Gaussian Approximation Potentials: theory, software implementation and application examples

TL;DR

This paper introduces Gaussian Approximation Potentials, a machine learning approach for modeling atomic-scale materials, detailing the theory, software, and recent improvements for efficient and scalable simulations.

Contribution

It presents a comprehensive overview of GAP theory, software implementation, and recent advancements like MPI parallelisation and descriptor compression.

Findings

MPI parallelisation enables large-scale computations

Descriptor compression improves scalability with chemical elements

The software facilitates fitting and applying interatomic potentials

Abstract

Gaussian Approximation Potentials are a class of Machine Learned Interatomic Potentials routinely used to model materials and molecular systems on the atomic scale. The software implementation provides the means for both fitting models using ab initio data and using the resulting potentials in atomic simulations. Details of the GAP theory, algorithms and software are presented, together with detailed usage examples to help new and existing users. We review some recent developments to the GAP framework, including MPI parallelisation of the fitting code enabling its use on thousands of CPU cores and compression of descriptors to eliminate the poor scaling with the number of different chemical elements.