Improving the prediction of streamflow in large watersheds based on seasonal trend decomposition and vectorized deep learning models.
Saved in:
| Title: | Improving the prediction of streamflow in large watersheds based on seasonal trend decomposition and vectorized deep learning models. |
|---|---|
| Authors: | Kang, Ningchang1 (AUTHOR), Wang, Zhaocai1 (AUTHOR) zcwang1028@163.com, Zhang, Anbin1 (AUTHOR), Chen, Hang1 (AUTHOR) |
| Source: | Ecological Informatics. Dec2025, Vol. 90, pN.PAG-N.PAG. 1p. |
| Subject Terms: | Streamflow, Deep learning, Transformer models, Long short-term memory, Ecological resilience, Time series analysis, Flood warning systems, Artificial neural networks |
| Abstract: | Accurate streamflow prediction is essential for water resource management and ecological conservation. With climate change and human activities intensifying extreme weather events, the risks associated with floods have grown, threatening both socioeconomic robustness and ecological integrity. Conventional prediction methods, such as physical and statistical models, often struggle to capture the complex nonlinear and nonstationary characteristics of streamflow. To address this challenge, this study presents a vectorized hybrid STL-LSTM-GRU-Transformer model designed to enhance prediction accuracy and stability. The approach begins by applying seasonal-trend decomposition using loess (STL) to separate streamflow data into trend, seasonal, and residual components. These components are then modeled independently: long short-term memory (LSTM) and convolutional neural networks (CNN) handle trend and seasonal patterns, while gated recurrent units (GRU) and Transformer process residual fluctuations. Furthermore, the model incorporates the Runoff process vectorization (RPV) method alongside vectorization techniques to improve sensitivity to extreme events. Evaluated on 2010–2022 data from six Jialing River stations, the model achieves 0.9991 (NSE), outperforming 12 benchmarks. SHAP analysis identifies dew point temperature (26.7 % contribution) and solar radiation (15.7 %) as key drivers, while kernel density estimation provides reliable probabilistic forecasts (PICP = 0.90 at 95 % CI). Demonstrating robust performance in flood-drought transition prediction (NSE > 0.9983), this approach contributes valuable insights for advancing flood early warning systems and hydro-ecological security. [Display omitted] • Hybrid STL-LSTM-GRU-Transformer model effectively improves streamflow prediction. • Multi-component decomposition optimizes modeling of trend, seasonality, and residual patterns. • Key drivers identified through SHAP analysis reveal meteorological influences on hydrological processes. • Vectorized RPV method enhances detection of rapid hydrological changes for early warning systems. • Robust flood-drought transition prediction demonstrates model adaptability to extreme events. [ABSTRACT FROM AUTHOR] |
| Database: | Supplemental Index |
Full Text Finder 
Nájsť tento článok vo Web of Science Be the first to leave a comment!