Scholarlink

<p>Accurate medium-long-term streamflow forecasting is crucial for flood mitigation and water-resource management across the Yangtze River Basin. Single deep-learning approaches remain challenged by non-stationarity, intricate long-range dependencies, and extreme-event sparsity. We propose a framework that integrates empirical mode decomposition (EMD) to decompose daily discharge, temporal convolutional networks (TCN) to extract multi-scale features, and gated recurrent units (GRU) to generate multi-step forecasts, with final outputs obtained via linear recombination, namely EMD-TCN-GRU. When the forecast horizon is set at 3 days, the model—trained on 2013–2022 Wuhan observations—records an R² of 0.9951 and a MAPE of 2.87%. Extending to 7 days, the R² is 0.9925 and the MAPE is 3.22%. At 15 days, the R² remains at 0.9922 while the MAPE is 3.25%. Compared to a standard GRU, the MAE is reduced by 63%, 51%, and 58%, respectively, and performance decay over time is negligible. Systematic ablation studies corroborate that the decomposition-convolution-gating pipeline is the primary factor in the observed increase in accuracy. The elimination of EMD serves to amplify residual noise, while the removal of TCN results in the severing of long-range information pathways. Furthermore, the substitution of multi-step GRU forecasting with single-step GRU forecasting triggers rapid error accumulation. The framework provides a robust, transferable solution for real-time flood warning and medium-long-term water allocation in the Yangtze River and analogous complex networks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Improving medium-long-term streamflow forecasts by exploiting multi-scale Temporal patterns with deep learning

  • 期刊论文

  • 发表日期：

    2025年12月22日

查看全文
  • Tiantian Li,
  • Jiali Guo,
  • Jihua Chen,
  • Yingping Huang,
  • Jingcheng Han,
  • Biao Xiong

摘要

Accurate medium-long-term streamflow forecasting is crucial for flood mitigation and water-resource management across the Yangtze River Basin. Single deep-learning approaches remain challenged by non-stationarity, intricate long-range dependencies, and extreme-event sparsity. We propose a framework that integrates empirical mode decomposition (EMD) to decompose daily discharge, temporal convolutional networks (TCN) to extract multi-scale features, and gated recurrent units (GRU) to generate multi-step forecasts, with final outputs obtained via linear recombination, namely EMD-TCN-GRU. When the forecast horizon is set at 3 days, the model—trained on 2013–2022 Wuhan observations—records an R² of 0.9951 and a MAPE of 2.87%. Extending to 7 days, the R² is 0.9925 and the MAPE is 3.22%. At 15 days, the R² remains at 0.9922 while the MAPE is 3.25%. Compared to a standard GRU, the MAE is reduced by 63%, 51%, and 58%, respectively, and performance decay over time is negligible. Systematic ablation studies corroborate that the decomposition-convolution-gating pipeline is the primary factor in the observed increase in accuracy. The elimination of EMD serves to amplify residual noise, while the removal of TCN results in the severing of long-range information pathways. Furthermore, the substitution of multi-step GRU forecasting with single-step GRU forecasting triggers rapid error accumulation. The framework provides a robust, transferable solution for real-time flood warning and medium-long-term water allocation in the Yangtze River and analogous complex networks.