Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction

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.

Molecular simulations guide the discovery of new batteries, catalysts, and numerious other critical fields. Machine learning interatomic potentials (MLIPs) are promising to accelerate these simulations, yet a model that looks great on standard benchmarks may not perform well in downstream tasks. We propose a practical quality check and design eSEN, a new MLIP that reliably delivers state‑of‑the‑art predictions for material stability, thermal conductivity, and atomic vibrations, accelerating the search for better materials.