Assessing the performance and interpretability of the CNN-LSTM-Attention model for daily streamflow forecasting in typical basins of the eastern Qinghai-Tibet Plateau
Abstract Hydrological forecasting is of great significance to regional water resources management and reservoir operation. Climate change has increased the complexity and difficulty of hydrological forecasting. In this study, a hybrid explainable streamflow forecasting model based on CNN-LSTM-Attent...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-84810-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559600243933184 |
|---|---|
| author | Chuchu Zhang Yuyan Zhou Fan Lu Jianwei Liu Jiayue Zhang Zeying Yin Mengyi Ji Baoqi Li |
| author_facet | Chuchu Zhang Yuyan Zhou Fan Lu Jianwei Liu Jiayue Zhang Zeying Yin Mengyi Ji Baoqi Li |
| author_sort | Chuchu Zhang |
| collection | DOAJ |
| description | Abstract Hydrological forecasting is of great significance to regional water resources management and reservoir operation. Climate change has increased the complexity and difficulty of hydrological forecasting. In this study, a hybrid explainable streamflow forecasting model based on CNN-LSTM-Attention was established for five typical river source regions in the eastern Qinghai-Tibet Plateau (EQTP). The model effectively simulates typical basins in the EQTP, achieving an NSE range of 0.79 to 0.92 and an R2 range of 0.81 to 0.93, which is better than LSTM. Incorporating base flow as an input significantly improves high-flow results in all basins, with mixed flow basins showing greater optimization than single flow basins. Higher base flow, increased daily minimum temperatures, lower relative humidity, and higher precipitation positively impact the model’s simulation and prediction capabilities. |
| format | Article |
| id | doaj-art-684bb31325ee485ca0555e7c7b55eaae |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-684bb31325ee485ca0555e7c7b55eaae2025-01-05T12:21:31ZengNature PortfolioScientific Reports2045-23222025-01-0115111310.1038/s41598-024-84810-5Assessing the performance and interpretability of the CNN-LSTM-Attention model for daily streamflow forecasting in typical basins of the eastern Qinghai-Tibet PlateauChuchu Zhang0Yuyan Zhou1Fan Lu2Jianwei Liu3Jiayue Zhang4Zeying Yin5Mengyi Ji6Baoqi Li7State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower ResearchState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower ResearchState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower ResearchState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower ResearchState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower ResearchState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower ResearchState Key Laboratory of Simulation and Regulation of Water Cycle in River Basin, China Institute of Water Resources and Hydropower ResearchSchool of Civil Engineering, Shijiazhuang Tiedao UniversityAbstract Hydrological forecasting is of great significance to regional water resources management and reservoir operation. Climate change has increased the complexity and difficulty of hydrological forecasting. In this study, a hybrid explainable streamflow forecasting model based on CNN-LSTM-Attention was established for five typical river source regions in the eastern Qinghai-Tibet Plateau (EQTP). The model effectively simulates typical basins in the EQTP, achieving an NSE range of 0.79 to 0.92 and an R2 range of 0.81 to 0.93, which is better than LSTM. Incorporating base flow as an input significantly improves high-flow results in all basins, with mixed flow basins showing greater optimization than single flow basins. Higher base flow, increased daily minimum temperatures, lower relative humidity, and higher precipitation positively impact the model’s simulation and prediction capabilities.https://doi.org/10.1038/s41598-024-84810-5Streamflow forecastingFlow regimeCNN-LSTM-AttentionInterpretabilityThe eastern Qinghai-Tibet Plateau |
| spellingShingle | Chuchu Zhang Yuyan Zhou Fan Lu Jianwei Liu Jiayue Zhang Zeying Yin Mengyi Ji Baoqi Li Assessing the performance and interpretability of the CNN-LSTM-Attention model for daily streamflow forecasting in typical basins of the eastern Qinghai-Tibet Plateau Scientific Reports Streamflow forecasting Flow regime CNN-LSTM-Attention Interpretability The eastern Qinghai-Tibet Plateau |
| title | Assessing the performance and interpretability of the CNN-LSTM-Attention model for daily streamflow forecasting in typical basins of the eastern Qinghai-Tibet Plateau |
| title_full | Assessing the performance and interpretability of the CNN-LSTM-Attention model for daily streamflow forecasting in typical basins of the eastern Qinghai-Tibet Plateau |
| title_fullStr | Assessing the performance and interpretability of the CNN-LSTM-Attention model for daily streamflow forecasting in typical basins of the eastern Qinghai-Tibet Plateau |
| title_full_unstemmed | Assessing the performance and interpretability of the CNN-LSTM-Attention model for daily streamflow forecasting in typical basins of the eastern Qinghai-Tibet Plateau |
| title_short | Assessing the performance and interpretability of the CNN-LSTM-Attention model for daily streamflow forecasting in typical basins of the eastern Qinghai-Tibet Plateau |
| title_sort | assessing the performance and interpretability of the cnn lstm attention model for daily streamflow forecasting in typical basins of the eastern qinghai tibet plateau |
| topic | Streamflow forecasting Flow regime CNN-LSTM-Attention Interpretability The eastern Qinghai-Tibet Plateau |
| url | https://doi.org/10.1038/s41598-024-84810-5 |
| work_keys_str_mv | AT chuchuzhang assessingtheperformanceandinterpretabilityofthecnnlstmattentionmodelfordailystreamflowforecastingintypicalbasinsoftheeasternqinghaitibetplateau AT yuyanzhou assessingtheperformanceandinterpretabilityofthecnnlstmattentionmodelfordailystreamflowforecastingintypicalbasinsoftheeasternqinghaitibetplateau AT fanlu assessingtheperformanceandinterpretabilityofthecnnlstmattentionmodelfordailystreamflowforecastingintypicalbasinsoftheeasternqinghaitibetplateau AT jianweiliu assessingtheperformanceandinterpretabilityofthecnnlstmattentionmodelfordailystreamflowforecastingintypicalbasinsoftheeasternqinghaitibetplateau AT jiayuezhang assessingtheperformanceandinterpretabilityofthecnnlstmattentionmodelfordailystreamflowforecastingintypicalbasinsoftheeasternqinghaitibetplateau AT zeyingyin assessingtheperformanceandinterpretabilityofthecnnlstmattentionmodelfordailystreamflowforecastingintypicalbasinsoftheeasternqinghaitibetplateau AT mengyiji assessingtheperformanceandinterpretabilityofthecnnlstmattentionmodelfordailystreamflowforecastingintypicalbasinsoftheeasternqinghaitibetplateau AT baoqili assessingtheperformanceandinterpretabilityofthecnnlstmattentionmodelfordailystreamflowforecastingintypicalbasinsoftheeasternqinghaitibetplateau |