Machine learning potentials(MLPs)have become an indispensable tool in large-scale atomistic simulations.However,mostMLPs today are trained on data computed using relatively cheap density functional theory(DFT)methods ...Machine learning potentials(MLPs)have become an indispensable tool in large-scale atomistic simulations.However,mostMLPs today are trained on data computed using relatively cheap density functional theory(DFT)methods such as the Perdew-Burke-Ernzerhof(PBE)generalized gradient approximation(GGA)functional.While meta-GGAs such as the strongly constrained and appropriately normed(SCAN)functional have been shown to yield significantly improved descriptions of atomic interactions for diversely bonded systems,their higher computational cost remains an impediment to their use in MLP development.In this work,we outline a data-efficient multi-fidelity approach to constructing Materials 3-body Graph Network(M3GNet)interatomic potentials that integrate different levels of theory within a singlemodel.Using silicon and water as examples,we show that a multi-fidelity M3GNet model trained on a combined dataset of low-fidelityGGAcalculations with 10%of high-fidelity SCAN calculations can achieve accuracies comparable to a single-fidelity M3GNet model trained on a dataset comprising 8×the number of SCAN calculations.This work provides a pathway to the development of high-fidelity MLPs in a cost-effective manner by leveraging existing low-fidelity datasets.展开更多
基金ntellectually led by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, Materials Sciences and Engineering Division under contract No. DE-AC02-05-CH11231 (Materials Project program KC23MP)This research used resources of the National Energy Research Scientific Computing Center (NERSC), a Department of Energy Office of Science User Facility using NERSC award DOE-ERCAP0026371the support of the Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship, a Schmidt Futures program.
文摘Machine learning potentials(MLPs)have become an indispensable tool in large-scale atomistic simulations.However,mostMLPs today are trained on data computed using relatively cheap density functional theory(DFT)methods such as the Perdew-Burke-Ernzerhof(PBE)generalized gradient approximation(GGA)functional.While meta-GGAs such as the strongly constrained and appropriately normed(SCAN)functional have been shown to yield significantly improved descriptions of atomic interactions for diversely bonded systems,their higher computational cost remains an impediment to their use in MLP development.In this work,we outline a data-efficient multi-fidelity approach to constructing Materials 3-body Graph Network(M3GNet)interatomic potentials that integrate different levels of theory within a singlemodel.Using silicon and water as examples,we show that a multi-fidelity M3GNet model trained on a combined dataset of low-fidelityGGAcalculations with 10%of high-fidelity SCAN calculations can achieve accuracies comparable to a single-fidelity M3GNet model trained on a dataset comprising 8×the number of SCAN calculations.This work provides a pathway to the development of high-fidelity MLPs in a cost-effective manner by leveraging existing low-fidelity datasets.
