Multiphysics‐Informed Neural Networks for Coupled Soil Hydrothermal Modeling

Abstract Soil water and heat transport are two physical processes that are described by the Richardson–Richards equation and heat transport equation, respectively. Soil water and heat motion directly control transport or indirectly influence parameters. The physics‐informed neural network (PINN) is...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanling Wang, Liangsheng Shi, Xiaolong Hu, Wenxiang Song, Lijun Wang
Format: Article
Language:English
Published: Wiley 2023-01-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2022WR031960
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849424742257262592
author Yanling Wang
Liangsheng Shi
Xiaolong Hu
Wenxiang Song
Lijun Wang
author_facet Yanling Wang
Liangsheng Shi
Xiaolong Hu
Wenxiang Song
Lijun Wang
author_sort Yanling Wang
collection DOAJ
description Abstract Soil water and heat transport are two physical processes that are described by the Richardson–Richards equation and heat transport equation, respectively. Soil water and heat motion directly control transport or indirectly influence parameters. The physics‐informed neural network (PINN) is a new method that combines deep learning and physical laws that approximates and learns physical dynamics better than traditional data‐driven deep learning methods. In this study, we propose multiphysics‐informed neural networks for soil water‐heat systems, in which the soil moisture and temperature information complement each other well. With our framework, existing soil moisture neural networks are improved to reduce their dependency on the soil moisture measurement density. Furthermore, soil moisture data are employed to promote soil temperature dynamic learning and soil thermal conductivity estimation. Moreover, soil temperature data assist in recovering the nonlinearity of the soil hydraulic conductivity through hydrothermal coupling constraints, allowing better estimations of the soil water flux density. The gradient‐based annealing method is applied to adapt the loss function, which satisfactorily balances the water‐heat transport governing equation constraints on the neural networks. The robustness and generalizability of our framework are examined under diverse scenarios. This work demonstrates the mutual compensation of multisource data in coupled physical processes in a deep learning framework and highlights the significance of appropriate multiphysical constraints designed for nonlinear parameter recovery in PINNs.
format Article
id doaj-art-472d1d1884b54d6fa958e57b0cc3c3f3
institution Kabale University
issn 0043-1397
1944-7973
language English
publishDate 2023-01-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-472d1d1884b54d6fa958e57b0cc3c3f32025-08-20T03:30:02ZengWileyWater Resources Research0043-13971944-79732023-01-01591n/an/a10.1029/2022WR031960Multiphysics‐Informed Neural Networks for Coupled Soil Hydrothermal ModelingYanling Wang0Liangsheng Shi1Xiaolong Hu2Wenxiang Song3Lijun Wang4State Key Laboratory of Water Resources and Hydropower Engineering Sciences Wuhan University Wuhan ChinaState Key Laboratory of Water Resources and Hydropower Engineering Sciences Wuhan University Wuhan ChinaState Key Laboratory of Water Resources and Hydropower Engineering Sciences Wuhan University Wuhan ChinaState Key Laboratory of Water Resources and Hydropower Engineering Sciences Wuhan University Wuhan ChinaState Key Laboratory of Water Resources and Hydropower Engineering Sciences Wuhan University Wuhan ChinaAbstract Soil water and heat transport are two physical processes that are described by the Richardson–Richards equation and heat transport equation, respectively. Soil water and heat motion directly control transport or indirectly influence parameters. The physics‐informed neural network (PINN) is a new method that combines deep learning and physical laws that approximates and learns physical dynamics better than traditional data‐driven deep learning methods. In this study, we propose multiphysics‐informed neural networks for soil water‐heat systems, in which the soil moisture and temperature information complement each other well. With our framework, existing soil moisture neural networks are improved to reduce their dependency on the soil moisture measurement density. Furthermore, soil moisture data are employed to promote soil temperature dynamic learning and soil thermal conductivity estimation. Moreover, soil temperature data assist in recovering the nonlinearity of the soil hydraulic conductivity through hydrothermal coupling constraints, allowing better estimations of the soil water flux density. The gradient‐based annealing method is applied to adapt the loss function, which satisfactorily balances the water‐heat transport governing equation constraints on the neural networks. The robustness and generalizability of our framework are examined under diverse scenarios. This work demonstrates the mutual compensation of multisource data in coupled physical processes in a deep learning framework and highlights the significance of appropriate multiphysical constraints designed for nonlinear parameter recovery in PINNs.https://doi.org/10.1029/2022WR031960soil moisturesoil heat transportmultiphysics‐informed neural networkshydrothermal coupling
spellingShingle Yanling Wang
Liangsheng Shi
Xiaolong Hu
Wenxiang Song
Lijun Wang
Multiphysics‐Informed Neural Networks for Coupled Soil Hydrothermal Modeling
Water Resources Research
soil moisture
soil heat transport
multiphysics‐informed neural networks
hydrothermal coupling
title Multiphysics‐Informed Neural Networks for Coupled Soil Hydrothermal Modeling
title_full Multiphysics‐Informed Neural Networks for Coupled Soil Hydrothermal Modeling
title_fullStr Multiphysics‐Informed Neural Networks for Coupled Soil Hydrothermal Modeling
title_full_unstemmed Multiphysics‐Informed Neural Networks for Coupled Soil Hydrothermal Modeling
title_short Multiphysics‐Informed Neural Networks for Coupled Soil Hydrothermal Modeling
title_sort multiphysics informed neural networks for coupled soil hydrothermal modeling
topic soil moisture
soil heat transport
multiphysics‐informed neural networks
hydrothermal coupling
url https://doi.org/10.1029/2022WR031960
work_keys_str_mv AT yanlingwang multiphysicsinformedneuralnetworksforcoupledsoilhydrothermalmodeling
AT liangshengshi multiphysicsinformedneuralnetworksforcoupledsoilhydrothermalmodeling
AT xiaolonghu multiphysicsinformedneuralnetworksforcoupledsoilhydrothermalmodeling
AT wenxiangsong multiphysicsinformedneuralnetworksforcoupledsoilhydrothermalmodeling
AT lijunwang multiphysicsinformedneuralnetworksforcoupledsoilhydrothermalmodeling