Work

Hyperparameter Optimization for Atomic Cluster Expansion Potentials

Year: 2024

Type: article

Abstract: High Resolution Image Download MS PowerPoint Slide Machine learning-based interatomic potentials enable accurate materials simulations on extended time- and length scales. ML potentials based on the atomic cluster expansion (ACE) framework have recently shown promising performance for this purpose. Here, we describe a largely automated computational approach to optimizing hyperparameters for ACE potential models. We extend our openly available Python package, XPOT, to include an interface for ACE fitting, and discuss the optimization of the functional form and complexity of these models based on systematic sweeps across relevant hyperparameters. We showcase the usefulness of the approach for two example systems: the covalent network of silicon and the phase-change material Sb 2 Te 3 . More generally, our work emphasizes the importance of hyperparameter selection in the development of advanced ML potential models.

Source: Journal of Chemical Theory and Computation

DOI: 10.1021/acs.jctc.4c01012

Authors: Daniel F. Thomas du Toit, Yuxing Zhou, Volker L. Deringer

Institution: University of Oxford

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $4,500

Funders: UK Research and Innovation, University of Oxford, China Scholarship Council, Engineering and Physical Sciences Research Council