Breaking Bottlenecks in Solid Electrolyte Discovery With Large Artificial Intelligence Models
Solid electrolytes (SEs) are central to next-generation metal batteries, yet their discovery remains constrained by fragmented data, limited transferability of simulations, and slow experimental iteration. Unlike catalysis, where surface reactivity dominates, SEs require simultaneous optimization of bulk ion transport, defect chemistry, mechanical integrity, and interfacial stability. Here, we outline a framework for autonomous SE discovery enabled by large artificial intelligence (AI) models, including machine learning interatomic potentials (MLIPs) and large language models (LLMs). We discuss the evolution from static materials databases to dynamic, self-updating knowledge systems, the role of MLIPs in bridging density functional theory (DFT) and long-timescale ion migration, and the emergence of LLMs as engines for literature mining, hypothesis generation, and scientific reasoning. We further describe a closed-loop architecture integrating AI-driven candidate design, multiscale simulation, uncertainty-aware selection, and experimental validation. Such systems shift SE research from intuition-guided exploration to data-informed, self-improving cycles. We conclude by highlighting challenges in data standardization, interfacial complexity, and reproducibility, and we propose design principles for building autonomous laboratories for solid-state battery materials.
Authors
- Aloysius Soon (ORCID: https://orcid.org/0000-0002-6273-9324)
- Hiroshi Kakinuma (ORCID: https://orcid.org/0000-0001-6944-0803)
- J Lu (ORCID: https://orcid.org/0000-0002-6121-5529)
- Senentxu Lanceros-Méndez (ORCID: https://orcid.org/0000-0001-6791-7620)
- Pengfei Ou (ORCID: https://orcid.org/0000-0002-3630-0385)
- Vlad Badilita (ORCID: https://orcid.org/0000-0002-7956-345X)
- Eric Jianfeng Cheng (ORCID: https://orcid.org/0000-0003-0904-802X)
- Carlos Miguel Costa (ORCID: https://orcid.org/0000-0001-8453-4031)
- Jie Peng (ORCID: https://orcid.org/0000-0002-9811-6831)
- Chuanyu Liu
- Jie Zhao (ORCID: https://orcid.org/0000-0003-4543-3494)
- Shin-ichi ORIMO
- Di Zhang
- Piao Ma (ORCID: https://orcid.org/0000-0002-4357-187X)
- Teguh Ariyanto (ORCID: https://orcid.org/0000-0002-9454-9541)
- Min Hong
- Weibo Gong
- Melissa Jane Meadowcroft
- Ying Li
- Sudaryanto
- Zhiquan Zeng
- Chenyao Ma
- Qian Wang
- Surendra Martha
- Hao Li
Institutions
- Karlsruhe Institute of Technology (DE)
- Universitas Gadjah Mada (ID)
- National University of Singapore (SG)
- Yonsei University (KR)
- Tohoku University (JP)
- Fudan University (CN)
- Basque Center for Materials, Applications and Nanostructures (ES)
- Kerntechnische Entsorgung Karlsruhe (Germany) (DE)
- Suzhou Industrial Park Institute of Services Outsourcing (CN)
- Institute for Materials Research, Tohoku University
- Centro de Física das Universidades do Minho e do Porto (PT)
- University at Buffalo, State University of New York (US)
- Indian Institute of Technology Hyderabad (IN)
- Zhejiang University (CN)
- London School of Economics and Political Science (GB)
- University of Minho (PT)
Publication Details
- Journal
- Advanced Materials
- Published
- 2026-10-13
- DOI
- https://doi.org/10.1002/adma.75354
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Japan Society for the Promotion of Science
- Tohoku University Center for Gender Equality Promotion
- Institute for Materials Research, Tohoku University
- Division of Materials Research
- Strategic International Collaborative Research Program