Articles | Volume 27, issue 12
https://doi.org/10.5194/hess-27-2357-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-27-2357-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
30 Jun 2023
Research article |
| 30 Jun 2023
| 30 Jun 2023
The suitability of differentiable, physics-informed machine learning hydrologic models for ungauged regions and climate change impact assessment
Dapeng Feng
Civil and Environmental Engineering, The Pennsylvania State
University, University Park, PA, USA
Hylke Beck
Physical Science and Engineering, King Abdullah University of
Science and Technology, Thuwal, Saudi Arabia
Kathryn Lawson
Civil and Environmental Engineering, The Pennsylvania State
University, University Park, PA, USA
Civil and Environmental Engineering, The Pennsylvania State
University, University Park, PA, USA
Viewed
Total article views: 6,159 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 08 Aug 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 4,304 | 1,763 | 92 | 6,159 | 64 | 76 |
- HTML: 4,304
- PDF: 1,763
- XML: 92
- Total: 6,159
- BibTeX: 64
- EndNote: 76
Total article views: 3,207 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 30 Jun 2023)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,374 | 782 | 51 | 3,207 | 48 | 57 |
- HTML: 2,374
- PDF: 782
- XML: 51
- Total: 3,207
- BibTeX: 48
- EndNote: 57
Total article views: 2,952 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 08 Aug 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,930 | 981 | 41 | 2,952 | 16 | 19 |
- HTML: 1,930
- PDF: 981
- XML: 41
- Total: 2,952
- BibTeX: 16
- EndNote: 19
Viewed (geographical distribution)
Total article views: 6,159 (including HTML, PDF, and XML)
Thereof 5,932 with geography defined
and 227 with unknown origin.
Total article views: 3,207 (including HTML, PDF, and XML)
Thereof 3,122 with geography defined
and 85 with unknown origin.
Total article views: 2,952 (including HTML, PDF, and XML)
Thereof 2,810 with geography defined
and 142 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
28 citations as recorded by crossref.
- Identifying Structural Priors in a Hybrid Differentiable Model for Stream Water Temperature Modeling F. Rahmani et al. 10.1029/2023WR034420
- Advancing Hydrology through Machine Learning: Insights, Challenges, and Future Directions Using the CAMELS, Caravan, GRDC, CHIRPS, PERSIANN, NLDAS, GLDAS, and GRACE Datasets F. Hasan et al. 10.3390/w16131904
- SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism Z. Cui et al. 10.1029/2023WR035932
- Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning T. Bindas et al. 10.1029/2023WR035337
- Deep learning insights into suspended sediment concentrations across the conterminous United States: Strengths and limitations Y. Song et al. 10.1016/j.jhydrol.2024.131573
- Improved National‐Scale Above‐Normal Flow Prediction for Gauged and Ungauged Basins Using a Spatio‐Temporal Hierarchical Model S. Fang et al. 10.1029/2023WR034557
- Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review B. Yifru et al. 10.3390/su16041376
- Probing the limit of hydrologic predictability with the Transformer network J. Liu et al. 10.1016/j.jhydrol.2024.131389
- On the need for physical constraints in deep learning rainfall–runoff projections under climate change: a sensitivity analysis to warming and shifts in potential evapotranspiration S. Wi & S. Steinschneider 10.5194/hess-28-479-2024
- Streamflow prediction in ungauged catchments through use of catchment classification and deep learning M. He et al. 10.1016/j.jhydrol.2024.131638
- Novel time-lag informed deep learning framework for enhanced streamflow prediction and flood early warning in large-scale catchments K. Ma et al. 10.1016/j.jhydrol.2024.130841
- Identification of Time-Varying Conceptual Hydrological Model Parameters with Differentiable Parameter Learning X. Lian et al. 10.3390/w16060896
- Revisit hydrological modeling in ungauged catchments comparing regionalization, satellite observations, and machine learning approaches R. Dasgupta et al. 10.1016/j.hydres.2023.11.001
- Exploring the feasibility of Support Vector Machine for short-term hydrological forecasting in South Tyrol: challenges and prospects D. Dalla Torre et al. 10.1007/s42452-024-05819-z
- Performance of LSTM over SWAT in Rainfall-Runoff Modeling in a Small, Forested Watershed: A Case Study of Cork Brook, RI S. Shrestha & S. Pradhanang 10.3390/w15234194
- A Surrogate Model for Shallow Water Equations Solvers with Deep Learning Y. Song et al. 10.1061/JHEND8.HYENG-13190
- Enhancing the performance of runoff prediction in data-scarce hydrological domains using advanced transfer learning S. Chen et al. 10.1016/j.resenv.2024.100177
- Technical Note: The divide and measure nonconformity – how metrics can mislead when we evaluate on different data partitions D. Klotz et al. 10.5194/hess-28-3665-2024
- Deep dive into hydrologic simulations at global scale: harnessing the power of deep learning and physics-informed differentiable models (δHBV-globe1.0-hydroDL) D. Feng et al. 10.5194/gmd-17-7181-2024
- When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling Y. Song et al. 10.5194/hess-28-3051-2024
- Advancing streamflow prediction in data-scarce regions through vegetation-constrained distributed hybrid ecohydrological models L. Zhong et al. 10.1016/j.jhydrol.2024.132165
- A framework on utilizing of publicly availability stream gauges datasets and deep learning in estimating monthly basin-scale runoff in ungauged regions M. Le et al. 10.1016/j.advwatres.2024.104694
- A differentiable, physics-informed ecosystem modeling and learning framework for large-scale inverse problems: demonstration with photosynthesis simulations D. Aboelyazeed et al. 10.5194/bg-20-2671-2023
- Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations J. Zwart et al. 10.3389/frwa.2023.1184992
- Differentiable modelling to unify machine learning and physical models for geosciences C. Shen et al. 10.1038/s43017-023-00450-9
- Improvement of streamflow simulation by combining physically hydrological model with deep learning methods in data-scarce glacial river basin C. Yang et al. 10.1016/j.jhydrol.2023.129990
- Deep learning for water quality W. Zhi et al. 10.1038/s44221-024-00202-z
- Hybrid forecasting: blending climate predictions with AI models L. Slater et al. 10.5194/hess-27-1865-2023
21 citations as recorded by crossref.
