Articles | Volume 26, issue 16
https://doi.org/10.5194/hess-26-4469-2022
© 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-26-4469-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Forward and inverse modeling of water flow in unsaturated soils with discontinuous hydraulic conductivities using physics-informed neural networks with domain decomposition
Life and Environmental Science Department, University of California, Merced, CA, USA
Teamrat A. Ghezzehei
Life and Environmental Science Department, University of California, Merced, CA, USA
Viewed
Total article views: 3,647 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 25 Feb 2022)
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
2,518 | 1,054 | 75 | 3,647 | 291 | 57 | 53 |
- HTML: 2,518
- PDF: 1,054
- XML: 75
- Total: 3,647
- Supplement: 291
- BibTeX: 57
- EndNote: 53
Total article views: 2,309 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 30 Aug 2022)
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
1,619 | 645 | 45 | 2,309 | 137 | 45 | 41 |
- HTML: 1,619
- PDF: 645
- XML: 45
- Total: 2,309
- Supplement: 137
- BibTeX: 45
- EndNote: 41
Total article views: 1,338 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 25 Feb 2022)
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
899 | 409 | 30 | 1,338 | 154 | 12 | 12 |
- HTML: 899
- PDF: 409
- XML: 30
- Total: 1,338
- Supplement: 154
- BibTeX: 12
- EndNote: 12
Viewed (geographical distribution)
Total article views: 3,647 (including HTML, PDF, and XML)
Thereof 3,434 with geography defined
and 213 with unknown origin.
Total article views: 2,309 (including HTML, PDF, and XML)
Thereof 2,182 with geography defined
and 127 with unknown origin.
Total article views: 1,338 (including HTML, PDF, and XML)
Thereof 1,252 with geography defined
and 86 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
16 citations as recorded by crossref.
- Physics informed neural networks for an inverse problem in peridynamic models F. Difonzo et al. 10.1007/s00366-024-01957-5
- Physics-informed neural networks for modeling two-phase steady state flow with capillary heterogeneity at varying flow conditions A. Chakraborty et al. 10.1016/j.advwatres.2024.104639
- Interface PINNs (I-PINNs): A physics-informed neural networks framework for interface problems A. Sarma et al. 10.1016/j.cma.2024.117135
- Causal Prior-Embedded Physics-Informed Neural Networks and a Case Study on Metformin Transport in Porous Media Q. Kang et al. 10.1016/j.watres.2024.121985
- Modeling Water Flow and Solute Transport in Unsaturated Soils Using Physics‐Informed Neural Networks Trained With Geoelectrical Data P. Haruzi & Z. Moreno 10.1029/2023WR034538
- PINN enhanced extended multiscale finite element method for fast mechanical analysis of heterogeneous materials Z. Wu et al. 10.1007/s00707-024-03984-1
- Bayesian back analysis of unsaturated hydraulic parameters for rainfall-induced slope failure: A review H. Yang & L. Zhang 10.1016/j.earscirev.2024.104714
- A multifactorial study of mass movement in the hilly and gully Loess Plateau based on intensive field surveys and remote sensing techniques L. Yan et al. 10.1016/j.scitotenv.2024.171628
- Reconstructing the Unsaturated Flow Equation From Sparse and Noisy Data: Leveraging the Synergy of Group Sparsity and Physics‐Informed Deep Learning W. Song et al. 10.1029/2022WR034122
- A mixed pressure-velocity formulation to model flow in heterogeneous porous media with physics-informed neural networks F. Lehmann et al. 10.1016/j.advwatres.2023.104564
- Numerical modeling of one-dimensional variably saturated flow in a homogeneous and layered soil–water system via mixed form Richards equation with Picard iterative scheme S. Shah et al. 10.1007/s40808-022-01588-z
- A novel approach to estimate sand particle-size using convolutional neural network with acoustic sensing Y. Sung et al. 10.1016/j.catena.2023.107639
- High-Resolution Estimation of Soil Saturated Hydraulic Conductivity via Upscaling and Karhunen–Loève Expansion within DREAM(ZS) Y. Xia & N. Li 10.3390/app14114521
- Hybrid data-mechanism-driven model of the unsteady soil temperature field for long-buried crude oil pipelines with non-isothermal batch transportation W. Jiang et al. 10.1016/j.energy.2024.130354
- Application of improved physics-informed neural networks for nonlinear consolidation problems with continuous drainage boundary conditions P. Lan et al. 10.1007/s11440-023-01899-0
- Forward and inverse modeling of water flow in unsaturated soils with discontinuous hydraulic conductivities using physics-informed neural networks with domain decomposition T. Bandai & T. Ghezzehei 10.5194/hess-26-4469-2022
14 citations as recorded by crossref.
