Best of Both Worlds: Enforcing Detailed Balance in Machine Learning Models of Transition Rates

TL;DR

This paper introduces physics-informed machine learning models that enforce detailed balance in transition rate predictions, improving accuracy and efficiency in simulating microstructural evolution in complex materials.

Contribution

The study presents a novel ML architecture that exactly enforces detailed balance, enhancing prediction accuracy without additional computational cost.

Findings

ML models with enforced detailed balance outperform unconstrained models.

Physics-informed architectures accurately predict transition barriers.

Improved simulation of vacancy diffusion in alloys.

Abstract

The slow microstructural evolution of materials often plays a key role in determining material properties. When the unit steps of the evolution process are slow, direct simulation approaches such as molecular dynamics become prohibitive and Kinetic Monte-Carlo (kMC) algorithms, where the state-to-state evolution of the system is represented in terms of a continuous-time Markov chain, are instead frequently relied upon to efficiently predict long-time evolution. The accuracy of kMC simulations however relies on the complete and accurate knowledge of reaction pathways and corresponding kinetics. This requirement becomes extremely stringent in complex systems such as concentrated alloys where the astronomical number of local atomic configurations makes the a priori tabulation of all possible transitions impractical. Machine learning models of transition kinetics have been used to mitigate this problem by enabling the efficient on-the-fly prediction of kinetic parameters. In this study, we show how physics-informed ML architectures can exactly enforce the detailed balance condition, by construction. Using the diffusion of a vacancy in a concentrated alloy as an example, we show that such ML architectures also exhibit superior performance in terms of prediction accuracy, demonstrating that the imposition of physical constraints can facilitate the accurate learning of barriers at no increase in computational cost.