The Journal of Physical Chemistry Letters · 2019 · 293 citations · 39 references
Natural SciencesChemistryPhysicsComputational ChemistryQuantum ChemistryTheoretical ChemistryAb Initio MethodsMolecular DynamicsMolecular Orbital TheoryMolecular SimulationPotential Energy SurfacesSpectroscopy SimulationAb Initio CalculationsAb Initio Molecular DynamicsAb Initio SimulationsEmbedded Atom ModelMachine Learning Potential Energy SurfacesMachine Learning PotentialsMolecular Simulation AlgorithmsQuantum Chemical Modeling
We propose a simple, but efficient and accurate, machine learning (ML) model for developing a high-dimensional potential energy surface. This so-called embedded atom neural network (EANN) approach is inspired by the well-known empirical embedded atom method (EAM) model used in the condensed phase. It simply replaces the scalar embedded atom density in EAM with a Gaussian-type orbital based density vector and represents the complex relationship between the embedded density vector and atomic energy by neural networks. We demonstrate that the EANN approach is equally accurate as several established ML models in representing both big molecular and extended periodic systems, yet with much fewer parameters and configurations. It is highly efficient as it implicitly contains the three-body information without an explicit sum of the conventional costly angular descriptors. With high accuracy and efficiency, EANN potentials can vastly accelerate molecular dynamics and spectroscopic simulations in complex systems at ab initio level.
39
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
Albert P. Bartók, M. C. Payne, Risi Kondor et al. · Physical Review Letters · 2010 · 3.1K citations · Full text
Natural Sciences, Chemistry, Physics +17
On representing chemical environments
Albert P. Bartók, Risi Kondor, Gábor Cśanyi · Physical Review B · 2013 · 2.6K citations · Full text
Natural Sciences, Chemistry, Physics +15