2020/01/31 by Howard Yanxon, David Zagaceta, Brandon C. Wood +1 · 16 citations
Chemistry · Materials Science · Physics and Astronomy · #Advanced Physical and Chemical Molecular Interactions #Artificial neural network #Bispectrum #Crystalline silicon #Energy (signal processing) #Force Microscopy Techniques and Applications #Machine Learning in Materials Science #Pattern recognition (psychology) #Set (abstract data type) #Silicon #Training set #physics.chem-ph #physics.comp-ph
paper · pdf · doi:10.1063/5.0014677
published in The Journal of Chemical Physics 153(5), 054118 (American Institute of Physics)
arxiv created 2020/05/21 · openalex publication_date 2020/08/06 · openalex created_date 2020/08/10 · arxiv updated 2020/08/26 · openalex updated_date 2026/08/05
In this article, we present a systematic study on developing machine learning force fields (MLFFs) for crystalline silicon. While the main-stream approach of fitting a MLFF is to use a small and localized training set from molecular dynamics simulations, it is unlikely to cover the global features of the potential energy surface. To remedy this issue, we used randomly generated symmetrical crystal structures to train a more general Si-MLFF. Furthermore, we performed substantial benchmarks among different choices of material descriptors and regression techniques on two different sets of silicon data. Our results show that neural network potential fitting with bispectrum coefficients as descriptors is a feasible method for obtaining accurate and transferable MLFFs.