Document Type
Article
Abstract
Richards' equation, widely used to model soil water flows, presents numerical challenges due tothe high nonlinearity of its constitutive relationships. The deep learning method with a physics‐informed neuralnetwork (PINN) provides a fresh perspective for solving this equation without prior knowledge of soil waterconstitutive relationship. However, existing PINN‐based methods for Richards' equation are still significantlylimited by the feasible soil types, and further developments are urgently needed to make the neural networkmodels practically applicable to various types of soils. In this paper, we introduce a deep learning method,“PINN‐AWL,” which simultaneously build the PINN model for prediction of soil water flows and establish theconstitutive relationships between soil matric potential, soil water content and unsaturated hydraulicconductivity. An adaptively weighted loss is specially designed for the training process of this model.Specifically, the loss function is adjusted with self‐adaptive weights at the training points in each iteration oftraining. This allows the proposed PINN‐AWL to automatically focus more on regions where the solution isdifficult to fit. The prediction accuracy and generalization ability of the PINN‐AWL are thoroughly tested on various soils ranging from silty to sandy types. We also conduct studies to investigate the optimal structure and hyper‐parameters used in the proposed method. The numerical results demonstrate that the proposed PINN‐AWL significantly outperforms both the standard PINN and the monotonic PINN, especially on soils exhibiting strong nonlinearity in constitutive relationships, as indicated by larger “n” values in the van Genuchten‐Mualemmodel.
Digital Object Identifier (DOI)
Publication Info
Published in Water Resources Research, Volume 61, Issue 9, 2025, pages e2024WR039108-.
APA Citation
Li, C., Zhu, Y., Zhang, X., Ju, L., Luo, Q., & Feng, H. (2025). A physics‐informed deep learning method with adaptively weighted loss for modeling soil water flows. Water Resources Research, 61(9), Article e2024WR039108.https://doi.org/10.1029%2F2024WR039108
Rights
© 2025. The Author(s).This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.