Modelling silica using MACE-MP machine learnt interatomic potentials
Jamal Abdul Nasir, Jingcheng Guan, W.S.S. Jee, Scott M. Woodley, Alexey A. Sokol, C. Richard A. Catlow, Alin M. Elena
Abstract
species, in agreement with prior DFT and experimental observations. Thus, we assess and demonstrate the suitability of off-the-shelf machine-learned foundation models, based on MACE-MP framework, for modelling silica materials of high importance from earth sciences to electronics and catalysis.
Topics & Concepts
MaceNanotechnologyMaterials scienceComputer scienceMedicineConventional PCIMyocardial infarctionPsychiatryNeural Networks and Applications