EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Machine Learning Interatomic Potentials for Energy Materials: Architectures, Training Strategies, and Applications

In Kee Park, Saeed Pourasad, Jinhong Mun, Arunkumar Chitteth Rajan, Tae Hyeon Park, Anand Rohit, Mohammad Zafari, Tan‐Lien Pham, Eunjae Jung, Bonseung Koo, Miran Ha, Gi Beom Sim und 8 weitere

Advanced Energy Materials · 2026-10 · 16 (39)

DOI: 10.1002/aenm.71046 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Energy Materials, online erschienen am 12.05.2026. Verfasst von In Kee Park und 19 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 303 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Research Foundation of Korea.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Machine learning interatomic potentials (MLIPs) provide a practical route to bridge first‐principles accuracy with the spatiotemporal scales required for modeling complex energy materials. By learning potential‐energy surfaces from density functional theory (DFT) data, MLIPs enable atomistic simulations up to 10 4 –10 6 atoms over nanosecond timescales, thereby extending access to phenomena inaccessible to ab initio molecular dynamics. This review presents a phenomenon‐oriented synthesis of MLIP development, spanning descriptor‐based models, Gaussian process frameworks with uncertainty quantification, equivariant graph neural networks, and foundation models trained on large‐scale datasets. We assess how architectural choices, training strategies (including active learning and multi‐fidelity approaches), and dataset design influence accuracy, transferability, and computational efficiency across representative energy systems. Applications in solid‐state electrolytes, battery electrodes, electrocatalysts, perovskite photovoltaics, and high‐entropy materials are discussed with both performance metrics and methodological rationale. While MLIPs capture qualitative trends and relative property variations, absolute predictions remain sensitive to DFT functional choices, dataset representativeness, and treatment of long‐range interactions. We address a structured validation framework linking model fidelity to experimentally relevant observables and system complexity. Also, we outline emerging directions including generative inverse design, autonomous discovery workflows, and foundation‐model fine‐tuning, highlighting opportunities and limitations for predictive deployment in energy materials research.

Förderung

  • National Research Foundation of Korea

Zitieren

APA

Park, I. K., Pourasad, S., Mun, J., Rajan, A. C., Park, T. H., Rohit, A., Zafari, M., Pham, T., Jung, E., Koo, B., Ha, M., Sim, G. B., Park, H. G., Choi, W. W., Jo, K., Willow, S. Y., Yang, D. C., Myung, C. W., Lee, G., & Kim, K. S. (2026). Machine Learning Interatomic Potentials for Energy Materials: Architectures, Training Strategies, and Applications. Advanced Energy Materials, 16(39). https://doi.org/10.1002/aenm.71046

Vancouver

Park IK, Pourasad S, Mun J, Rajan AC, Park TH, Rohit A, et al. Machine Learning Interatomic Potentials for Energy Materials: Architectures, Training Strategies, and Applications. Advanced Energy Materials. 2026;16(39). doi:10.1002/aenm.71046

BibTeX
@article{Park2026,
  author = {Park, In Kee and Pourasad, Saeed and Mun, Jinhong and Rajan, Arunkumar Chitteth and Park, Tae Hyeon and Rohit, Anand and Zafari, Mohammad and Pham, Tan‐Lien and Jung, Eunjae and Koo, Bonseung and Ha, Miran and Sim, Gi Beom and Park, Hyun Gyu and Choi, Won Woong and Jo, Kwanghyeon and Willow, Soohaeng Yoo and Yang, David ChangMo and Myung, Chang Woo and Lee, Geunsik and Kim, Kwang S.},
  title = {Machine Learning Interatomic Potentials for Energy Materials: Architectures, Training Strategies, and Applications},
  journal = {Advanced Energy Materials},
  year = {2026},
  volume = {16},
  number = {39},
  doi = {10.1002/aenm.71046}
}
Kostenlos starten →