AI-driven design of multiprincipal element alloys for optimal water splitting

Abstract

Water splitting for hydrogen production is essential in advancing the hydrogen economy. Multiprincipal element alloys offer promising opportunities for optimizing this process, yet their vast compositional space and the presence of local minima pose significant challenges for experimental and AI-driven exploration. To overcome these challenges, an AI framework is developed by integrating Gaussian Process Regression with a configuration entropy–based acquisition function for screening and a design of experiments (DoE) for data-efficient overpotential mapping. Through Bayesian optimization across 16.2 million chemical compositions, this entropy-screened and DoE dataset–trained AI identifies Fe₁₂ Co₂₈Ni₃₃Mo₁₇Pd₅Pt₅ as the best composition for water splitting within its search space. The alloy exhibits ultralow overpotentials of 24 mV for hydrogen evolution and 204 mV for oxygen evolution at 10 mA·cm −2 with robust stability, surpassing state-of-the-art non-noble and noble metal electrocatalysts including Pt/C+IrO₂, Pt 35 Ru₆₅, and Ru–VO₂ —demonstrating remarkable performance beyond reach by contemporary experimental and AI frameworks.

Group Members

William A. Goddard III

Charles and Mary Ferkel Professor