Uncertainty quantification for misspecified machine learned interatomic potentials

Abstract The use of high-dimensional regression techniques from machine learning has significantly improved the quantitative accuracy of interatomic potentials. Atomic simulations can now plausibly target quantitative predictions in a variety of settings, which has brought renewed interest in robust...

Full description

Saved in:
Bibliographic Details
Main Authors: Danny Perez, Aparna P. A. Subramanyam, Ivan Maliyov, Thomas D. Swinburne
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01758-4
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract The use of high-dimensional regression techniques from machine learning has significantly improved the quantitative accuracy of interatomic potentials. Atomic simulations can now plausibly target quantitative predictions in a variety of settings, which has brought renewed interest in robust means to quantify uncertainties. In many practical settings where model complexity is constrained (e.g., due to performance considerations), misspecification — the inability of any one choice of model parameters to exactly match all training data — is a key contributor to errors that is often disregarded. Here, we employ a recent misspecification-aware regression technique to quantify parameter uncertainties, which is then propagated to a broad range of phase and defect properties in tungsten. The propagation is performed through both brute-force resampling and implicit Taylor expansion. The propagated misspecification uncertainties robustly quantify and bound errors on a broad range of material properties. We demonstrate application to recent foundational machine learning interatomic potentials, accurately predicting and bounding errors in MACE-MPA-0 energy predictions across the diverse materials project database.
ISSN:2057-3960