Deep Learning Identification of the Governing Equation for Water Flow in Heterogeneous Soils From Data

Abstract Despite the remarkable advances in using deep learning for describing and predicting soil water flow, these models inherently cannot deepen our understanding of its underlying physical mechanisms as they are black‐box approaches. To address this issue, a novel data‐driven equation discovery...

Full description

Saved in:
Bibliographic Details
Main Authors: Wenxiang Song, Liangsheng Shi, Leilei He, Yuanyuan Zha, Xiaolong Hu, Mehdi Rahmati, Harry Vereecken
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2024WR037786
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850211945859252224
author Wenxiang Song
Liangsheng Shi
Leilei He
Yuanyuan Zha
Xiaolong Hu
Mehdi Rahmati
Harry Vereecken
author_facet Wenxiang Song
Liangsheng Shi
Leilei He
Yuanyuan Zha
Xiaolong Hu
Mehdi Rahmati
Harry Vereecken
author_sort Wenxiang Song
collection DOAJ
description Abstract Despite the remarkable advances in using deep learning for describing and predicting soil water flow, these models inherently cannot deepen our understanding of its underlying physical mechanisms as they are black‐box approaches. To address this issue, a novel data‐driven equation discovery approach has recently been widely used to facilitate scientific discovery in geoscience disciplines, including soil hydrology. However, due to the inherent complexity of soils, current data‐driven discovery approaches cannot deal with heterogeneous soil scenarios. In this study, we present a new group sparse regression theory and a deep learning framework to extend previous studies to be able to identify the governing equations for soil water flow in heterogeneous soils from observational data. Specifically, we focus on discovering equations from only time series of volumetric soil water content data, which are easily accessible. To accommodate it, the underlying assumption of the generalized soil‐water content‐based governing equation is utilized, and a coarse‐grained group sparsity theory is developed. Furthermore, we incorporate the proposed group sparse regression into a new deep‐learning framework: Extended‐DeepGS (Extended Deep‐learning‐based Group Sparsity). Through deep‐learning identification, it realizes simultaneous reconstructions of soil moisture dynamics and governing equations. A series of comprehensive numerical experiments are designed and conducted to test the performance of the theory and framework, and the results show its robustness. We also summarize the potential effects of soil heterogeneity on the discovery of equations. Finally, we discuss the limitations of the approach, which may inform future developments.
format Article
id doaj-art-1eabe232bd7f4dde8d476001bea7be48
institution OA Journals
issn 0043-1397
1944-7973
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-1eabe232bd7f4dde8d476001bea7be482025-08-20T02:09:27ZengWileyWater Resources Research0043-13971944-79732025-03-01613n/an/a10.1029/2024WR037786Deep Learning Identification of the Governing Equation for Water Flow in Heterogeneous Soils From DataWenxiang Song0Liangsheng Shi1Leilei He2Yuanyuan Zha3Xiaolong Hu4Mehdi Rahmati5Harry Vereecken6State Key Laboratory of Water Resources Engineering and Management Wuhan University Wuhan ChinaState Key Laboratory of Water Resources Engineering and Management Wuhan University Wuhan ChinaState Key Laboratory of Water Resources Engineering and Management Wuhan University Wuhan ChinaState Key Laboratory of Water Resources Engineering and Management Wuhan University Wuhan ChinaState Key Laboratory of Water Resources Engineering and Management Wuhan University Wuhan ChinaInstitute of Bio‐ and Geosciences: Agrosphere (IBG‐3) Forschungszentrum Jülich Jülich GermanyInstitute of Bio‐ and Geosciences: Agrosphere (IBG‐3) Forschungszentrum Jülich Jülich GermanyAbstract Despite the remarkable advances in using deep learning for describing and predicting soil water flow, these models inherently cannot deepen our understanding of its underlying physical mechanisms as they are black‐box approaches. To address this issue, a novel data‐driven equation discovery approach has recently been widely used to facilitate scientific discovery in geoscience disciplines, including soil hydrology. However, due to the inherent complexity of soils, current data‐driven discovery approaches cannot deal with heterogeneous soil scenarios. In this study, we present a new group sparse regression theory and a deep learning framework to extend previous studies to be able to identify the governing equations for soil water flow in heterogeneous soils from observational data. Specifically, we focus on discovering equations from only time series of volumetric soil water content data, which are easily accessible. To accommodate it, the underlying assumption of the generalized soil‐water content‐based governing equation is utilized, and a coarse‐grained group sparsity theory is developed. Furthermore, we incorporate the proposed group sparse regression into a new deep‐learning framework: Extended‐DeepGS (Extended Deep‐learning‐based Group Sparsity). Through deep‐learning identification, it realizes simultaneous reconstructions of soil moisture dynamics and governing equations. A series of comprehensive numerical experiments are designed and conducted to test the performance of the theory and framework, and the results show its robustness. We also summarize the potential effects of soil heterogeneity on the discovery of equations. Finally, we discuss the limitations of the approach, which may inform future developments.https://doi.org/10.1029/2024WR037786soil moisturedata‐driven discoverydeep learning
spellingShingle Wenxiang Song
Liangsheng Shi
Leilei He
Yuanyuan Zha
Xiaolong Hu
Mehdi Rahmati
Harry Vereecken
Deep Learning Identification of the Governing Equation for Water Flow in Heterogeneous Soils From Data
Water Resources Research
soil moisture
data‐driven discovery
deep learning
title Deep Learning Identification of the Governing Equation for Water Flow in Heterogeneous Soils From Data
title_full Deep Learning Identification of the Governing Equation for Water Flow in Heterogeneous Soils From Data
title_fullStr Deep Learning Identification of the Governing Equation for Water Flow in Heterogeneous Soils From Data
title_full_unstemmed Deep Learning Identification of the Governing Equation for Water Flow in Heterogeneous Soils From Data
title_short Deep Learning Identification of the Governing Equation for Water Flow in Heterogeneous Soils From Data
title_sort deep learning identification of the governing equation for water flow in heterogeneous soils from data
topic soil moisture
data‐driven discovery
deep learning
url https://doi.org/10.1029/2024WR037786
work_keys_str_mv AT wenxiangsong deeplearningidentificationofthegoverningequationforwaterflowinheterogeneoussoilsfromdata
AT liangshengshi deeplearningidentificationofthegoverningequationforwaterflowinheterogeneoussoilsfromdata
AT leileihe deeplearningidentificationofthegoverningequationforwaterflowinheterogeneoussoilsfromdata
AT yuanyuanzha deeplearningidentificationofthegoverningequationforwaterflowinheterogeneoussoilsfromdata
AT xiaolonghu deeplearningidentificationofthegoverningequationforwaterflowinheterogeneoussoilsfromdata
AT mehdirahmati deeplearningidentificationofthegoverningequationforwaterflowinheterogeneoussoilsfromdata
AT harryvereecken deeplearningidentificationofthegoverningequationforwaterflowinheterogeneoussoilsfromdata