Active Δ-learning with universal potentials for global structure optimization

Joe Pitfield

doi:10.1039/D5CP04302F

Active Δ-learning with universal potentials for global structure optimization

2025-12-01

0

PRE

AI

J

Joe Pitfield

M

Mads-Peter Verner Christiansen

B

Bjørk Hammer

DOI：10.1039/D5CP04302F

Original

Original request for help

Save

Abstract

En 中文

Universal machine learning interatomic potentials (uMLIPs) have recently been formulated and shown to generalize well. When applied out-of-sample; further data collection for improvement of the uMLIPs may; however; be required. In this work we demonstrate that; whenever the envisaged use of the MLIPs is global optimization; the data acquisition can follow an active learning scheme in which a gradually updated uMLIP directs the finding of new structures; which are subsequently evaluated at the density functional theory (DFT) level. In the scheme; we augment foundation models using a Δ-model based on these new data using local SOAP-descriptors; Gaussian kernels; and a sparse Gaussian Process Regression model. We compare the efficacy of the approach with different global optimization algorithms; Random Structure Search; Basin Hopping; a Bayesian approach with competitive candidates (GOFEE); and a replica exchange formulation (REX). We further compare several foundation models; CHGNet; MACE-MP0; and MACE-MPA. The test systems are silver-sulfur clusters and sulfur-induced surface reconstructions on Ag(111) and Ag(100). Judged by the fidelity of identifying global minima; active learning with GPR-based Δ-models appears to be a robust approach. Judged by the total CPU time spent; the REX approach stands out as being the most efficient.

Active Δ-learning with universal potentials for global structure optimization

Abstract

Journal

Organization