Runoff Forecast Model Integrating Time Series Decomposition and Deep Learning for the Short Term: A Case Study in the Weihe River Basin, China
文献类型：期刊论文
| 作者 | Ma, Ruijia1,2,5; An, Qiang1,2,5; Liu, Liu1,2,5; Cheng, Yongming1,2,5; Liu, Xingcai3,4 |
| 刊名 | WATER
 |
| 出版日期 | 2025-09-14 |
| 卷号 | 17期号:18页码:2718 |
| 关键词 | runoff forecasting Convolutional Long Short-Term Memory Seasonal-Trend decomposition using Loess Variational Mode Decomposition segmented decomposition sampling multi-input neural network |
| DOI | 10.3390/w17182718 |
| 产权排序 | 4 |
| 文献子类 | Article |
| 英文摘要 | Accurate prediction of river runoff is significant for flood control, water resource allocation, and basin ecological management. Despite the promise of integrating signal decomposition with deep learning, current decomposition-based hybrid models face critical forward data contamination: decomposition algorithms improperly access future test data in full-series applications, artificially inflating prediction accuracy. In contrast, the stepwise decomposition method currently proposed leads to high computational costs. To address this limitation, we introduce a novel framework integrating segmented decomposition sampling with a multi-input neural network. Specifically, a hybrid forecasting model combining Seasonal-Trend decomposition using Loess (STL) and Convolutional Long Short-Term Memory (CNN-LSTM) networks was implemented for daily runoff estimation. Method reliability was evaluated using historical runoff data from Huaxian Station in China's Weihe River Basin, with comparative experiments conducted against established single and hybrid models. The results showed that the proposed framework can effectively avoid future information leakage and simultaneously improve prediction accuracy. For 1-3-day-ahead Nash-Sutcliffe efficiency (NSE) at Huaxian Station, the STL-CNN-LSTM model achieved values of 0.96, 0.83, and 0.80, respectively-representing improvements of 5.49%, 5.06%, and 12.68% over the VMD-CNN-LSTM model. This STL-based configuration outperformed the standalone LSTM counterpart by 23.08%, 9.21%, and 17.65% in NSE, respectively. Therefore, the proposed framework, which incorporates the segmented decomposition sampling method and a multi-input neural network, proves to be both practical and reliable. |
| URL标识 | 查看原文 |
| WOS关键词 | DISCRETE WAVELET TRANSFORM ; INCORRECT USAGE ; HYBRID MODELS ; PREDICTION ; INFLOW ; WATER |
| WOS研究方向 | Environmental Sciences & Ecology ; Water Resources |
| 语种 | 英语 |
| WOS记录号 | WOS:001579570400001 |
| 出版者 | MDPI |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/217463]  |
| 专题 | 陆地水循环及地表过程院重点实验室_外文论文 |
| 通讯作者 | Liu, Liu |
| 作者单位 | 1.China Agr Univ, State Key Lab Efficient Utilizat Agr Water Resourc, Beijing 100083, Peoples R China; 2.China Agr Univ, Ctr Agr Water Res China, Beijing 100083, Peoples R China; 3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Water Cycle & Related Land Surface Proc, Beijing 100101, Peoples R China; 5.China Agr Univ, Coll Water Resources & Civil Engn, Beijing 100083, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Ma, Ruijia,An, Qiang,Liu, Liu,et al. Runoff Forecast Model Integrating Time Series Decomposition and Deep Learning for the Short Term: A Case Study in the Weihe River Basin, China[J]. WATER,2025,17(18):2718. |
| APA | Ma, Ruijia,An, Qiang,Liu, Liu,Cheng, Yongming,&Liu, Xingcai.(2025).Runoff Forecast Model Integrating Time Series Decomposition and Deep Learning for the Short Term: A Case Study in the Weihe River Basin, China.WATER,17(18),2718. |
| MLA | Ma, Ruijia,et al."Runoff Forecast Model Integrating Time Series Decomposition and Deep Learning for the Short Term: A Case Study in the Weihe River Basin, China".WATER 17.18(2025):2718. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。