Development of a Distributed Physics‐Informed Deep Learning Hydrological Model for Data‐Scarce Regions
Abstract Climate change has exacerbated water stress and water‐related disasters, necessitating more precise streamflow simulations. However, in the majority of global regions, a deficiency of streamflow data constitutes a significant constraint on modeling endeavors. Traditional distributed hydrolo...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-06-01
|
| Series: | Water Resources Research |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023WR036333 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850115855434645504 |
|---|---|
| author | Liangjin Zhong Huimin Lei Jingjing Yang |
| author_facet | Liangjin Zhong Huimin Lei Jingjing Yang |
| author_sort | Liangjin Zhong |
| collection | DOAJ |
| description | Abstract Climate change has exacerbated water stress and water‐related disasters, necessitating more precise streamflow simulations. However, in the majority of global regions, a deficiency of streamflow data constitutes a significant constraint on modeling endeavors. Traditional distributed hydrological models and regionalization approaches have shown suboptimal performance. While current deep learning (DL)‐related models trained on large data sets excel in spatial generalization, the direct applicability of these models in certain regions with unique hydrological processes can be challenging due to the limited representativeness within the training data set. Furthermore, transfer learning DL models pre‐trained on large data sets still necessitate local data for retraining, thereby constraining their applicability. To address these challenges, we present a physics‐informed DL model based on a distributed framework. It involves spatial discretization and the establishment of differentiable hydrological models for discrete sub‐basins, coupled with a differentiable Muskingum method for channel routing. By introducing upstream‐downstream relationships, model errors in sub‐basins propagate through the river network to the watershed outlet, enabling the optimization using limited downstream streamflow data, thereby achieving spatial simulation of ungauged internal sub‐basins. The model, when trained solely on the downstream‐most station, outperforms the distributed hydrological model in streamflow simulation at both the training station and upstream held‐out stations. Additionally, in comparison to transfer learning models, our model requires fewer gauge stations for training, but achieves higher precision in simulating streamflow on spatially held‐out stations, indicating better spatial generalization ability. Consequently, this model offers a novel approach to hydrological simulation in data‐scarce regions, especially those with poor hydrological representativeness. |
| format | Article |
| id | doaj-art-982a51f8695945a09b8adfcc67f5af8f |
| institution | OA Journals |
| issn | 0043-1397 1944-7973 |
| language | English |
| publishDate | 2024-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | Water Resources Research |
| spelling | doaj-art-982a51f8695945a09b8adfcc67f5af8f2025-08-20T02:36:28ZengWileyWater Resources Research0043-13971944-79732024-06-01606n/an/a10.1029/2023WR036333Development of a Distributed Physics‐Informed Deep Learning Hydrological Model for Data‐Scarce RegionsLiangjin Zhong0Huimin Lei1Jingjing Yang2State Key Laboratory of Hydroscience and Engineering Key Laboratory of Hydrosphere Sciences of the Ministry of Water Resources Department of Hydraulic Engineering Tsinghua University Beijing ChinaState Key Laboratory of Hydroscience and Engineering Key Laboratory of Hydrosphere Sciences of the Ministry of Water Resources Department of Hydraulic Engineering Tsinghua University Beijing ChinaState Key Laboratory of Hydroscience and Engineering Key Laboratory of Hydrosphere Sciences of the Ministry of Water Resources Department of Hydraulic Engineering Tsinghua University Beijing ChinaAbstract Climate change has exacerbated water stress and water‐related disasters, necessitating more precise streamflow simulations. However, in the majority of global regions, a deficiency of streamflow data constitutes a significant constraint on modeling endeavors. Traditional distributed hydrological models and regionalization approaches have shown suboptimal performance. While current deep learning (DL)‐related models trained on large data sets excel in spatial generalization, the direct applicability of these models in certain regions with unique hydrological processes can be challenging due to the limited representativeness within the training data set. Furthermore, transfer learning DL models pre‐trained on large data sets still necessitate local data for retraining, thereby constraining their applicability. To address these challenges, we present a physics‐informed DL model based on a distributed framework. It involves spatial discretization and the establishment of differentiable hydrological models for discrete sub‐basins, coupled with a differentiable Muskingum method for channel routing. By introducing upstream‐downstream relationships, model errors in sub‐basins propagate through the river network to the watershed outlet, enabling the optimization using limited downstream streamflow data, thereby achieving spatial simulation of ungauged internal sub‐basins. The model, when trained solely on the downstream‐most station, outperforms the distributed hydrological model in streamflow simulation at both the training station and upstream held‐out stations. Additionally, in comparison to transfer learning models, our model requires fewer gauge stations for training, but achieves higher precision in simulating streamflow on spatially held‐out stations, indicating better spatial generalization ability. Consequently, this model offers a novel approach to hydrological simulation in data‐scarce regions, especially those with poor hydrological representativeness.https://doi.org/10.1029/2023WR036333distributed physics‐informed deep learningphysics‐informed deep learningstreamflow simulationdata‐scarce regionsungauged basinstransfer learning |
| spellingShingle | Liangjin Zhong Huimin Lei Jingjing Yang Development of a Distributed Physics‐Informed Deep Learning Hydrological Model for Data‐Scarce Regions Water Resources Research distributed physics‐informed deep learning physics‐informed deep learning streamflow simulation data‐scarce regions ungauged basins transfer learning |
| title | Development of a Distributed Physics‐Informed Deep Learning Hydrological Model for Data‐Scarce Regions |
| title_full | Development of a Distributed Physics‐Informed Deep Learning Hydrological Model for Data‐Scarce Regions |
| title_fullStr | Development of a Distributed Physics‐Informed Deep Learning Hydrological Model for Data‐Scarce Regions |
| title_full_unstemmed | Development of a Distributed Physics‐Informed Deep Learning Hydrological Model for Data‐Scarce Regions |
| title_short | Development of a Distributed Physics‐Informed Deep Learning Hydrological Model for Data‐Scarce Regions |
| title_sort | development of a distributed physics informed deep learning hydrological model for data scarce regions |
| topic | distributed physics‐informed deep learning physics‐informed deep learning streamflow simulation data‐scarce regions ungauged basins transfer learning |
| url | https://doi.org/10.1029/2023WR036333 |
| work_keys_str_mv | AT liangjinzhong developmentofadistributedphysicsinformeddeeplearninghydrologicalmodelfordatascarceregions AT huiminlei developmentofadistributedphysicsinformeddeeplearninghydrologicalmodelfordatascarceregions AT jingjingyang developmentofadistributedphysicsinformeddeeplearninghydrologicalmodelfordatascarceregions |