EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fine-tuning universal machine-learned interatomic potentials: A Tutorial on methods and applications

Xiaoqing Liu, Kehan Zeng, Zedong Luo, Yangshuai Wang, Teng Zhao, Zhenli Xu

Journal of Applied Physics · 28.01.2026 · 139 (4)

DOI: 10.1063/5.0299305 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Physics, online erschienen am 26.01.2026. Verfasst von Xiaoqing Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 141 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality, Natural Science Foundation of Chongqing.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Universal machine-learned interatomic potentials (U-MLIPs) have demonstrated broad applicability across diverse atomistic systems but often require fine-tuning to achieve task-specific accuracy. While the number of available U-MLIPs and their fine-tuning applications are rapidly expanding, there remains a lack of systematic guidance on how to effectively fine-tune these models. This Tutorial provides a comprehensive, step-by-step guide to fine-tuning U-MLIPs for computational materials modeling. Using the recently released MACE-MP-0 as a representative foundation model, we illustrate the full workflow of data set preparation, hyperparameter selection, model training, and validation. Beyond methodological guidance, we conduct systematic case studies on solid-state electrolytes, stacking fault defects in metals, semiconductors, solid–liquid interfacial interactions in low-dimensional systems, and more complicated heterointerfaces. These examples demonstrate that fine-tuning substantially improves predictive accuracy while maintaining affordable computational cost, accelerates training convergence, enhances out-of-distribution generalization, and achieves superior data efficiency. Remarkably, fine-tuned foundation models can even capture aspects of long-range physics without explicit corrections. Together, these results highlight that fine-tuning not only provides a practical recipe for applying U-MLIPs but also offers new insights into their physical fidelity and potential for advancing large-scale atomistic simulations. To support practical applications, we include code examples that enable researchers, particularly those new to the field, to efficiently incorporate fine-tuned U-MLIPs into their workflows.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Commission of Shanghai Municipality
  • Natural Science Foundation of Chongqing
  • National Supercomputing Center

Zitieren

APA

Liu, X., Zeng, K., Luo, Z., Wang, Y., Zhao, T., & Xu, Z. (2026). Fine-tuning universal machine-learned interatomic potentials: A Tutorial on methods and applications. Journal of Applied Physics, 139(4). https://doi.org/10.1063/5.0299305

Vancouver

Liu X, Zeng K, Luo Z, Wang Y, Zhao T, Xu Z. Fine-tuning universal machine-learned interatomic potentials: A Tutorial on methods and applications. Journal of Applied Physics. 2026;139(4). doi:10.1063/5.0299305

BibTeX
@article{Liu2026,
  author = {Liu, Xiaoqing and Zeng, Kehan and Luo, Zedong and Wang, Yangshuai and Zhao, Teng and Xu, Zhenli},
  title = {Fine-tuning universal machine-learned interatomic potentials: A Tutorial on methods and applications},
  journal = {Journal of Applied Physics},
  year = {2026},
  volume = {139},
  number = {4},
  doi = {10.1063/5.0299305}
}
Kostenlos starten →