Navigating chemical design spaces for metal-ion batteries via machine-learning-guided phase-field simulations

TL;DR

This paper introduces a machine-learning-guided phase-field simulation framework to optimize chemical parameters in metal-ion batteries, aiming to suppress dendrite growth and improve fast-charging performance.

Contribution

It presents a scalable Bayesian optimization approach for phase-field models, identifying key parameters like interfacial mobility to enhance battery safety and charging speed.

Findings

Optimal interfacial mobility increases dendrite suppression

Framework achieves high sample efficiency in parameter exploration

Simulations confirm improved charging performance

Abstract

Metal anodes provide the highest energy density in batteries. However, they still suffer from electrode/electrolyte interface side reactions and dendrite growth, especially under fast-charging conditions. In this paper, we consider a phase-field model of electrodeposition in metal-anode batteries and provide a scalable, versatile framework for optimizing its chemical parameters. Our approach is based on Bayesian optimization and explores the parameter space with a high sample efficiency and a low computation complexity. We use this framework to find the optimal cell for suppressing dendrite growth and accelerating charging speed under constant voltage. We identify interfacial mobility as a key parameter, which should be maximized to inhibit dendrites without compromising the charging speed. The results are verified using extended simulations of dendrite evolution in charging half cells with lithium-metal anodes.