Robust development of data-driven models for methane and hydrogen mixture solubility in brine

Abstract Within the domain of hydrogen storage initiatives inside subterranean structures, the accurate estimation of solubility of methane and hydrogen mixtures in brine becomes vital. In this paper, we aim to form robust data-driven intelligent algorithms founded on various machine learning method...

Full description

Saved in:
Bibliographic Details
Main Authors: Kashif Saleem, Abhinav Kumar, K. D. V. Prasad, Ahmad Alkhayyat, T. Ramachandran, Protyay Dey, Navdeep Kaur, R. Sivaranjani, I. B. Sapaev, Mehrdad Mottaghi
Format: Article
Language:English
Published: Springer 2025-04-01
Series:Geomechanics and Geophysics for Geo-Energy and Geo-Resources
Subjects:
Online Access:https://doi.org/10.1007/s40948-025-00947-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849765252122542080
author Kashif Saleem
Abhinav Kumar
K. D. V. Prasad
Ahmad Alkhayyat
T. Ramachandran
Protyay Dey
Navdeep Kaur
R. Sivaranjani
I. B. Sapaev
Mehrdad Mottaghi
author_facet Kashif Saleem
Abhinav Kumar
K. D. V. Prasad
Ahmad Alkhayyat
T. Ramachandran
Protyay Dey
Navdeep Kaur
R. Sivaranjani
I. B. Sapaev
Mehrdad Mottaghi
author_sort Kashif Saleem
collection DOAJ
description Abstract Within the domain of hydrogen storage initiatives inside subterranean structures, the accurate estimation of solubility of methane and hydrogen mixtures in brine becomes vital. In this paper, we aim to form robust data-driven intelligent algorithms founded on various machine learning methods of Support Vector Machine, Random Forest, AdaBoost, Decision Tree, K-nearest Neighbors, Multilayer Perceptron Artificial Neural Network and Convolutional Neural Network to model solubility of hydrogen/methane blend in brine under realistic conditions of underground hydrogen storage projects by utilizing an experimental dataset collected from the existing body of published research. An outlier detection method is utilized for checking out the data reliability for the model development. Also, sensitivity study is done to explore relative impacts of input parameters on solubility. The findings show that the Ensemble Learning model (R2 = 0.994842, MSE = 0.012959, AARE% = 3.842907) and AdaBoost model (R2 = 0.996241, MSE = 0.009444, AARE% = 3.607931) provide the highest accuracy in forecasting hydrogen/methane solubility in brine. These models attain the greatest determination coefficient (R2) and the lowest error metrics (MSE and AARE%), underscoring their remarkable capability to identify complex patterns and provide accurate predictions for estimating hydrogen/methane solubility in brine. The results indicate that Ensemble Learning and AdaBoost yield the highest accuracy algorithms in prediction capability as they tend to illustrate the lowest values of mean squared error and mean absolute relative error (%) and highest R-squared values. In addition, it was shown that solubility is mostly affected by hydrogen mole fraction in mixture and pressure. The developed models can be made use of for the estimate task of hydrogen/methane solubility in brine without needing experiments that are extremely laborious and require a lot of time.
format Article
id doaj-art-62f2e0a695904054bbb3276f3749855e
institution DOAJ
issn 2363-8419
2363-8427
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series Geomechanics and Geophysics for Geo-Energy and Geo-Resources
spelling doaj-art-62f2e0a695904054bbb3276f3749855e2025-08-20T03:04:54ZengSpringerGeomechanics and Geophysics for Geo-Energy and Geo-Resources2363-84192363-84272025-04-0111112010.1007/s40948-025-00947-1Robust development of data-driven models for methane and hydrogen mixture solubility in brineKashif Saleem0Abhinav Kumar1K. D. V. Prasad2Ahmad Alkhayyat3T. Ramachandran4Protyay Dey5Navdeep Kaur6R. Sivaranjani7I. B. Sapaev8Mehrdad Mottaghi9Department of Computer Science and Engineering, College of Applied Studies and Community Service, King Saud UniversityDepartment of Nuclear and Renewable Energy, Ural Federal University Named After the First President of Russia Boris YeltsinSymbiosis Institute of Business Management, Hyderabad, Symbiosis International (Deemed University)Department of Computers Techniques Engineering, College of Technical Engineering, The Islamic UniversityDepartment of Mechanical Engineering, School of Engineering and Technology, JAIN (Deemed to be University)Department of Computing Science and Artificial Intelligence, NIMS Institute of Engineering