Salvato in:
Dettagli Bibliografici
Autori principali: Zubatyuk, Tetiana, Nebgen, Ben, Lubbers, Nicholas, Smith, Justin S., Zubatyuk, Roman, Zhou, Guoqing, Koh, Christopher, Barros, Kipton, Isayev, Olexandr, Tretiak, Sergei
Natura: Preprint
Pubblicazione: 2019
Soggetti:
Accesso online:https://arxiv.org/abs/1909.12963
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910492130279424
author Zubatyuk, Tetiana
Nebgen, Ben
Lubbers, Nicholas
Smith, Justin S.
Zubatyuk, Roman
Zhou, Guoqing
Koh, Christopher
Barros, Kipton
Isayev, Olexandr
Tretiak, Sergei
author_facet Zubatyuk, Tetiana
Nebgen, Ben
Lubbers, Nicholas
Smith, Justin S.
Zubatyuk, Roman
Zhou, Guoqing
Koh, Christopher
Barros, Kipton
Isayev, Olexandr
Tretiak, Sergei
contents The Hückel Hamiltonian is an incredibly simple tight-binding model famed for its ability to capture qualitative physics phenomena arising from electron interactions in molecules and materials. Part of its simplicity arises from using only two types of empirically fit physics-motivated parameters: the first describes the orbital energies on each atom and the second describes electronic interactions and bonding between atoms. By replacing these traditionally static parameters with dynamically predicted values, we vastly increase the accuracy of the extended Hückel model. The dynamic values are generated with a deep neural network, which is trained to reproduce orbital energies and densities derived from density functional theory. The resulting model retains interpretability while the deep neural network parameterization is smooth, accurate, and reproduces insightful features of the original static parameterization. Finally, we demonstrate that the Hückel model, and not the deep neural network, is responsible for capturing intricate orbital interactions in two molecular case studies. Overall, this work shows the promise of utilizing machine learning to formulate simple, accurate, and dynamically parameterized physics models.
format Preprint
id arxiv_https___arxiv_org_abs_1909_12963
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle Machine Learned Hückel Theory: Interfacing Physics and Deep Neural Networks
Zubatyuk, Tetiana
Nebgen, Ben
Lubbers, Nicholas
Smith, Justin S.
Zubatyuk, Roman
Zhou, Guoqing
Koh, Christopher
Barros, Kipton
Isayev, Olexandr
Tretiak, Sergei
Disordered Systems and Neural Networks
Chemical Physics
Computational Physics
The Hückel Hamiltonian is an incredibly simple tight-binding model famed for its ability to capture qualitative physics phenomena arising from electron interactions in molecules and materials. Part of its simplicity arises from using only two types of empirically fit physics-motivated parameters: the first describes the orbital energies on each atom and the second describes electronic interactions and bonding between atoms. By replacing these traditionally static parameters with dynamically predicted values, we vastly increase the accuracy of the extended Hückel model. The dynamic values are generated with a deep neural network, which is trained to reproduce orbital energies and densities derived from density functional theory. The resulting model retains interpretability while the deep neural network parameterization is smooth, accurate, and reproduces insightful features of the original static parameterization. Finally, we demonstrate that the Hückel model, and not the deep neural network, is responsible for capturing intricate orbital interactions in two molecular case studies. Overall, this work shows the promise of utilizing machine learning to formulate simple, accurate, and dynamically parameterized physics models.
title Machine Learned Hückel Theory: Interfacing Physics and Deep Neural Networks
topic Disordered Systems and Neural Networks
Chemical Physics
Computational Physics
url https://arxiv.org/abs/1909.12963