ICHOR: a modern pipeline for producing Gaussian process regression models for atomistic simulations

Abstract

Current practical use of machine learning is more involved than model architecture and the optimisation technique itself. It is very important that the modern machine learning method is supported with a robust set of tools for the creation and manipulation of data sets. ICHOR is one such tool designed for the purpose of creating fast and accurate atomistic Gaussian process regression (GPR) models through the use of active learning. ICHOR operates in the context of FFLUX, a fully polarisable force field based on the energies and multipole moments of quantum topological atoms. ICHOR interacts with the in-house GPR program FEREBUS for training, and with DL_FFLUX (derived from DL_POLY) for geometry optimisation and molecular simulation. ICHOR utilises the latest technologies in HPC cluster management to produce GPR models reliably at scale.