- Identifying Structural Priors in a Hybrid Differentiable Model for Stream Water Temperature Modeling F. Rahmani et al. 10.1029/2023WR034420
- Advancing Hydrology through Machine Learning: Insights, Challenges, and Future Directions Using the CAMELS, Caravan, GRDC, CHIRPS, PERSIANN, NLDAS, GLDAS, and GRACE Datasets F. Hasan et al. 10.3390/w16131904
- SA‐RelayGANs: A Novel Framework for the Characterization of Complex Hydrological Structures Based on GANs and Self‐Attention Mechanism Z. Cui et al. 10.1029/2023WR035932
- Improving River Routing Using a Differentiable Muskingum‐Cunge Model and Physics‐Informed Machine Learning T. Bindas et al. 10.1029/2023WR035337
- Deep learning insights into suspended sediment concentrations across the conterminous United States: Strengths and limitations Y. Song et al. 10.1016/j.jhydrol.2024.131573
- Improved National‐Scale Above‐Normal Flow Prediction for Gauged and Ungauged Basins Using a Spatio‐Temporal Hierarchical Model S. Fang et al. 10.1029/2023WR034557
- Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review B. Yifru et al. 10.3390/su16041376
- Probing the limit of hydrologic predictability with the Transformer network J. Liu et al. 10.1016/j.jhydrol.2024.131389
- On the need for physical constraints in deep learning rainfall–runoff projections under climate change: a sensitivity analysis to warming and shifts in potential evapotranspiration S. Wi & S. Steinschneider 10.5194/hess-28-479-2024
- Streamflow prediction in ungauged catchments through use of catchment classification and deep learning M. He et al. 10.1016/j.jhydrol.2024.131638
- Novel time-lag informed deep learning framework for enhanced streamflow prediction and flood early warning in large-scale catchments K. Ma et al. 10.1016/j.jhydrol.2024.130841
- Identification of Time-Varying Conceptual Hydrological Model Parameters with Differentiable Parameter Learning X. Lian et al. 10.3390/w16060896
- Revisit hydrological modeling in ungauged catchments comparing regionalization, satellite observations, and machine learning approaches R. Dasgupta et al. 10.1016/j.hydres.2023.11.001
- Exploring the feasibility of Support Vector Machine for short-term hydrological forecasting in South Tyrol: challenges and prospects D. Dalla Torre et al. 10.1007/s42452-024-05819-z
- Performance of LSTM over SWAT in Rainfall-Runoff Modeling in a Small, Forested Watershed: A Case Study of Cork Brook, RI S. Shrestha & S. Pradhanang 10.3390/w15234194
- A Surrogate Model for Shallow Water Equations Solvers with Deep Learning Y. Song et al. 10.1061/JHEND8.HYENG-13190
- Enhancing the performance of runoff prediction in data-scarce hydrological domains using advanced transfer learning S. Chen et al. 10.1016/j.resenv.2024.100177
- Technical Note: The divide and measure nonconformity – how metrics can mislead when we evaluate on different data partitions D. Klotz et al. 10.5194/hess-28-3665-2024
- Deep dive into hydrologic simulations at global scale: harnessing the power of deep learning and physics-informed differentiable models (δHBV-globe1.0-hydroDL) D. Feng et al. 10.5194/gmd-17-7181-2024
- When ancient numerical demons meet physics-informed machine learning: adjoint-based gradients for implicit differentiable modeling Y. Song et al. 10.5194/hess-28-3051-2024
- Advancing streamflow prediction in data-scarce regions through vegetation-constrained distributed hybrid ecohydrological models L. Zhong et al. 10.1016/j.jhydrol.2024.132165
7 citations as recorded by crossref.
- A framework on utilizing of publicly availability stream gauges datasets and deep learning in estimating monthly basin-scale runoff in ungauged regions M. Le et al. 10.1016/j.advwatres.2024.104694
- A differentiable, physics-informed ecosystem modeling and learning framework for large-scale inverse problems: demonstration with photosynthesis simulations D. Aboelyazeed et al. 10.5194/bg-20-2671-2023
- Evaluating deep learning architecture and data assimilation for improving water temperature forecasts at unmonitored locations J. Zwart et al. 10.3389/frwa.2023.1184992
- Differentiable modelling to unify machine learning and physical models for geosciences C. Shen et al. 10.1038/s43017-023-00450-9
- Improvement of streamflow simulation by combining physically hydrological model with deep learning methods in data-scarce glacial river basin C. Yang et al. 10.1016/j.jhydrol.2023.129990
- Deep learning for water quality W. Zhi et al. 10.1038/s44221-024-00202-z
- Hybrid forecasting: blending climate predictions with AI models L. Slater et al. 10.5194/hess-27-1865-2023
Latest update: 20 Nov 2024
Short summary
Powerful hybrid models (called δ or delta models) embrace the fundamental learning capability of AI and can also explain the physical processes. Here we test their performance when applied to regions not in the training data. δ models rivaled the accuracy of state-of-the-art AI models under the data-dense scenario and even surpassed them for the data-sparse one. They generalize well due to the physical structure included. δ models could be ideal candidates for global hydrologic assessment.
Powerful hybrid models (called δ or delta models) embrace the fundamental learning capability...
