基于ICEEMDAN分解的多维时间序列
干旱预测模型性能评估

韦余鑫; 李 巧; 卢春雷; 陶洪飞; 马合木江·艾合买提; 姜有为

引用本文:	韦余鑫,李巧,卢春雷,等.基于ICEEMDAN分解的多维时间序列干旱预测模型性能评估[J].灌溉排水学报,2025,43(3):94-103.
	WEI Yuxin,LI Qiao,LU Chunlei,et al.基于ICEEMDAN分解的多维时间序列干旱预测模型性能评估[J].灌溉排水学报,2025,43(3):94-103.

【打印本页】【下载PDF全文】【查看/发表评论】【EndNote】【RefMan】【BibTex】

←前一篇|后一篇→

过刊浏览高级检索

本文已被：浏览 1452次下载 1497次	码上扫一扫！
分享到：微信更多字体:加大+\|默认\|缩小-
基于ICEEMDAN分解的多维时间序列干旱预测模型性能评估
韦余鑫，李巧，卢春雷，陶洪飞，马合木江·艾合买提，姜有为
1.新疆农业大学水利与土木工程学院，乌鲁木齐 830052；2.新疆水利工程安全与水灾害防治重点实验室，乌鲁木齐 830052；3.昌吉市水利管理站（三屯河流域管理处），新疆昌吉 831100

摘要:

【目的】评估基于ICEEMDAN分解的多维时间序列干旱模型预测性能，为干旱预测提供新思路。【方法】以新疆三屯河灌区为研究区域，基于碾盘庄站1980—2023年逐月降水数据，计算1、3、6、9、12、24个月时间尺度的标准化降水指数（SPI），构建自回归差分移动平均模型（ARIMA）、门控循环单元网络（GRU）、长短期记忆网络（LSTM）、改进的完全自适应噪声集合经验模态分解ICEEMDAN-ARIMA、ICEEMDAN-GRU和ICEEMDAN-LSTM组合模型，利用6种预测模型对多时间尺度SPI进行预测，借助均方根误差（RMSE）、平均绝对误差（MAE）、决定系数（R2）对所有模型预测精度进行评价。【结果】6种模型的预测精度均随时间尺度的增加而逐步提高，在24个月时间尺度下达到最高；ICEEMDAN能有效平稳时间数据，提升模型预测精度；6种模型的预测性能排序为：ICEEMDAN-ARIMA＞ICEEMDAN-GRU＞ICEEMDAN-LSTM＞ARIMA＞GRU＞LSTM。【结论】基于ICEEMDAN算法的组合模型在干旱预测中表现出色，其中ICEEMDAN-ARIMA模型优于其他单一及组合模型，最有利于干旱预测。

关键词: ICEEMDAN；长短期记忆网络；差分自回归移动平均模型；门控循环单元网络；标准化降水指数

DOI：10.13522/j.cnki.ggps.2024262

分类号:

基金项目:

Incorporating the ICEEMDAN decomposition to improve the accuracy of models for drought prediction

WEI Yuxin, LI Qiao, LU Chunlei, TAO Hongfei, AIHEMAITI Mahemujiang, JIANG Youwei

1. College of Water Conservancy and Civil Engineering, Xinjiang Agricultural University, Urumqi 830052, China; 2. Xinjiang Key Laboratory of Water Conservancy Engineering Safety and Water Disaster Prevention, Urumqi 830052, China; 3. Changji Water Conservancy Management Station (Santunhe River Basin Management Office), Changji 831100, China

Abstract:

【Objective】Drought is one of the most common abiotic stresses affecting crop production worldwide. Accurate forecasting is essential for improving irrigation management and water use efficiency. This study evaluates a multi-dimensional time series model for drought prediction based on the ICEEMDAN decomposition, aiming to provide a new method for improving drought prediction accuracy.【Method】The Santun River Irrigation District in Xinjiang was chosen as a case study. Monthly precipitation data from the Nianpanzhuang Station (1980—2023) were used, and the standardized precipitation index (SPI) was calculated for time intervals of 1, 3, 6, 9, 12, and 24 months. Six prediction models were compared: the autoregressive integrated moving average (ARIMA) model, gated recurrent unit (GRU) network, long short-term memory (LSTM) network, and their combinations with the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), resulting in ICEEMDAN-ARIMA, ICEEMDAN-GRU, and ICEEMDAN-LSTM models. These models were used to predict the SPI series at multiple time scales. Model accuracy was evaluated using root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R2).【Result】The accuracy of all six models improved as the time interval increased, reaching the highest at the 24-month interval. ICEEMDAN effectively stabilized the time series data and improved model accuracy for drought prediction. The accuracy of the models was ranked as follows: ICEEMDAN-ARIMA＞ICEEMDAN-GRU＞ICEEMDAN-LSTM＞ARIMA＞GRU＞LSTM.【Conclusion】Incorporating ICEEMDAN enhances the accuracy of drought prediction. Among the six models compared, ICEEMDAN-ARIMA was the most accurate and can be used for drought prediction in the studied region.

Key words: ICEEMDAN; LSTM; ARIMA; GRU; SPI