Bayesian optimization of metastable nickel formation during the spontaneous crystallization under extreme conditions

Abstract

Spontaneous crystallization of metals under extreme conditions is a unique phenomenon occurring under far-from-equilibrium conditions that could enable the development of revolutionary and disruptive metastable metals with unusual properties. In this work, the formation of the hexagonal close-packed nickel (hcp-Ni) metastable phase during spontaneous crystallization is studied using non-equilibrium molecular dynamics (MD) simulations, with the goal of maximizing the fraction of this metastable phase in the final state. We employ Bayesian optimization (BO) with the Gaussian processes (GPs) regression as the surrogate model to maximize the hcp-Ni phase fraction, where temperature and pressure are control variables. MD simulations provide data for training the GP model, which is then used with BO to predict the next simulation condition. Such BO-guided active learning leads to a maximum hcp-Ni fraction of 43.38% in the final crystallized phase within 40 iterations when a face-centered cubic crystallite serves as the seed for crystallization from the amorphous phase. When an hcp seed is used, the maximum hcp-Ni fraction in the final crystal increases to 58.25% with 13 iterations. This study shows the promise of using BO to identify the process conditions that can maximize the rare phases. This method can also be generally applicable to process optimization to achieve target material properties.