Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction

Abstract

Machine learning interatomic potentials (MLIPs) have become increasingly effective at approximating quantum mechanical calculations at a fraction of the computational cost. However, lower errors on held out test sets do not always translate to improved results on downstream physical property prediction tasks. In this paper, we propose testing MLIPs on their practical ability to conserve energy during molecular dynamic simulations. If passed, improved correlations are found between test errors and their performance on physical property prediction tasks. We identify choices which may lead to models failing this test, and use these observations to improve upon highly-expressive models. The resulting model, eSEN, provides state-of-the-art results on a range of physical property prediction tasks, including materials stability prediction, thermal conductivity prediction, and phonon calculations.

20 pages, 14 figures, 6 tables

Cited by in corpus (6)

• Machine Learning Potentials for Alloys: A Detailed Workflow to Predict Phase Diagrams and Benchmark Accuracy
• A Comprehensive Assessment and Benchmark Study of Large Atomistic Foundation Models for Phonons
• Crystal structure prediction with host-guided inpainting generation and foundation potentials
• MC3D: The Materials Cloud computational database of experimentally known stoichiometric inorganics
• Locating Ab Initio Transition States via Approximate Geodesics on Machine Learned Potential Energy Surfaces
• Active Δ-learning with universal potentials for global structure optimization