Forward and inverse modeling of water flow in unsaturated soils with discontinuous hydraulic conductivities using physics-informed neural networks with domain decomposition
Open accessPublished version of a preprint
The DOI matches its Crossref record; 64 of the 67 references it cites were found in a registry or an index, and 3 are not checked yet.
Abstract
Modeling water flow in unsaturated soils is vital for describing various hydrological and ecological phenomena. Soil water dynamics is described by well-established physical laws (Richardson–Richards equation – RRE). Solving the RRE is difficult due to the inherent nonlinearity of the processes, and various numerical methods have been proposed to solve the issue. However, applying the methods to practical situations is very challenging because they require well-defined initial and boundary conditions. Recent advances in machine learning and the growing availability of soil moisture data provide new opportunities for addressing the lingering challenges. Specifically, physics-informed machine learning allows both the known physics and data-driven modeling to be taken advantage of. Here, we present a physics-informed neural network (PINN) method that approximates the solution to the RRE using neural networks while concurrently matching available soil moisture data. Although the ability of PINNs to solve partial differential equations, including the RRE, has been demonstrated previously, its potential applications and limitations are not fully known. This study conducted a comprehensive analysis of PINNs and carefully tested the accuracy of the solutions by comparing them with analytical solutions and accepted traditional numerical solutions. We demonstrated that the solutions by PINNs with adaptive activation functions are comparable with those by traditional methods. Furthermore, while a single neural network (NN) is adequate to represent a homogeneous soil, we showed that soil moisture dynamics in layered soils with discontinuous hydraulic conductivities are correctly simulated by PINNs with domain decomposition (using separate NNs for each unique layer). A key advantage of PINNs is the absence of the strict requirement for precisely prescribed initial and boundary conditions. In addition, unlike traditional numerical methods, PINNs provide an inverse solution without repeatedly solving the forward problem. We demonstrated the application of these advantages by successfully simulating infiltration and redistribution constrained by sparse soil moisture measurements. As a free by-product, we gain knowledge of the water flux over the entire flow domain, including the unspecified upper and bottom boundary conditions. Nevertheless, there remain challenges that require further development. Chiefly, PINNs are sensitive to the initialization of NNs and are significantly slower than traditional numerical methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“In this study, we used the Adam algorithm (Kingma and Ba, 2014).”
MethodSciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2020) · Nature Methods · doi:10.1038/s41592-019-0686-2 · Cited by 38,430 · cited 1×
“After the Adam algorithm, the loss function was further minimized through the L-BFGS-B optimizer (Byrd et al., 1995) from Scipy (Virtanen et al., 2020), which was terminated once the loss function converged with prescribed thresholds.”
MethodPyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
A Closed‐form Equation for Predicting the Hydraulic Conductivity of Unsaturated Soils
van Genuchten, M. T. (1980) · Soil Science Society of America Journal · doi:10.2136/sssaj1980.03615995004400050002x · Cited by 27,578 · cited 3×
“…solutions are based on the linearization of the RRE using the following relationships for WRCs and HCFs for ψ 0 (Gardner, 1958): where θ r is the residual water Note that the parameter α G can be interpreted using van-Genuchten parameters α V G and n V G (van Genuchten, 1980), as α G ≈ 1 .”
MethodRaissi, M., Perdikaris, P., & Karniadakis, G. E. (2019) · Journal of Computational Physics · doi:10.1016/j.jcp.2018.10.045 · Cited by 20,384 · cited 4×
“In the original PINN framework proposed by Raissi et al. (2019), all λ i were set to 1.”
MethodInfluentialApproximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2019) · Apollo - University of Cambridge Repository · doi:10.17863/cam.64134 · Cited by 10,460
Physics-informed machine learning
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021) · Nature Reviews Physics · doi:10.1038/s42254-021-00314-5 · Cited by 8,718 · cited 5×
“Furthermore, PINNs can store the solutions of PDEs efficiently with a smaller number of degrees of freedom, particularly for high dimensions (Karniadakis et al., 2021).”
