Machine learned Hückel theory: Interfacing physics and deep neural networks

Tetiana Zubatiuk, Benjamin Nebgen, Nicholas Lubbers, Justin S. Smith, Roman Zubatyuk, Guoqing Zhou, Christopher Koh, Kipton Barros, Olexandr Isayev, Sergei Tretiak

Research output: Contribution to journalArticlepeer-review

8 Citations (Scopus)

Abstract

The Hückel Hamiltonian is an incredibly simple tight-binding model known 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 empirical parameters with machine-learned dynamic 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 and accurate and reproduces insightful features of the original empirical parameterization. Overall, this work shows the promise of utilizing machine learning to formulate simple, accurate, and dynamically parameterized physics models.

Original languageEnglish
Article number244108
JournalJournal of Chemical Physics
Volume154
Issue number24
DOIs
Publication statusPublished - 28 Jun 2021
Externally publishedYes

Fingerprint

Dive into the research topics of 'Machine learned Hückel theory: Interfacing physics and deep neural networks'. Together they form a unique fingerprint.

Cite this