Hajibabaei Amir, Umer Muhammad, Anand Rohit, Ha Miran, Kim Kwang S
Center for Superfunctional Materials, Department of Chemistry, Ulsan National Institute of Science and Technology, 50 UNIST-gil, Ulsan 44919, Republic of Korea.
J Phys Condens Matter. 2022 Jun 28;34(34). doi: 10.1088/1361-648X/ac76ff.
We apply on-the-fly machine learning potentials (MLPs) using the sparse Gaussian process regression (SGPR) algorithm for fast optimization of atomic structures. Great acceleration is achieved even in the context of a single local optimization. Although for finding the exact local minimum, due to limited accuracy of MLPs, switching to another algorithm may be needed. For random gold clusters, the forces are reduced to ∼0.1 eV Åwithin less than ten first-principles (FP) calculations. Because of highly transferable MLPs, this algorithm is specially suitable for global optimization methods such as random or evolutionary structure searching or basin hopping. This is demonstrated by sequential optimization of random gold clusters for which, after only a few optimizations, FP calculations were rarely needed.
我们使用稀疏高斯过程回归（SGPR）算法应用实时机器学习势（MLP），以快速优化原子结构。即使在单个局部优化的情况下也能实现大幅加速。尽管为了找到精确的局部最小值，由于MLP的精度有限，可能需要切换到另一种算法。对于随机金团簇，在不到十次第一性原理（FP）计算内，力就降低到了约0.1 eV Å。由于MLP具有高度可转移性，该算法特别适用于全局优化方法，如随机或进化结构搜索或盆地跳跃。对随机金团簇的顺序优化证明了这一点，经过几次优化后，很少需要进行FP计算。
