Accelerating crystal structure search through active learning with neural networks for rapid relaxations

Abstract

Global optimization of crystal compositions is a significant yet computationally intensive method to identify stable structures within chemical space. The specific physical properties linked to a three-dimensional atomic arrangement make this an essential task in the development of new materials. We present a method that efficiently uses active learning of neural network force fields for structure relaxation, minimizing the required number of steps in the process. This is achieved by neural network force fields equipped with uncertainty estimation, which iteratively guide a pool of randomly generated candidates toward their respective local minima. Using this approach, we are able to effectively identify the most promising candidates for further evaluation using density functional theory (DFT). Our method not only reliably reduces computational costs by up to two orders of magnitude across the benchmark systems Si₁₆, Na₈Cl₈, Ga₈As₈ and Al₄O₆ but also excels in finding the most stable minimum for the unseen, more complex systems Si₄₆ and Al₁₆O₂₄. Moreover, we demonstrate at the example of Si₁₆ that our method can find multiple relevant local minima while only adding minor computational effort.