文献类型： 外文期刊

作者： Chen, Ying ¹ ; Wu, Huanping ² ; Xie, Nengfu ¹ ; Liang, Xiaohe ¹ ; Jiang, Lihua ¹ ; Qiu, Minghui ¹ ; Li, Yonglei ¹ ;

作者机构： 1.Chinese Acad Agr Sci, Agr Informat Inst, Zhongguancun South St, Beijing 100081, Peoples R China

2.China Meteorol Adm, Natl Climate Ctr, Zhongguancun South St, Beijing 100081, Peoples R China

3.Minist Agr & Rural Affairs, Key Lab Agr Blockchain Applicat, Zhongguancun South St, Beijing 100081, Peoples R China

关键词： Drought prediction; Deep learning; Temporal convolutional network; Feature aggregation

期刊名称：EARTH SCIENCE INFORMATICS （ 影响因子：3.0； 五年影响因子：3.1 ）

ISSN： 1865-0473

年卷期： 2025 年 18 卷 3 期

页码：

收录情况： SCI

摘要： In recent decades, shifts in the spatiotemporal patterns of precipitation and extreme temperatures have contributed to more frequent droughts. These changes impact not only agricultural production but also food security, ecological systems, and social stability. Advanced techniques such as machine learning and deep learning models outperform traditional models by improving meteorological drought prediction. Specifically, this study proposes a novel model named the multivariate feature aggregation-based temporal convolutional network for meteorological drought spatiotemporal prediction (STAT-LSTM). The method consists of three parts: a feature aggregation module, which aggregates multivariate features to extract initial features; a self-attention-temporal convolutional network (SA-TCN), which extracts time series features and uses the self-attention module's weighting mechanism to automatically capture global dependencies in the sequential data; and a long short-term memory network (LSTM), which captures long-term dependencies. The performance of the STAT-LSTM model was assessed and compared via performance indicators (i.e., MAE, RMSE, and R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>2$$\end{document}). The results indicated that STAT-LSTM provided the most accurate SPEI prediction (MAE = 0.474, RMSE = 0.63, and R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>2$$\end{document} = 0.613 for SPEI-3; MAE = 0.356, RMSE = 0.468, and R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>2$$\end{document} = 0.748 for SPEI-6; MAE = 0.284, RMSE = 0.437, and R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>2$$\end{document} = 0.813 for SPEI-9; and MAE = 0.182, RMSE = 0.267, and R2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$<^>2$$\end{document} = 0.934 for SPEI-12).