An automated framework for exploring and learning potential-energy surfaces

YB Liu and JD Morrow and C Ertural and NL Fragapane and JLA Gardner and AA Naik and YX Zhou and J George and VL Deringer, NATURE COMMUNICATIONS, 16, 7666 (2025).

DOI: 10.1038/s41467-025-62510-6

Machine learning has become ubiquitous in materials modelling and now routinely enables large-scale atomistic simulations with quantum- mechanical accuracy. However, developing machine-learned interatomic potentials requires high-quality training data, and the manual generation and curation of such data can be a major bottleneck. Here, we introduce an automated framework for the exploration and fitting of potential-energy surfaces, implemented in an openly available software package that we call autoplex ('automatic potential-landscape explorer'). We discuss design choices, particularly the interoperability with existing software architectures, and the ability for the end user to easily use the computational workflows provided. We show wide-ranging capability demonstrations: for the titanium-oxygen system, SiO2, crystalline and liquid water, as well as phase-change memory materials. More generally, our study illustrates how automation can speed up atomistic machine learning in computational materials science.

Return to Publications page