- Physics informed neural networks for an inverse problem in peridynamic models F. Difonzo et al. 10.1007/s00366-024-01957-5
- Physics-informed neural networks for modeling two-phase steady state flow with capillary heterogeneity at varying flow conditions A. Chakraborty et al. 10.1016/j.advwatres.2024.104639
- Interface PINNs (I-PINNs): A physics-informed neural networks framework for interface problems A. Sarma et al. 10.1016/j.cma.2024.117135
- Causal Prior-Embedded Physics-Informed Neural Networks and a Case Study on Metformin Transport in Porous Media Q. Kang et al. 10.1016/j.watres.2024.121985
- Modeling Water Flow and Solute Transport in Unsaturated Soils Using Physics‐Informed Neural Networks Trained With Geoelectrical Data P. Haruzi & Z. Moreno 10.1029/2023WR034538
- PINN enhanced extended multiscale finite element method for fast mechanical analysis of heterogeneous materials Z. Wu et al. 10.1007/s00707-024-03984-1
- Bayesian back analysis of unsaturated hydraulic parameters for rainfall-induced slope failure: A review H. Yang & L. Zhang 10.1016/j.earscirev.2024.104714
- A multifactorial study of mass movement in the hilly and gully Loess Plateau based on intensive field surveys and remote sensing techniques L. Yan et al. 10.1016/j.scitotenv.2024.171628
- Reconstructing the Unsaturated Flow Equation From Sparse and Noisy Data: Leveraging the Synergy of Group Sparsity and Physics‐Informed Deep Learning W. Song et al. 10.1029/2022WR034122
- A mixed pressure-velocity formulation to model flow in heterogeneous porous media with physics-informed neural networks F. Lehmann et al. 10.1016/j.advwatres.2023.104564
- Numerical modeling of one-dimensional variably saturated flow in a homogeneous and layered soil–water system via mixed form Richards equation with Picard iterative scheme S. Shah et al. 10.1007/s40808-022-01588-z
- A novel approach to estimate sand particle-size using convolutional neural network with acoustic sensing Y. Sung et al. 10.1016/j.catena.2023.107639
- High-Resolution Estimation of Soil Saturated Hydraulic Conductivity via Upscaling and Karhunen–Loève Expansion within DREAM(ZS) Y. Xia & N. Li 10.3390/app14114521
- Hybrid data-mechanism-driven model of the unsteady soil temperature field for long-buried crude oil pipelines with non-isothermal batch transportation W. Jiang et al. 10.1016/j.energy.2024.130354
2 citations as recorded by crossref.
- Application of improved physics-informed neural networks for nonlinear consolidation problems with continuous drainage boundary conditions P. Lan et al. 10.1007/s11440-023-01899-0
- Forward and inverse modeling of water flow in unsaturated soils with discontinuous hydraulic conductivities using physics-informed neural networks with domain decomposition T. Bandai & T. Ghezzehei 10.5194/hess-26-4469-2022
Latest update: 29 Jun 2024
Short summary
Scientists use a physics-based equation to simulate water dynamics that influence hydrological and ecological phenomena. We present hybrid physics-informed neural networks (PINNs) to leverage the growing availability of soil moisture data and advances in machine learning. We showed that PINNs perform comparably to traditional methods and enable the estimation of rainfall rates from soil moisture. However, PINNs are challenging to train and significantly slower than traditional methods.
Scientists use a physics-based equation to simulate water dynamics that influence hydrological...