Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage

Abstract Subsurface flow research is essential for the sustainable management of natural resources and the environment. Deep learning (DL) has significantly advanced this field by developing efficient and accurate surrogate models to replace computationally expensive physics‐based simulations. These...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaowen Mao, Alvaro Carbonero, Mohamed Mehana
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Journal of Geophysical Research: Machine Learning and Computation
Subjects:
Online Access:https://doi.org/10.1029/2024JH000401
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063197674930176
author Shaowen Mao
Alvaro Carbonero
Mohamed Mehana
author_facet Shaowen Mao
Alvaro Carbonero
Mohamed Mehana
author_sort Shaowen Mao
collection DOAJ
description Abstract Subsurface flow research is essential for the sustainable management of natural resources and the environment. Deep learning (DL) has significantly advanced this field by developing efficient and accurate surrogate models to replace computationally expensive physics‐based simulations. These surrogate models are commonly used to predict the spatiotemporal evolution of state variables, such as gas saturation and reservoir pressure, in heterogeneous geological formations. Despite the various DL models applied to this task, there is a lack of studies systematically comparing their performance. This absence of comparative analysis leads to somewhat arbitrary DL model selection in subsurface flow research, resulting in suboptimal performance and potentially inaccurate predictions. To bridge this gap, we conduct a systematic comparison study of three popular DL architectures—U‐Net, Fourier Neural Operators (FNO), and Segmentation Transformer (SETR)—in surrogate modeling of underground hydrogen storage (UHS). We focus on UHS due to its promise of enhancing clean energy resilience and its cyclic operational conditions that represent common scenarios in various subsurface applications. We evaluate the models based on accuracy, training cost, and inference speed. The comparison shows that U‐Net achieves the highest accuracy, followed by SETR and FNO. Despite its lower accuracy, FNO has the highest inference speed. SETR offers competitive accuracy with the least training memory usage, demonstrating the potential of transformers in learning subsurface flow. Our results provide guidance for selecting DL models for surrogate modeling in a wide range of subsurface flow problems.
format Article
id doaj-art-dd4bd102aaa2433d87a0d1c29e515697
institution DOAJ
issn 2993-5210
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Journal of Geophysical Research: Machine Learning and Computation
spelling doaj-art-dd4bd102aaa2433d87a0d1c29e5156972025-08-20T02:49:43ZengWileyJournal of Geophysical Research: Machine Learning and Computation2993-52102025-03-0121n/an/a10.1029/2024JH000401Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen StorageShaowen Mao0Alvaro Carbonero1Mohamed Mehana2Earth and Environmental Sciences Division Los Alamos National Laboratory Los Alamos NM USAEarth and Environmental Sciences Division Los Alamos National Laboratory Los Alamos NM USAEarth and Environmental Sciences Division Los Alamos National Laboratory Los Alamos NM USAAbstract Subsurface flow research is essential for the sustainable management of natural resources and the environment. Deep learning (DL) has significantly advanced this field by developing efficient and accurate surrogate models to replace computationally expensive physics‐based simulations. These surrogate models are commonly used to predict the spatiotemporal evolution of state variables, such as gas saturation and reservoir pressure, in heterogeneous geological formations. Despite the various DL models applied to this task, there is a lack of studies systematically comparing their performance. This absence of comparative analysis leads to somewhat arbitrary DL model selection in subsurface flow research, resulting in suboptimal performance and potentially inaccurate predictions. To bridge this gap, we conduct a systematic comparison study of three popular DL architectures—U‐Net, Fourier Neural Operators (FNO), and Segmentation Transformer (SETR)—in surrogate modeling of underground hydrogen storage (UHS). We focus on UHS due to its promise of enhancing clean energy resilience and its cyclic operational conditions that represent common scenarios in various subsurface applications. We evaluate the models based on accuracy, training cost, and inference speed. The comparison shows that U‐Net achieves the highest accuracy, followed by SETR and FNO. Despite its lower accuracy, FNO has the highest inference speed. SETR offers competitive accuracy with the least training memory usage, demonstrating the potential of transformers in learning subsurface flow. Our results provide guidance for selecting DL models for surrogate modeling in a wide range of subsurface flow problems.https://doi.org/10.1029/2024JH000401deep learningunderground hydrogen storagesubsurface flowU‐NetFourier neural operators (FNO)transformers
spellingShingle Shaowen Mao
Alvaro Carbonero
Mohamed Mehana
Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage
Journal of Geophysical Research: Machine Learning and Computation
deep learning
underground hydrogen storage
subsurface flow
U‐Net
Fourier neural operators (FNO)
transformers
title Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage
title_full Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage
title_fullStr Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage
title_full_unstemmed Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage
title_short Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage
title_sort deep learning for subsurface flow a comparative study of u net fourier neural operators and transformers in underground hydrogen storage
topic deep learning
underground hydrogen storage
subsurface flow
U‐Net
Fourier neural operators (FNO)
transformers
url https://doi.org/10.1029/2024JH000401
work_keys_str_mv AT shaowenmao deeplearningforsubsurfaceflowacomparativestudyofunetfourierneuraloperatorsandtransformersinundergroundhydrogenstorage
AT alvarocarbonero deeplearningforsubsurfaceflowacomparativestudyofunetfourierneuraloperatorsandtransformersinundergroundhydrogenstorage
AT mohamedmehana deeplearningforsubsurfaceflowacomparativestudyofunetfourierneuraloperatorsandtransformersinundergroundhydrogenstorage