Convergence acceleration in machine learning potentials for atomistic simulations
Dylan Bayerl, Christopher M. Andolina, Shyam Dwaraknath, Wissam A. Saidi
Abstract
Machine learning potentials (MLPs) for atomistic simulations have an enormous prospective impact on materials modeling, offering orders of magnitude speedup over density functional theory simulations without appreciably sacrificing accuracy of material property prediction.
Topics & Concepts
SpeedupConvergence (economics)AccelerationProperty (philosophy)Computer scienceStatistical physicsMolecular dynamicsDensity functional theoryStability (learning theory)AlgorithmArtificial intelligenceMachine learningComputational chemistryPhysicsParallel computingClassical mechanicsChemistryEconomicsPhilosophyEpistemologyEconomic growthMachine Learning in Materials ScienceElectron and X-Ray Spectroscopy TechniquesX-ray Diffraction in Crystallography