No Cover Image

Journal article 196 views 4 downloads

Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications

Saeid Khairandesh, Marzieh Lotfi, Afsanehsadat Larimi Orcid Logo, Ali Akbar Asgharinezhad, Cyrus Ghotbi

Scientific Reports, Volume: 16, Start page: 14114

Swansea University Author: Afsanehsadat Larimi Orcid Logo

  • 71692.VOR.pdf

    PDF | Version of Record

    © The Author(s) 2026. This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

    Download (2.13MB)

Check full text

DOI (Published version): 10.1038/s41598-026-44340-8

Abstract

Hydrogen is a promising clean energy carrier, but its low energy density necessitates advanced storage solutions. Metal–Organic Frameworks (MOFs) offer high tunability and porosity for efficient hydrogen adsorption. This work combines Grand Canonical Monte Carlo (GCMC) simulations with machine learn...

Full description

Published in: Scientific Reports
ISSN: 2045-2322
Published: Springer Nature 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71692
first_indexed 2026-04-01T09:14:24Z
last_indexed 2026-05-19T11:16:26Z
id cronfa71692
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-05-18T11:12:16.0792638</datestamp><bib-version>v2</bib-version><id>71692</id><entry>2026-04-01</entry><title>Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications</title><swanseaauthors><author><sid>db028d01b9d62d39518f147f6bb08fa5</sid><ORCID>0000-0001-5566-171X</ORCID><firstname>Afsanehsadat</firstname><surname>Larimi</surname><name>Afsanehsadat Larimi</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-04-01</date><deptcode>EAAS</deptcode><abstract>Hydrogen is a promising clean energy carrier, but its low energy density necessitates advanced storage solutions. Metal&#x2013;Organic Frameworks (MOFs) offer high tunability and porosity for efficient hydrogen adsorption. This work combines Grand Canonical Monte Carlo (GCMC) simulations with machine learning, employing Feed-Forward (FNN) and Pattern Recognition (PRNN) neural networks optimized via Equilibrium Optimizer and Genetic Algorithm. The integrated approach predicts gravimetric and volumetric hydrogen storage capacities across 98,695 metal&#x2013;organic frameworks under temperature&#x2013;pressure swing conditions. Pore volume and void fraction emerged as dominant structural descriptors. The models identified 12 top-performing MOFs exceeding MOF-5 in both gravimetric (8.27 wt.%) and volumetric (51.94 g-H2/L) capacities, demonstrating the power of ML-accelerated screening for next-generation hydrogen storage materials.</abstract><type>Journal Article</type><journal>Scientific Reports</journal><volume>16</volume><journalNumber/><paginationStart>14114</paginationStart><paginationEnd/><publisher>Springer Nature</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>2045-2322</issnElectronic><keywords>Hydrogen storage; Metal&#x2013;organic-framework (MOFs); Artificial neural networks (ANNs); Grand canonical Monte Carlo (GCMC); Temperature&#x2013;pressure swing conditions</keywords><publishedDay>18</publishedDay><publishedMonth>3</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-03-18</publishedDate><doi>10.1038/s41598-026-44340-8</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering and Applied Sciences School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EAAS</DepartmentCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders/><projectreference/><lastEdited>2026-05-18T11:12:16.0792638</lastEdited><Created>2026-04-01T10:10:59.7166178</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Chemical Engineering</level></path><authors><author><firstname>Saeid</firstname><surname>Khairandesh</surname><order>1</order></author><author><firstname>Marzieh</firstname><surname>Lotfi</surname><order>2</order></author><author><firstname>Afsanehsadat</firstname><surname>Larimi</surname><orcid>0000-0001-5566-171X</orcid><order>3</order></author><author><firstname>Ali Akbar</firstname><surname>Asgharinezhad</surname><order>4</order></author><author><firstname>Cyrus</firstname><surname>Ghotbi</surname><order>5</order></author></authors><documents><document><filename>71692__36773__7a34b8911e6f4823818e5529d8c4e7d5.pdf</filename><originalFilename>71692.VOR.pdf</originalFilename><uploaded>2026-05-18T11:09:05.0568031</uploaded><type>Output</type><contentLength>2238499</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; The