Neural network potentials for reactive chemistry: CASPT2 quality potential energy surfaces for bond breaking
Quin Hu, Andrew Johannesen, Daniel S. Graham, Jason D. Goodpaster
Abstract
Neural network potentials achieve CASPT2 accuracy for reactive chemistry and molecular simulations. Using transfer learning, these potentials require minimal CASPT2 data on small systems to accurately predict bond dissociation in larger systems.
Topics & Concepts
Dissociation (chemistry)Artificial neural networkChemistryPotential energyQuality (philosophy)Biological systemComputational chemistryChemical physicsComputer scienceNanotechnologyArtificial intelligencePhysicsMaterials sciencePhysical chemistryAtomic physicsBiologyQuantum mechanicsMachine Learning in Materials ScienceComputational Drug Discovery MethodsProtein Structure and Dynamics