Forecasting Groundwater Level by Characterizing Multiple Spatial Dependencies of Environmental Factors Using Graph‐Based Deep Learning

Abstract Accurate forecasting for groundwater levels is essential for water resource management and sustainable development. Regional variations in groundwater levels exhibit a complex spatial dependency structure due to the physical proximity of monitoring wells, hydrological connectivity, and shar...

Full description

Saved in:
Bibliographic Details
Main Authors: Yinghan Wu, Gang Mei, Kaixuan Shao, Nengxiong Xu, Jianbing Peng
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:Journal of Geophysical Research: Machine Learning and Computation
Subjects:
Online Access:https://doi.org/10.1029/2024JH000520
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850167598508933120
author Yinghan Wu
Gang Mei
Kaixuan Shao
Nengxiong Xu
Jianbing Peng
author_facet Yinghan Wu
Gang Mei
Kaixuan Shao
Nengxiong Xu
Jianbing Peng
author_sort Yinghan Wu
collection DOAJ
description Abstract Accurate forecasting for groundwater levels is essential for water resource management and sustainable development. Regional variations in groundwater levels exhibit a complex spatial dependency structure due to the physical proximity of monitoring wells, hydrological connectivity, and shared environmental characteristics. However, existing research has mostly overlooked the multiple spatial dependencies between monitoring wells, limiting the understanding of the added value that graph‐based models bring to groundwater dynamics prediction. In this study, we characterize spatial dependencies of groundwater from multiple perspectives and investigate the impact on the forecasting results of groundwater dynamics using graph‐based deep learning. Characterizing spatial dependencies helps improve the understanding of groundwater dynamics, but its effectiveness in enhancing prediction accuracy depends on the characteristics of spatial interactions. Graph neural networks facilitate learning from diverse spatial associations, allowing for a more comprehensive representation of spatial dependencies and uncovering potential connections between monitoring wells. Results based on real data sets contribute to understanding how multiple spatial dependencies influence groundwater level forecasting. Our research provides insights into exploiting potential spatial dependencies in similarly complex and highly interconnected earth systems.
format Article
id doaj-art-e8be9c5beec641bcbd4b0792141e5788
institution OA Journals
issn 2993-5210
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series Journal of Geophysical Research: Machine Learning and Computation
spelling doaj-art-e8be9c5beec641bcbd4b0792141e57882025-08-20T02:21:10ZengWileyJournal of Geophysical Research: Machine Learning and Computation2993-52102025-06-0122n/an/a10.1029/2024JH000520Forecasting Groundwater Level by Characterizing Multiple Spatial Dependencies of Environmental Factors Using Graph‐Based Deep LearningYinghan Wu0Gang Mei1Kaixuan Shao2Nengxiong Xu3Jianbing Peng4School of Engineering and Technology China University of Geosciences Beijing ChinaSchool of Engineering and Technology China University of Geosciences Beijing ChinaSchool of Engineering and Technology China University of Geosciences Beijing ChinaSchool of Engineering and Technology China University of Geosciences Beijing ChinaSchool of Engineering and Technology China University of Geosciences Beijing ChinaAbstract Accurate forecasting for groundwater levels is essential for water resource management and sustainable development. Regional variations in groundwater levels exhibit a complex spatial dependency structure due to the physical proximity of monitoring wells, hydrological connectivity, and shared environmental characteristics. However, existing research has mostly overlooked the multiple spatial dependencies between monitoring wells, limiting the understanding of the added value that graph‐based models bring to groundwater dynamics prediction. In this study, we characterize spatial dependencies of groundwater from multiple perspectives and investigate the impact on the forecasting results of groundwater dynamics using graph‐based deep learning. Characterizing spatial dependencies helps improve the understanding of groundwater dynamics, but its effectiveness in enhancing prediction accuracy depends on the characteristics of spatial interactions. Graph neural networks facilitate learning from diverse spatial associations, allowing for a more comprehensive representation of spatial dependencies and uncovering potential connections between monitoring wells. Results based on real data sets contribute to understanding how multiple spatial dependencies influence groundwater level forecasting. Our research provides insights into exploiting potential spatial dependencies in similarly complex and highly interconnected earth systems.https://doi.org/10.1029/2024JH000520groundwater level forecastingmultiple spatial dependenciesgraph‐based deep learningtemporal graph convolutional network
spellingShingle Yinghan Wu
Gang Mei
Kaixuan Shao
Nengxiong Xu
Jianbing Peng
Forecasting Groundwater Level by Characterizing Multiple Spatial Dependencies of Environmental Factors Using Graph‐Based Deep Learning
Journal of Geophysical Research: Machine Learning and Computation
groundwater level forecasting
multiple spatial dependencies
graph‐based deep learning
temporal graph convolutional network
title Forecasting Groundwater Level by Characterizing Multiple Spatial Dependencies of Environmental Factors Using Graph‐Based Deep Learning
title_full Forecasting Groundwater Level by Characterizing Multiple Spatial Dependencies of Environmental Factors Using Graph‐Based Deep Learning
title_fullStr Forecasting Groundwater Level by Characterizing Multiple Spatial Dependencies of Environmental Factors Using Graph‐Based Deep Learning
title_full_unstemmed Forecasting Groundwater Level by Characterizing Multiple Spatial Dependencies of Environmental Factors Using Graph‐Based Deep Learning
title_short Forecasting Groundwater Level by Characterizing Multiple Spatial Dependencies of Environmental Factors Using Graph‐Based Deep Learning
title_sort forecasting groundwater level by characterizing multiple spatial dependencies of environmental factors using graph based deep learning
topic groundwater level forecasting
multiple spatial dependencies
graph‐based deep learning
temporal graph convolutional network
url https://doi.org/10.1029/2024JH000520
work_keys_str_mv AT yinghanwu forecastinggroundwaterlevelbycharacterizingmultiplespatialdependenciesofenvironmentalfactorsusinggraphbaseddeeplearning
AT gangmei forecastinggroundwaterlevelbycharacterizingmultiplespatialdependenciesofenvironmentalfactorsusinggraphbaseddeeplearning
AT kaixuanshao forecastinggroundwaterlevelbycharacterizingmultiplespatialdependenciesofenvironmentalfactorsusinggraphbaseddeeplearning
AT nengxiongxu forecastinggroundwaterlevelbycharacterizingmultiplespatialdependenciesofenvironmentalfactorsusinggraphbaseddeeplearning
AT jianbingpeng forecastinggroundwaterlevelbycharacterizingmultiplespatialdependenciesofenvironmentalfactorsusinggraphbaseddeeplearning