Multi-objective optimization of cushion gas design in underground gas storage using machine learning

Underground natural gas storage (UGS) has played a vital role in ensuring the energy supply chain stability in various regions worldwide over the past decades. The increasing trend in energy and natural gas consumption globally necessitates further development of UGS projects. Depleted oil reservoir...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohaddeseh Ahmadi Aghdam, Maryam Fazaeli, Mahdi Kanaani, Behnam Sedaee
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025027264
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849389480202469376
author Mohaddeseh Ahmadi Aghdam
Maryam Fazaeli
Mahdi Kanaani
Behnam Sedaee
author_facet Mohaddeseh Ahmadi Aghdam
Maryam Fazaeli
Mahdi Kanaani
Behnam Sedaee
author_sort Mohaddeseh Ahmadi Aghdam
collection DOAJ
description Underground natural gas storage (UGS) has played a vital role in ensuring the energy supply chain stability in various regions worldwide over the past decades. The increasing trend in energy and natural gas consumption globally necessitates further development of UGS projects. Depleted oil reservoirs, due to their limited suitable storage environments in some areas and proximity to major consumption centers, can be utilized to develop natural gas storage further. In this study, a UGS project in an oil reservoir is optimized by designing it in a manner that facilitates the sequestration of CO₂ gas through the replacement of a portion of the cushion gas with inert gases. To address the computational cost of dynamic simulation, a proxy model was developed using three regression algorithms: SVR, XGBoost, and MLNN. Among them, the MLNN model, with three hidden layers, achieved the best performance (R² = 0.9886 for training and 0.9562 for testing), and reduced MAE by over 40 % compared to SVR. This model enabled rapid multi-objective optimization using the MOPSO algorithm. Several Pareto fronts were generated, and the best front provided 500 optimal solutions after 300 iterations. The proposed framework significantly reduces optimization time—by over 90 % compared to conventional simulation—while capturing the complex trade-off between maximizing gas recovery and CO₂ sequestration. This research is among the first to integrate intelligent proxy modeling with multi-objective optimization for cushion gas design in UGS systems, offering a novel path toward environmentally responsible storage strategies.
format Article
id doaj-art-fab2797938764a4cbc7d52df9ada3693
institution Kabale University
issn 2590-1230
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-fab2797938764a4cbc7d52df9ada36932025-08-20T03:41:57ZengElsevierResults in Engineering2590-12302025-09-012710665910.1016/j.rineng.2025.106659Multi-objective optimization of cushion gas design in underground gas storage using machine learningMohaddeseh Ahmadi Aghdam0Maryam Fazaeli1Mahdi Kanaani2Behnam Sedaee3Institute of Petroleum Engineering, Department of Chemical Engineering, College of Engineering, University of Tehran, IranKish Campus, University of Tehran, IranInstitute of Petroleum Engineering, Department of Chemical Engineering, College of Engineering, University of Tehran, IranInstitute of Petroleum Engineering, Department of Chemical Engineering, College of Engineering, University of Tehran, Iran; The core of the Research Center for Underground Hydrogen Storage, University of Tehran, Iran; Corresponding author.Underground natural gas storage (UGS) has played a vital role in ensuring the energy supply chain stability in various regions worldwide over the past decades. The increasing trend in energy and natural gas consumption globally necessitates further development of UGS projects. Depleted oil reservoirs, due to their limited suitable storage environments in some areas and proximity to major consumption centers, can be utilized to develop natural gas storage further. In this study, a UGS project in an oil reservoir is optimized by designing it in a manner that facilitates the sequestration of CO₂ gas through the replacement of a portion of the cushion gas with inert gases. To address the computational cost of dynamic simulation, a proxy model was developed using three regression algorithms: SVR, XGBoost, and MLNN. Among them, the MLNN model, with three hidden layers, achieved the best performance (R² = 0.9886 for training and 0.9562 for testing), and reduced MAE by over 40 % compared to SVR. This model enabled rapid multi-objective optimization using the MOPSO algorithm. Several Pareto fronts were generated, and the best front provided 500 optimal solutions after 300 iterations. The proposed framework significantly reduces optimization time—by over 90 % compared to conventional simulation—while capturing the complex trade-off between maximizing gas recovery and CO₂ sequestration. This research is among the first to integrate intelligent proxy modeling with multi-objective optimization for cushion gas design in UGS systems, offering a novel path toward environmentally responsible storage strategies.http://www.sciencedirect.com/science/article/pii/S2590123025027264UGSCushion gas replacementCarbon sequestrationGas recovery factorMachine LearningMulti-Objective Optimization
spellingShingle Mohaddeseh Ahmadi Aghdam
Maryam Fazaeli
Mahdi Kanaani
Behnam Sedaee
Multi-objective optimization of cushion gas design in underground gas storage using machine learning
Results in Engineering
UGS
Cushion gas replacement
Carbon sequestration
Gas recovery factor
Machine Learning
Multi-Objective Optimization
title Multi-objective optimization of cushion gas design in underground gas storage using machine learning
title_full Multi-objective optimization of cushion gas design in underground gas storage using machine learning
title_fullStr Multi-objective optimization of cushion gas design in underground gas storage using machine learning
title_full_unstemmed Multi-objective optimization of cushion gas design in underground gas storage using machine learning
title_short Multi-objective optimization of cushion gas design in underground gas storage using machine learning
title_sort multi objective optimization of cushion gas design in underground gas storage using machine learning
topic UGS
Cushion gas replacement
Carbon sequestration
Gas recovery factor
Machine Learning
Multi-Objective Optimization
url http://www.sciencedirect.com/science/article/pii/S2590123025027264
work_keys_str_mv AT mohaddesehahmadiaghdam multiobjectiveoptimizationofcushiongasdesigninundergroundgasstorageusingmachinelearning
AT maryamfazaeli multiobjectiveoptimizationofcushiongasdesigninundergroundgasstorageusingmachinelearning
AT mahdikanaani multiobjectiveoptimizationofcushiongasdesigninundergroundgasstorageusingmachinelearning
AT behnamsedaee multiobjectiveoptimizationofcushiongasdesigninundergroundgasstorageusingmachinelearning