Density Functionals with Quantum Chemical Accuracy: From Machine Learning to Molecular Dynamics (bibtex)
by Mihail Bogojeski, Leslie Vogt-Maranto, Mark E. Tuckerman, Klaus-Robert Mueller, Kieron Burke
Abstract:
Kohn-Sham density functional theory (DFT) is a standard tool in most branches of chemistry, but accuracies for many molecules are limited to 2-3 kcal/mol with presently-available functionals. Ab initio methods, such as coupled-cluster, routinely produce much higher accuracy, but computational costs limit their application to small molecules. We create density functionals from coupled-cluster energies, based only on DFT densities, via machine learning. These functionals attain quantum chemical accuracy (errors below 1 kcal/mol). Moreover, density-based ∆-learning (learning only the correction to a standard DFT calculation, ∆-DFT) significantly reduces the amount of training data required. We demonstrate these concepts for a single water molecule, and then illustrate how to include molecular symmetries with ethanol. Finally, we highlight the robustness of ∆-DFT by correcting DFT simulations of resorcinol on the fly to obtain molecular dynamics (MD) trajectories with coupled-cluster accuracy. Thus ∆-DFT opens the door to running gas-phase MD simulations with quantum chemical accuracy, even for strained geometries and conformer changes where standard DFT is quantitatively incorrect.
Reference:
Density Functionals with Quantum Chemical Accuracy: From Machine Learning to Molecular Dynamics Mihail Bogojeski, Leslie Vogt-Maranto, Mark E. Tuckerman, Klaus-Robert Mueller, Kieron Burke, Submitted , (2019).
Bibtex Entry:
@article{MTMB19,
	Pub-num 	   = {192},
	Title 		   = {Density Functionals with Quantum Chemical Accuracy: From Machine Learning to Molecular Dynamics
},
	Author 		   = {Mihail Bogojeski, Leslie Vogt-Maranto, Mark E. Tuckerman, Klaus-Robert Mueller, Kieron Burke},
	Abstract 	   = {Kohn-Sham density functional theory (DFT) is a standard tool in most branches of chemistry, but accuracies for many molecules are limited to 2-3 kcal/mol with presently-available functionals. Ab initio methods, such as coupled-cluster, routinely produce much higher accuracy, but computational costs limit their application to small molecules. We create density functionals from coupled-cluster energies, based only on DFT densities, via machine learning. These functionals attain quantum chemical accuracy (errors below 1 kcal/mol). Moreover, density-based ∆-learning (learning only the correction to a standard DFT calculation, ∆-DFT) significantly reduces the amount of training data required. We demonstrate these concepts for a single water molecule, and then illustrate how to include molecular symmetries with ethanol. Finally, we highlight the robustness of ∆-DFT by correcting DFT simulations of resorcinol on the fly to obtain molecular dynamics (MD) trajectories with coupled-cluster accuracy. Thus ∆-DFT opens the door to running gas-phase MD simulations with quantum chemical accuracy, even for strained geometries and conformer changes where standard DFT is quantitatively incorrect.},
	Doi 		   = {10.26434/chemrxiv.8079917},
%%	Issn		   = {},
	Year 		   = {2019},
	Month 		   = {},
	Journal		   = {Submitted},
	Volume 		   = {},
%%	Issue 		   = {},
%%	Number 		   = {},
	Pages 		   = {},
	Publisher 	   = { },
%%	Url 		   = {https://chemrxiv.org/articles/Density_Functionals_with_Quantum_Chemical_Accuracy_From_Machine_Learning_to_Molecular_Dynamics/8079917},
%%	arXiv		   = {},
	keywords 	   = {}
}
Powered by bibtexbrowser