Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged Basins
Abstract Streamflow prediction in ungauged basins (PUB) is challenging, and Long Short‐Term Memory (LSTM) is widely used to for such predictions, owing to its excellent migration performance. Traditional LSTM forced by meteorological data and catchment attribute data barely highlight the optimum dat...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-07-01
|
| Series: | Water Resources Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2022WR034352 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839639730921144320 |
|---|---|
| author | Senlin Tang Fubao Sun Wenbin Liu Hong Wang Yao Feng Ziwei Li |
| author_facet | Senlin Tang Fubao Sun Wenbin Liu Hong Wang Yao Feng Ziwei Li |
| author_sort | Senlin Tang |
| collection | DOAJ |
| description | Abstract Streamflow prediction in ungauged basins (PUB) is challenging, and Long Short‐Term Memory (LSTM) is widely used to for such predictions, owing to its excellent migration performance. Traditional LSTM forced by meteorological data and catchment attribute data barely highlight the optimum data integration strategy for LSTM and its migration from data‐rich basins to ungauged ones. In this study, we experimented with 1,897 global catchments and found that LSTM‐corrected Global Hydrological Models (GHMs) outperformed uncorrected GHMs, improving the median Nash‐Sutcliff efficiency (NSE) from 0.03 to 0.66. Notably, there was a large gap between traditional LSTM modeling in ungauged basins and autoregressive modeling in data‐rich basins, and GHM‐forced LSTM were an effective way to close this gap in ungauged basins. The spatial heterogeneity of the performance of GHM‐forced LSTM was mainly influenced by three metrics (dryness, the leaf area index and latitude), which described the hydrological similarity among catchments. Weaker hydrological similarity among continental catchments results in larger variability in GHM‐forced LSTM, with the best performance in Siberia (NSE, 0.54) and the worst in North America (NSE, 0.10). However, the migration performance of GHM‐forced LSTM was significantly improved (NSE, 0.63) in ungauged basins when hydrological similarity was considered. This study stressed the advantages of GHM‐forced LSTM and due significance should be attached to hydrological similarities among catchments to improve hydrological prediction in ungauged catchments. |
| format | Article |
| id | doaj-art-a76e2b342e5b41d6a176441faa8e4db5 |
| institution | Matheson Library |
| issn | 0043-1397 1944-7973 |
| language | English |
| publishDate | 2023-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Water Resources Research |
| spelling | doaj-art-a76e2b342e5b41d6a176441faa8e4db52025-07-04T06:40:25ZengWileyWater Resources Research0043-13971944-79732023-07-01597n/an/a10.1029/2022WR034352Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged BasinsSenlin Tang0Fubao Sun1Wenbin Liu2Hong Wang3Yao Feng4Ziwei Li5Key Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing ChinaKey Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing ChinaKey Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing ChinaKey Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing ChinaKey Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing ChinaKey Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing ChinaAbstract Streamflow prediction in ungauged basins (PUB) is challenging, and Long Short‐Term Memory (LSTM) is widely used to for such predictions, owing to its excellent migration performance. Traditional LSTM forced by meteorological data and catchment attribute data barely highlight the optimum data integration strategy for LSTM and its migration from data‐rich basins to ungauged ones. In this study, we experimented with 1,897 global catchments and found that LSTM‐corrected Global Hydrological Models (GHMs) outperformed uncorrected GHMs, improving the median Nash‐Sutcliff efficiency (NSE) from 0.03 to 0.66. Notably, there was a large gap between traditional LSTM modeling in ungauged basins and autoregressive modeling in data‐rich basins, and GHM‐forced LSTM were an effective way to close this gap in ungauged basins. The spatial heterogeneity of the performance of GHM‐forced LSTM was mainly influenced by three metrics (dryness, the leaf area index and latitude), which described the hydrological similarity among catchments. Weaker hydrological similarity among continental catchments results in larger variability in GHM‐forced LSTM, with the best performance in Siberia (NSE, 0.54) and the worst in North America (NSE, 0.10). However, the migration performance of GHM‐forced LSTM was significantly improved (NSE, 0.63) in ungauged basins when hydrological similarity was considered. This study stressed the advantages of GHM‐forced LSTM and due significance should be attached to hydrological similarities among catchments to improve hydrological prediction in ungauged catchments.https://doi.org/10.1029/2022WR034352long short‐term memoryglobal hydrological modelshydrological similaritiesstreamflowungauged basins |
| spellingShingle | Senlin Tang Fubao Sun Wenbin Liu Hong Wang Yao Feng Ziwei Li Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged Basins Water Resources Research long short‐term memory global hydrological models hydrological similarities streamflow ungauged basins |
| title | Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged Basins |
| title_full | Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged Basins |
| title_fullStr | Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged Basins |
| title_full_unstemmed | Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged Basins |
| title_short | Optimal Postprocessing Strategies With LSTM for Global Streamflow Prediction in Ungauged Basins |
| title_sort | optimal postprocessing strategies with lstm for global streamflow prediction in ungauged basins |
| topic | long short‐term memory global hydrological models hydrological similarities streamflow ungauged basins |
| url | https://doi.org/10.1029/2022WR034352 |
| work_keys_str_mv | AT senlintang optimalpostprocessingstrategieswithlstmforglobalstreamflowpredictioninungaugedbasins AT fubaosun optimalpostprocessingstrategieswithlstmforglobalstreamflowpredictioninungaugedbasins AT wenbinliu optimalpostprocessingstrategieswithlstmforglobalstreamflowpredictioninungaugedbasins AT hongwang optimalpostprocessingstrategieswithlstmforglobalstreamflowpredictioninungaugedbasins AT yaofeng optimalpostprocessingstrategieswithlstmforglobalstreamflowpredictioninungaugedbasins AT ziweili optimalpostprocessingstrategieswithlstmforglobalstreamflowpredictioninungaugedbasins |