Evidential Deep Learning for Interatomic Potentials

TL;DR

This paper introduces evidential deep learning for interatomic potentials (eIP), providing reliable uncertainty quantification in molecular simulations without significant computational costs or accuracy loss.

Contribution

The work presents a physics-inspired evidential deep learning approach for interatomic potentials that outperforms existing uncertainty quantification methods in efficiency and accuracy.

Findings

eIP offers reliable uncertainty estimates without high computational costs

eIP outperforms other UQ methods across multiple datasets

eIP enables exploration of diverse atomic configurations

Abstract

Machine learning interatomic potentials (MLIPs) have been widely used to facilitate large-scale molecular simulations with accuracy comparable to ab initio methods. In practice, MLIP-based molecular simulations often encounter the issue of collapse due to reduced prediction accuracy for out-of-distribution (OOD) data. Addressing this issue requires enriching the training dataset through active learning, where uncertainty serves as a critical indicator for identifying and collecting OOD data. However, existing uncertainty quantification (UQ) methods tend to involve either expensive computations or compromise prediction accuracy. In this work, we introduce evidential deep learning for interatomic potentials (eIP) with a physics-inspired design. Our experiments indicate that eIP provides reliable UQ results without significant computational overhead or decreased prediction accuracy, consistently outperforming other UQ methods across a variety of datasets. Furthermore, we demonstrate the applications of eIP in exploring diverse atomic configurations, using examples including water and universal potentials. These results highlight the potential of eIP as a robust and efficient alternative for UQ in molecular simulations.