Machine learned Hückel theory: Interfacing physics and deep neural networks
| Autor: | Benjamin Nebgen, Tetiana Zubatiuk, Kipton Barros, Olexandr Isayev, Nicholas Lubbers, Sergei Tretiak, Guoqing Zhou, Justin S. Smith, Christopher Koh, Roman Zubatyuk |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Physics
Work (thermodynamics) 010304 chemical physics Artificial neural network General Physics and Astronomy Parameterized complexity 010402 general chemistry 01 natural sciences 0104 chemical sciences Interfacing Simple (abstract algebra) 0103 physical sciences Density functional theory Statistical physics Physical and Theoretical Chemistry Hamiltonian (control theory) Interpretability |
| Zdroj: | The Journal of chemical physics. 154(24) |
| ISSN: | 1089-7690 |
| Popis: | The Huckel 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 Huckel 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|