Machine learning assisted canonical sampling (MLACS)

TL;DR

MLACS is a Python package that accelerates ab initio material property calculations at finite temperatures by iteratively training machine learning interatomic potentials, enabling efficient simulations with near-DFT accuracy.

Contribution

Introduces MLACS, a self-consistent variational method that combines active learning and MLIP to significantly reduce computational costs in ab initio simulations.

Findings

MLACS achieves near-DFT accuracy with reduced computational time.

The package seamlessly integrates DFT, MLIP, and MD tools.

Demonstrates effectiveness in sampling, free energy calculations, and geometry optimization.

Abstract

The acceleration of material property calculations while maintaining ab initio accuracy (1 meV/atom) is one of the major challenges in computational physics. In this paper, we introduce a Python package enhancing the computation of (finite temperature) material properties at the ab initio level using machine learning interatomic potentials (MLIP). The Machine-Learning Assisted Canonical Sampling (MLACS) method, grounded in a self-consistent variational approach, iteratively trains a MLIP using an active learning strategy in order to significantly reduce the computational cost of ab initio simulations. MLACS offers a modular and user-friendly interface that seamlessly integrates Density Functional Theory (DFT) codes, MLIP potentials, and molecular dynamics packages, enabling a wide range of applications, while maintaining a near-DFT accuracy. These include sampling the canonical ensemble of a system, performing free energy calculations, transition path sampling, and geometry optimization, all by utilizing surrogate MLIP potentials, in place of ab initio calculations. This paper provides a comprehensive overview of the theoretical foundations and implementation of the MLACS method. We also demonstrate its accuracy and efficiency through various examples, showcasing the capabilities of the MLACS package.