An automated framework for exploring and learning potential-energy surfaces
Yuanbin Liu, Joe D. Morrow, Christina Ertural, Natascia L. Fragapane, John L. A. Gardner, Aakash Ashok Naik, Yuxing Zhou, Janine George, Volker L. Deringer
Abstract
Abstract 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 (‘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, SiO 2 , 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.