Benchmarking Machine Learning Potentials for Crystal Structure Relaxation

Kowen Woo, Prashant Govindarajan, Sarath Chandar

Additional Submission Instructions: For the camera-ready version, please include the author names and affiliations, funding disclosures, and acknowledgements.

Track: Track 1: Original Research/Position/Education/Attention Track

Keywords: ML potentials, crystals, structure relaxation, benchmark

TL;DR: We benchmark ML interatomic potentials on RL-generated crystals for reliable structure relaxation.

Abstract: High-throughput materials discovery workflows require rapid and accurate relaxation of crystal structures to identify thermodynamically stable phases among thousands to millions of candidate structures. We introduce a supplementary benchmark that evaluates state-of-the-art MLIPs and a one-shot relaxation model on structure relaxation with crystals generated via a reinforcement learning pipeline. We compare energy lowering and average maximum force computed via DFT, as well as relaxation runtime. We also contrast direct force-prediction strategies against conservative energy-differentiation approaches to determine which paradigm delivers superior relaxation performance. Our results indicate that there is a disconnect between MLIP energy prediction and force convergence in relaxation; however, we note that this is an ongoing study and further analysis is required.

Submission Number: 442