and Technology, NIMS University RajasthanDepartment of Computer Science Engineering, Chandigarh Engineering College, Chandigarh Group of Colleges, JhanjeriDepartment of Computer Science and Engineering, Raghu Engineering CollegeDepartment «Physics and Chemistry», “Tashkent Institute of Irrigation and Agricultural Mechanization Engineers” National Research UniversityFaculty of Chemistry, Kabul UniversityAbstract Within the domain of hydrogen storage initiatives inside subterranean structures, the accurate estimation of solubility of methane and hydrogen mixtures in brine becomes vital. In this paper, we aim to form robust data-driven intelligent algorithms founded on various machine learning methods of Support Vector Machine, Random Forest, AdaBoost, Decision Tree, K-nearest Neighbors, Multilayer Perceptron Artificial Neural Network and Convolutional Neural Network to model solubility of hydrogen/methane blend in brine under realistic conditions of underground hydrogen storage projects by utilizing an experimental dataset collected from the existing body of published research. An outlier detection method is utilized for checking out the data reliability for the model development. Also, sensitivity study is done to explore relative impacts of input parameters on solubility. The findings show that the Ensemble Learning model (R2 = 0.994842, MSE = 0.012959, AARE% = 3.842907) and AdaBoost model (R2 = 0.996241, MSE = 0.009444, AARE% = 3.607931) provide the highest accuracy in forecasting hydrogen/methane solubility in brine. These models attain the greatest determination coefficient (R2) and the lowest error metrics (MSE and AARE%), underscoring their remarkable capability to identify complex patterns and provide accurate predictions for estimating hydrogen/methane solubility in brine. The results indicate that Ensemble Learning and AdaBoost yield the highest accuracy algorithms in prediction capability as they tend to illustrate the lowest values of mean squared error and mean absolute relative error (%) and highest R-squared values. In addition, it was shown that solubility is mostly affected by hydrogen mole fraction in mixture and pressure. The developed models can be made use of for the estimate task of hydrogen/methane solubility in brine without needing experiments that are extremely laborious and require a lot of time.https://doi.org/10.1007/s40948-025-00947-1Hydrogen energyHydrogen/methane solubilityOutlier detectionSensitivity studyMachine learningIntelligent modeling
spellingShingle Kashif Saleem
Abhinav Kumar
K. D. V. Prasad
Ahmad Alkhayyat
T. Ramachandran
Protyay Dey
Navdeep Kaur
R. Sivaranjani
I. B. Sapaev
Mehrdad Mottaghi
Robust development of data-driven models for methane and hydrogen mixture solubility in brine
Geomechanics and Geophysics for Geo-Energy and Geo-Resources
Hydrogen energy
Hydrogen/methane solubility
Outlier detection
Sensitivity study
Machine learning
Intelligent modeling
title Robust development of data-driven models for methane and hydrogen mixture solubility in brine
title_full Robust development of data-driven models for methane and hydrogen mixture solubility in brine
title_fullStr Robust development of data-driven models for methane and hydrogen mixture solubility in brine
title_full_unstemmed Robust development of data-driven models for methane and hydrogen mixture solubility in brine
title_short Robust development of data-driven models for methane and hydrogen mixture solubility in brine
title_sort robust development of data driven models for methane and hydrogen mixture solubility in brine
topic Hydrogen energy
Hydrogen/methane solubility
Outlier detection
Sensitivity study
Machine learning
Intelligent modeling
url https://doi.org/10.1007/s40948-025-00947-1
work_keys_str_mv AT kashifsaleem robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT abhinavkumar robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT kdvprasad robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT ahmadalkhayyat robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT tramachandran robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT protyaydey robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT navdeepkaur robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT rsivaranjani robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT ibsapaev robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine
AT mehrdadmottaghi robustdevelopmentofdatadrivenmodelsformethaneandhydrogenmixturesolubilityinbrine