Articles | Volume 26, issue 19
https://doi.org/10.5194/hess-26-5085-2022
© Author(s) 2022. 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-26-5085-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| Highlight paper
| 
11 Oct 2022
Research article | Highlight paper |
| 11 Oct 2022
| 11 Oct 2022
Improving hydrologic models for predictions and process understanding using neural ODEs
Department of Systems Analysis, Integrated Assessment and Modelling, Eawag, Dübendorf, Switzerland
Andreas Scheidegger
Department of Systems Analysis, Integrated Assessment and Modelling, Eawag, Dübendorf, Switzerland
Marco Baity-Jesi
Department of Systems Analysis, Integrated Assessment and Modelling, Eawag, Dübendorf, Switzerland
Carlo Albert
Department of Systems Analysis, Integrated Assessment and Modelling, Eawag, Dübendorf, Switzerland
Fabrizio Fenicia
Department of Systems Analysis, Integrated Assessment and Modelling, Eawag, Dübendorf, Switzerland
Viewed
Total article views: 5,369 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 10 Mar 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 3,783 | 1,525 | 61 | 5,369 | 66 | 56 |
- HTML: 3,783
- PDF: 1,525
- XML: 61
- Total: 5,369
- BibTeX: 66
- EndNote: 56
Total article views: 3,866 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 11 Oct 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,929 | 901 | 36 | 3,866 | 51 | 44 |
- HTML: 2,929
- PDF: 901
- XML: 36
- Total: 3,866
- BibTeX: 51
- EndNote: 44
Total article views: 1,503 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 10 Mar 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 854 | 624 | 25 | 1,503 | 15 | 12 |
- HTML: 854
- PDF: 624
- XML: 25
- Total: 1,503
- BibTeX: 15
- EndNote: 12
Viewed (geographical distribution)
Total article views: 5,369 (including HTML, PDF, and XML)
Thereof 5,074 with geography defined
and 295 with unknown origin.
Total article views: 3,866 (including HTML, PDF, and XML)
Thereof 3,672 with geography defined
and 194 with unknown origin.
Total article views: 1,503 (including HTML, PDF, and XML)
Thereof 1,402 with geography defined
and 101 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
17 citations as recorded by crossref.
- Convergence of mechanistic modeling and artificial intelligence in hydrologic science and engineering R. Muñoz-Carpena et al. 10.1371/journal.pwat.0000059
- Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review B. Yifru et al. 10.3390/su16041376
- 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
- Assessment of Time Series Models for Mean Discharge Modeling and Forecasting in a Sub-Basin of the Paranaíba River, Brazil G. Costa et al. 10.3390/hydrology10110208
- Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning R. Palmitessa et al. 10.1016/j.watres.2022.118972
- Using a long short-term memory (LSTM) neural network to boost river streamflow forecasts over the western United States K. Hunt et al. 10.5194/hess-26-5449-2022
- Enhancing process-based hydrological models with embedded neural networks: A hybrid approach B. Li et al. 10.1016/j.jhydrol.2023.130107
- A comparative evaluation of streamflow prediction using the SWAT and NNAR models in the Meenachil River Basin of Central Kerala, India M. Saranya & V. Vinish 10.2166/wst.2023.330
- CAMELS-CH: hydro-meteorological time series and landscape attributes for 331 catchments in hydrologic Switzerland M. Höge et al. 10.5194/essd-15-5755-2023
- Long-term streamflow forecasting in data-scarce regions: Insightful investigation for leveraging satellite-derived data, Informer architecture, and concurrent fine-tuning transfer learning F. Ghobadi et al. 10.1016/j.jhydrol.2024.130772
- Short-term runoff forecasting in an alpine catchment with a long short-term memory neural network C. Frank et al. 10.3389/frwa.2023.1126310
- DeepGR4J: A deep learning hybridization approach for conceptual rainfall-runoff modelling A. Kapoor et al. 10.1016/j.envsoft.2023.105831
- Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow V. Shankar et al. 10.1063/5.0122115
- Deep learning for water quality W. Zhi et al. 10.1038/s44221-024-00202-z
- Differentiable modelling to unify machine learning and physical models for geosciences C. Shen et al. 10.1038/s43017-023-00450-9
- A fast physically-guided emulator of MATSIRO land surface model R. Olson et al. 10.1016/j.jhydrol.2024.131093
- Long‐Lead Drought Forecasting Across the Continental United States Using Burg Entropy Spectral Analysis With a Multiresolution Approach J. Han & V. Singh 10.1029/2022WR034188
16 citations as recorded by crossref.
- Convergence of mechanistic modeling and artificial intelligence in hydrologic science and engineering R. Muñoz-Carpena et al. 10.1371/journal.pwat.0000059
- Enhancing Streamflow Prediction Physically Consistently Using Process-Based Modeling and Domain Knowledge: A Review B. Yifru et al. 10.3390/su16041376
- 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
- Assessment of Time Series Models for Mean Discharge Modeling and Forecasting in a Sub-Basin of the Paranaíba River, Brazil G. Costa et al. 10.3390/hydrology10110208
- Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning R. Palmitessa et al. 10.1016/j.watres.2022.118972
- Using a long short-term memory (LSTM) neural network to boost river streamflow forecasts over the western United States K. Hunt et al. 10.5194/hess-26-5449-2022
- Enhancing process-based hydrological models with embedded neural networks: A hybrid approach B. Li et al. 10.1016/j.jhydrol.2023.130107
- A comparative evaluation of streamflow prediction using the SWAT and NNAR models in the Meenachil River Basin of Central Kerala, India M. Saranya & V. Vinish 10.2166/wst.2023.330
- CAMELS-CH: hydro-meteorological time series and landscape attributes for 331 catchments in hydrologic Switzerland M. Höge et al. 10.5194/essd-15-5755-2023
- Long-term streamflow forecasting in data-scarce regions: Insightful investigation for leveraging satellite-derived data, Informer architecture, and concurrent fine-tuning transfer learning F. Ghobadi et al. 10.1016/j.jhydrol.2024.130772
- Short-term runoff forecasting in an alpine catchment with a long short-term memory neural network C. Frank et al. 10.3389/frwa.2023.1126310
- DeepGR4J: A deep learning hybridization approach for conceptual rainfall-runoff modelling A. Kapoor et al. 10.1016/j.envsoft.2023.105831
- Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow V. Shankar et al. 10.1063/5.0122115
- Deep learning for water quality W. Zhi et al. 10.1038/s44221-024-00202-z
- Differentiable modelling to unify machine learning and physical models for geosciences C. Shen et al. 10.1038/s43017-023-00450-9
- A fast physically-guided emulator of MATSIRO land surface model R. Olson et al. 10.1016/j.jhydrol.2024.131093
Latest update: 26 Apr 2024
Executive editor
This is a paper demonstrating the added value of hybrid modeling approaches for modeling hydrological features (flow and internal states). The paper is well written and will be sent out for a detailed scientific review. The combination of ANN with ODE-based hydrological models is a good way forward to construct hybrid modeling approaches. It is a significant step forward compared to the current state of the art.
This is a paper demonstrating the added value of hybrid modeling approaches for modeling...
Short summary
Neural ODEs fuse physics-based models with deep learning: neural networks substitute terms in differential equations that represent the mechanistic structure of the system. The approach combines the flexibility of machine learning with physical constraints for inter- and extrapolation. We demonstrate that neural ODE models achieve state-of-the-art predictive performance while keeping full interpretability of model states and processes in hydrologic modelling over multiple catchments.
Neural ODEs fuse physics-based models with deep learning: neural networks substitute terms in...
