Building a Physics-Aware AI Ecosystem for Solid-State Hydrogen Storage Materials
Abstract Hydrogen storage remains a central bottleneck for scalable hydrogen energy systems due to the multiscale and coupled nature of the thermodynamics, kinetics, and microstructural evolution of hydrogen storage materials (HSMs). Although artificial intelligence (AI) has accelerated materials discovery, current approaches remain constrained by fragmented data, limited physical consistency, and weak integration with experimental validation. Here, we propose a unified framework that integrates coherent data infrastructure, physics-grounded modeling, and AI-driven inverse design within a closed-loop discovery paradigm. By constraining optimization with thermodynamics, kinetics, uncertainty, provenance, and experimental feedback, this approach enables adaptive, physically consistent optimization, thereby establishing a pathway toward autonomous, digital-twin-enabled discovery of HSMs.
Authors
- George E. Froudakis (ORCID: https://orcid.org/0000-0002-6907-1822)
- Chris J. Pickard (ORCID: https://orcid.org/0000-0002-9684-5432)
- Zhenpeng Yao (ORCID: https://orcid.org/0000-0001-8286-8257)
- Kaihang Shi (ORCID: https://orcid.org/0000-0002-0297-1746)
- Darren P. Broom (ORCID: https://orcid.org/0000-0002-1328-7376)
- Marcello Baricco (ORCID: https://orcid.org/0000-0002-2856-9894)
- Mark Paskevicius (ORCID: https://orcid.org/0000-0003-2677-3434)
- Toyoto Sato (ORCID: https://orcid.org/0000-0002-0527-1235)
- Ikutaro Hamada (ORCID: https://orcid.org/0000-0001-5112-2452)
- Seong‐Hoon Jang (ORCID: https://orcid.org/0000-0001-6026-636X)
- Linda Zhang (ORCID: https://orcid.org/0000-0003-3841-544X)
- Thomas Gennett
- Jianfeng Mao (ORCID: https://orcid.org/0000-0002-4787-4261)
- Rana Mohtadi (ORCID: https://orcid.org/0000-0002-1203-3809)
- Stefano Deledda (ORCID: https://orcid.org/0000-0002-4694-1012)
- Kentaro Kutsukake (ORCID: https://orcid.org/0000-0001-7878-347X)
- Eun Seon Cho (ORCID: https://orcid.org/0000-0001-9428-1269)
- Martin Dornheim (ORCID: https://orcid.org/0000-0001-8491-435X)
- Hung Ba Tran (ORCID: https://orcid.org/0000-0001-5508-3956)
- Andreas Borgschulte (ORCID: https://orcid.org/0000-0001-6250-4667)
- Y. Filinchuk
- Ryuhei Sato (ORCID: https://orcid.org/0000-0002-5503-0982)
- Hu S
- Bjørn C. Hauback
- Astrid Pundt
- Torben R. Jensen
- Eric Jianfeng Cheng
- Yusuke Ohashi
- Zhigang Hu
- Mingxia Gao
- Chuanyu Liu
- Lixin Chen
- Anibal Ramirez-Cuesta
- Hiroshi Yabu
- Xi Lin (ORCID: https://orcid.org/0000-0003-2526-5163)
- Michael Felderhoff
- Jason Hattrick-Simpers
- Takahiro Kondo
- Jiayu Peng
- Hyunchul Oh
- Weijie Yang
- Piao Ma (ORCID: https://orcid.org/0000-0002-4357-187X)
- Jianxin Zou
- Mark Allendorf
- Michael Hirscher
- Aloysius Soon
- Nongnuch Artrith
- Xue Jia
- Zhao Ding
- Baohua Jia
- Zhenhao Zhou
- Xiao-Yan Li
- Hiroyuki Saitoh
- Zaiping Guo
- Ang Cao
- Di Zhang (ORCID: https://orcid.org/0000-0002-4229-9755)
- Yiwen Yao
- Hyoung Seop Kim (ORCID: https://orcid.org/0000-0002-3155-583X)
- Shin-ichi Orimo
- Tongliang Liu
- Yusuke Hashimoto
- Ping Chen
- Benjamin W. J. Chen
- Chris Wolverton
- Pengfei Ou
- Panpan Zhou
- Xuebin Yu
- Chenghua Sun
- Hao Li
Institutions
- Karlsruhe Institute of Technology (DE)
- Pohang University of Science and Technology (KR)
- Oak Ridge National Laboratory (US)
- Toyota Motor Corporation (Switzerland) (CH)
- The University of Sydney (AU)
- University of Nottingham (GB)
- University of Crete (GR)
- University of Tsukuba (JP)
- North China Electric Power University (CN)
- Korea Advanced Institute of Science and Technology (KR)
- Chongqing University (CN)
- National University of Singapore (SG)
- Colorado School of Mines (US)
- City University of Hong Kong (HK)
- Shanghai Jiao Tong University (CN)
- University of Toronto (CA)
- Utrecht University (NL)
- Yonsei University (KR)
- Tohoku University (JP)
- Aarhus University (DK)
- Washington University in St. Louis (US)
- Curtin University (AU)
- University of Cambridge (GB)
- Fudan University (CN)
- Institute of High Performance Computing (SG)
- Chinese Academy of Engineering (CN)
- Max Planck Institute for Solid State Research (DE)
- Max-Planck-Institut für Kohlenforschung (DE)
- Tohoku University Hospital (JP)
- Northwestern University (PH)
- University of Tokyo Hospital (JP)
- National Institutes for Quantum Science and Technology (JP)
- Department of Medical Sciences (BY)
- Museum of Japanese Art Yamato Bunkakan (JP)
- Institut für Energie- und Umweltforschung Heidelberg (DE)
- Hiden Analytical (United Kingdom) (GB)
- Universitas Islam Negeri Palangka Raya (ID)
- Suzhou Industrial Park Institute of Services Outsourcing (CN)
- University of Chinese Academy of Sciences (CN)
- Ulsan National Institute of Science and Technology (KR)
- University of Turin (IT)
- The University of Adelaide (AU)
- Swinburne University of Technology (AU)
- Nagoya University (JP)
- University at Buffalo, State University of New York (US)
- Carrier (United States) (US)
- The University of Tokyo (JP)
- Zhejiang University (CN)
- RMIT University (AU)
- The University of Osaka (JP)
Publication Details
- Journal
- ACS Energy Letters
- Published
- 2026-08-14
- DOI
- https://doi.org/10.1021/acsenergylett.6c01856
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Research Foundation of Korea
- Ministero dell'Università e della Ricerca
- Japan Science and Technology Agency