The optimization of atomic structures plays a pivotal role in understanding and designing materials with desired properties. However, conventional methods often struggle with the formidable task of navigating the vast potential energy surface, especially in high-dimensional spaces with numerous local minima. Recent advancements in machine learning-driven surrogate models offer a promising avenue for alleviating this computational burden. In this study, we propose a novel approach that combines the strengths of universal machine learning potentials with a Bayesian approach of the GOFEE/BEACON framework. By leveraging the comprehensive chemical knowledge encoded in pretrained universal machine learning potentials as a prior estimate of energy and forces, we enable the Gaussian process to focus solely on capturing the intricate nuances of the potential energy surface. We demonstrate the efficacy of our approach through comparative analyses across diverse systems, including periodic bulk materials, surface structures, and a cluster.

翻译：原子结构优化在理解和设计具有特定性质的材料中起着关键作用。然而，传统方法在探索广阔的势能面时常常面临巨大挑战，尤其是在存在大量局部极小值的高维空间中。近期机器学习驱动的代理模型进展为减轻这一计算负担提供了有前景的途径。本研究提出一种创新方法，将通用机器学习势的优势与GOFEE/BEACON框架的贝叶斯方法相结合。通过利用预训练通用机器学习势中所编码的全面化学知识作为能量和力的先验估计，我们使高斯过程能够专注于捕捉势能面的复杂细微特征。我们通过对多种体系（包括周期性块体材料、表面结构及团簇）的对比分析，证明了本方法的有效性。