Physically Interpretable Interatomic Potentials via Symbolic Regression and Reinforcement Learning

TL;DR

This paper introduces a novel method combining symbolic regression and reinforcement learning to develop interpretable interatomic potentials that outperform traditional fixed-form models in accuracy and physical insight.

Contribution

The authors present a new approach using symbolic regression with reinforcement learning to derive physically interpretable interatomic potentials directly from DFT data, surpassing fixed-form models.

Findings

SR-derived models accurately reproduce key material properties

Models outperform traditional Sutton-Chen EAM potentials

SR models effectively capture vibrational and structural dynamics

Abstract

The development of next-generation molecular simulation models requires moving beyond pre-defined functional forms toward machine learning (ML) techniques that directly capture multiscale physics. Here, we demonstrate such an approach using symbolic regression (SR) with equation learner networks and a reinforcement learning search engine to derive interpretable equations for interatomic interactions. Training data were generated through nested ensemble sampling with density functional theory (DFT) energetics, spanning crystalline to highly disordered states. The optimization of the learner network employed continuous-action Monte Carlo Tree Search (MCTS) combined with gradient descent, enabling efficient exploration of function space. For copper as a representative transition metal, an unconstrained search produced models that outperformed fixed-form Sutton-Chen EAM potentials. The SR-derived models (SR1 and SR2) reproduced key material properties - lattice constants, cohesive energies, equations of state, elastic constants, phonon dispersion, defect formation energies, surface/bulk energetics, and phase transformation with significantly improved accuracy. Furthermore, stringent melting simulations using two-phase solid-amorphous interfaces confirmed that SR models accurately capture the interplay of vibrational entropy, cohesive energy, and structural dynamics, surpassing SC-EAM in both qualitative and quantitative predictions. This highlights the potential of SR to deliver fast, accurate, flexible, and physically meaningful potentials, advancing predictive modeling across scales.