BackgroundMethodInfluentialA new model for predicting the hydraulic conductivity of unsaturated porous media
Mualem, Y. (1976) · Water Resources Research · doi:10.1029/wr012i003p00513 · Cited by 8,300
CAPILLARY CONDUCTION OF LIQUIDS THROUGH POROUS MEDIUMS
Richards, L. A. (1931) · Physics · doi:10.1063/1.1745010 · Cited by 6,392 · cited 3×
“Equations (1) and (2) are combined to derive the Richardson–Richards equation (RRE) (Richardson, 1922; Richards, 1931):”
BackgroundMethod
Research works printed but not linked: 2
- Glorot, X. and Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the thirteenth international conference on artificial intelligence and statistics, 13–15 May 2010, Sardinia, Italy, 249–256, 2010.
- Li, Z., Kovachki, N., Azizzadenesheli, K., Liu, B., Bhattacharya, K., Stuart, A., and Anandkumar, A.: Fourier neural operator for parametric partial differential equations, in: International conference on learning and representations, 4 May 2021, Vienna, Austria, https://resolver.caltech.edu/CaltechAUTHORS:20201106-120140981 (last access: 30 August 2022), 2021.
Cited by
Zhao, C., Zhang, F., Lou, W., Wang, X., & Yang, J. (2024) · Physics of Fluids · doi:10.1063/5.0226562 · Cited by 197
Soil Science-Informed Machine Learning
Minasny, B., Bandai, T., Ghezzehei, T. A., Huang, Y., Ma, Y., McBratney, A. B., Ng, W., Norouzi, S., Padarian, J., Rudiyanto, N.-F., et al. (2024) · Geoderma · doi:10.1016/j.geoderma.2024.117094 · Cited by 178
Self-citationInterface PINNs (I-PINNs): A physics-informed neural networks framework for interface problems
Sarma, A. K., Roy, S., Annavarapu, C., Roy, P., & Jagannathan, S. (2024) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2024.117135 · Cited by 115
Physics-informed machine learning in geotechnical engineering: a direction paper
Yuan, B., Choo, C. S., Yeo, L. Y., Wang, Y., Yang, Z., Guan, Q., Suryasentana, S. K., Choo, J., Shen, H. R., Megía, M., et al. (2025) · Geomechanics and Geoengineering · doi:10.1080/17486025.2025.2502029 · Cited by 136
Inverse Physics-Informed Neural Networks for transport models in porous materials
Berardi, M., Difonzo, F. V., & Icardi, M. (2024) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2024.117628 · Cited by 87
Metadata
- Authors
- Bandai, T., & Ghezzehei, T. A.
- Affiliations
- University of California, Merced (US)
- Corresponding author
- Bandai, Toshiyuki
- Ghezzehei, Teamrat A.
- Venue
- Hydrology and Earth System Sciences
- Publisher
- Copernicus GmbH
- Published
- 2022-08-30
- Volume
- 26
- Issue
- 16
- Pages
- 4469-4495
- ISSN
- 1027-5606 (ISSN-L)
- 1607-7938
- OpenAlex
- W4293569036
- Cited by
- 111
- References
- 62
- Citations by year
- 2026: 30 · 2025: 40 · 2024: 28 · 2023: 10 · 2022: 3
- FWCI
- 7.63
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Hydrology and earth system sciences (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- University of Pennsylvania
- Topics
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks
- Physical Sciences › Engineering › Civil and Structural Engineering › Soil and Unsaturated Flow
- Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- Keywords
- unsaturated flow, physics-informed neural networks, domain decomposition, layered soil, inverse modeling, forward modeling, infiltration, soil water redistribution, adaptive activation functions
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Forward and inverse modeling of water flow in unsaturated soils with discontinuous hydraulic conductivities using physics-informed neural networks with domain decomposition. https://app.cochat.ai/papers/10.5194/hess-26-4469-2022
- The paper
- Bandai, T., & Ghezzehei, T. A. (2022). Forward and inverse modeling of water flow in unsaturated soils with discontinuous hydraulic conductivities using physics-informed neural networks with domain decomposition. Hydrology and Earth System Sciences. https://doi.org/10.5194/hess-26-4469-2022
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.