后续冬小麦产量估测提供参考。更多还原

【Abstract】 Accurate and timely crop yield estimation is of great significance for ensuring food security and promoting sustainable agricultural development. Focusing on the Guanzhong Plain in Shaanxi Province, selecting the vegetation temperature condition index(VTCI), leaf area index(LAI), and fraction of photosynthetically active radiation(FPAR) as remotely sensed feature parameters closely related to winter wheat growth. By combining the advantages of long short-term memory network(LSTM) in processing time series data with the capability of the attention mechanism(AM) to extract key information, an LSTM-AM deep learning model for winter wheat yield estimation was constructed. The results indicated that the coefficient of determination(R~2) for the LSTM-AM model was 0.65, with a root mean squared error(RMSE) of 496.43 kg/hm~2 and a mean absolute percentage error(MAPE) of 7.31%, and a normalized root mean squared error(NRMSE) of 0.11. Compared with the LSTM model(R~2=0.60, RMSE is 527.81 kg/hm~2, MAPE is 7.85%, NRMSE is 0.15), the LSTM-AM model demonstrated higher estimation accuracy and mitigated the underestimation of high yields and overestimation of low yields observed in the LSTM model. To further enhance the model’s interpretability, the permutation feature importance(PFI) method for an in-depth explanation of the estimation results was utilized. The findings indicated that FPAR from late April to early May, VTCI from late March to early May, and LAI from late April to late May significantly influenced the final yield of winter wheat. Therefore, the LSTM-AM model not only exhibited high estimation accuracy but also enhanced interpretability through the PFI method, providing a valuable reference for subsequent winter wheat yield estimation.更多还原