Author(s) 2026. This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-05-18T11:12:16.0792638 v2 71692 2026-04-01 Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications db028d01b9d62d39518f147f6bb08fa5 0000-0001-5566-171X Afsanehsadat Larimi Afsanehsadat Larimi true false 2026-04-01 EAAS Hydrogen is a promising clean energy carrier, but its low energy density necessitates advanced storage solutions. Metal–Organic Frameworks (MOFs) offer high tunability and porosity for efficient hydrogen adsorption. This work combines Grand Canonical Monte Carlo (GCMC) simulations with machine learning, employing Feed-Forward (FNN) and Pattern Recognition (PRNN) neural networks optimized via Equilibrium Optimizer and Genetic Algorithm. The integrated approach predicts gravimetric and volumetric hydrogen storage capacities across 98,695 metal–organic frameworks under temperature–pressure swing conditions. Pore volume and void fraction emerged as dominant structural descriptors. The models identified 12 top-performing MOFs exceeding MOF-5 in both gravimetric (8.27 wt.%) and volumetric (51.94 g-H2/L) capacities, demonstrating the power of ML-accelerated screening for next-generation hydrogen storage materials. Journal Article Scientific Reports 16 14114 Springer Nature 2045-2322 Hydrogen storage; Metal–organic-framework (MOFs); Artificial neural networks (ANNs); Grand canonical Monte Carlo (GCMC); Temperature–pressure swing conditions 18 3 2026 2026-03-18 10.1038/s41598-026-44340-8 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University Not Required 2026-05-18T11:12:16.0792638 2026-04-01T10:10:59.7166178 Faculty of Science and Engineering School of Engineering and Applied Sciences - Chemical Engineering Saeid Khairandesh 1 Marzieh Lotfi 2 Afsanehsadat Larimi 0000-0001-5566-171X 3 Ali Akbar Asgharinezhad 4 Cyrus Ghotbi 5 71692__36773__7a34b8911e6f4823818e5529d8c4e7d5.pdf 71692.VOR.pdf 2026-05-18T11:09:05.0568031 Output 2238499 application/pdf Version of Record true © The Author(s) 2026. This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications
spellingShingle Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications
Afsanehsadat Larimi
title_short Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications
title_full Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications
title_fullStr Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications
title_full_unstemmed Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications
title_sort Accelerating discovery of MOFs for hydrogen storage via machine learning in energy related applications
author_id_str_mv db028d01b9d62d39518f147f6bb08fa5
author_id_fullname_str_mv db028d01b9d62d39518f147f6bb08fa5_***_Afsanehsadat Larimi
author Afsanehsadat Larimi
author2 Saeid Khairandesh
Marzieh Lotfi
Afsanehsadat Larimi
Ali Akbar Asgharinezhad
Cyrus Ghotbi
format Journal article
container_title Scientific Reports
container_volume 16
container_start_page 14114
publishDate 2026
institution Swansea University
issn 2045-2322
doi_str_mv 10.1038/s41598-026-44340-8
publisher Springer Nature
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Chemical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Chemical Engineering
document_store_str 1
active_str 0
description Hydrogen is a promising clean energy carrier, but its low energy density necessitates advanced storage solutions. Metal–Organic Frameworks (MOFs) offer high tunability and porosity for efficient hydrogen adsorption. This work combines Grand Canonical Monte Carlo (GCMC) simulations with machine learning, employing Feed-Forward (FNN) and Pattern Recognition (PRNN) neural networks optimized via Equilibrium Optimizer and Genetic Algorithm. The integrated approach predicts gravimetric and volumetric hydrogen storage capacities across 98,695 metal–organic frameworks under temperature–pressure swing conditions. Pore volume and void fraction emerged as dominant structural descriptors. The models identified 12 top-performing MOFs exceeding MOF-5 in both gravimetric (8.27 wt.%) and volumetric (51.94 g-H2/L) capacities, demonstrating the power of ML-accelerated screening for next-generation hydrogen storage materials.
published_date 2026-03-18T07:24:17Z
_version_ 1866955864724733952
score 11.107121

Similar Items