Modeling electronic response properties with an explicit-electron machine learning potential
- Author
- Maarten Cools-Ceuppens (UGent) , Joni Dambre (UGent) and Toon Verstraelen (UGent)
- Organization
- Project
- Abstract
- Explicit-electron force fields introduce electrons or electron pairs as semiclassical particles in force fields or empirical potentials, which are suitable for molecular dynamics simulations. Even though semiclassical electrons are a drastic simplification compared to a quantum-mechanical electronic wave function, they still retain a relatively detailed electronic model compared to conventional polarizable and reactive force fields. The ability of explicit-electron models to describe chemical reactions and electronic response properties has already been demonstrated, yet the description of short-range interactions for a broad range of chemical systems remains challenging. In this work, we present the electron machine learning potential (eMLP), a new explicit electron force field in which the short-range interactions are modeled with machine learning. The electron pair particles will be located at well-defined positions, derived from localized molecular orbitals or Wannier centers, naturally imposing the correct dielectric and piezoelectric behavior of the system. The eMLP is benchmarked on two newly constructed data sets: eQM7, an extension of the QM7 data set for small molecules, and a data set for the crystalline beta-glycine. It is shown that the eMLP can predict dipole moments, polarizabilities, and IR-spectra of unseen molecules with high precision. Furthermore, a variety of response properties, for example, stiffness or piezoelectric constants, can be accurately reproduced.
- Keywords
- REACTIVE FORCE-FIELD, MOLECULAR-DYNAMICS, BERRY-PHASE, BASIS-SETS, EXCHANGE, CHARGE, EQUATIONS
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 1.66 MB
-
2109.13111.pdf
- full text (Accepted manuscript)
- |
- open access
- |
- |
- 2.92 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8759262
- MLA
- Cools-Ceuppens, Maarten, et al. “Modeling Electronic Response Properties with an Explicit-Electron Machine Learning Potential.” JOURNAL OF CHEMICAL THEORY AND COMPUTATION, vol. 18, no. 3, 2022, pp. 1672–91, doi:10.1021/acs.jctc.1c00978.
- APA
- Cools-Ceuppens, M., Dambre, J., & Verstraelen, T. (2022). Modeling electronic response properties with an explicit-electron machine learning potential. JOURNAL OF CHEMICAL THEORY AND COMPUTATION, 18(3), 1672–1691. https://doi.org/10.1021/acs.jctc.1c00978
- Chicago author-date
- Cools-Ceuppens, Maarten, Joni Dambre, and Toon Verstraelen. 2022. “Modeling Electronic Response Properties with an Explicit-Electron Machine Learning Potential.” JOURNAL OF CHEMICAL THEORY AND COMPUTATION 18 (3): 1672–91. https://doi.org/10.1021/acs.jctc.1c00978.
- Chicago author-date (all authors)
- Cools-Ceuppens, Maarten, Joni Dambre, and Toon Verstraelen. 2022. “Modeling Electronic Response Properties with an Explicit-Electron Machine Learning Potential.” JOURNAL OF CHEMICAL THEORY AND COMPUTATION 18 (3): 1672–1691. doi:10.1021/acs.jctc.1c00978.
- Vancouver
- 1.Cools-Ceuppens M, Dambre J, Verstraelen T. Modeling electronic response properties with an explicit-electron machine learning potential. JOURNAL OF CHEMICAL THEORY AND COMPUTATION. 2022;18(3):1672–91.
- IEEE
- [1]M. Cools-Ceuppens, J. Dambre, and T. Verstraelen, “Modeling electronic response properties with an explicit-electron machine learning potential,” JOURNAL OF CHEMICAL THEORY AND COMPUTATION, vol. 18, no. 3, pp. 1672–1691, 2022.
@article{8759262,
abstract = {{Explicit-electron force fields introduce electrons or electron pairs as semiclassical particles in force fields or empirical potentials, which are suitable for molecular dynamics simulations. Even though semiclassical electrons are a drastic simplification compared to a quantum-mechanical electronic wave function, they still retain a relatively detailed electronic model compared to conventional polarizable and reactive force fields. The ability of explicit-electron models to describe chemical reactions and electronic response properties has already been demonstrated, yet the description of short-range interactions for a broad range of chemical systems remains challenging. In this work, we present the electron machine learning potential (eMLP), a new explicit electron force field in which the short-range interactions are modeled with machine learning. The electron pair particles will be located at well-defined positions, derived from localized molecular orbitals or Wannier centers, naturally imposing the correct dielectric and piezoelectric behavior of the system. The eMLP is benchmarked on two newly constructed data sets: eQM7, an extension of the QM7 data set for small molecules, and a data set for the crystalline beta-glycine. It is shown that the eMLP can predict dipole moments, polarizabilities, and IR-spectra of unseen molecules with high precision. Furthermore, a variety of response properties, for example, stiffness or piezoelectric constants, can be accurately reproduced.}},
author = {{Cools-Ceuppens, Maarten and Dambre, Joni and Verstraelen, Toon}},
issn = {{1549-9618}},
journal = {{JOURNAL OF CHEMICAL THEORY AND COMPUTATION}},
keywords = {{REACTIVE FORCE-FIELD,MOLECULAR-DYNAMICS,BERRY-PHASE,BASIS-SETS,EXCHANGE,CHARGE,EQUATIONS}},
language = {{eng}},
number = {{3}},
pages = {{1672--1691}},
title = {{Modeling electronic response properties with an explicit-electron machine learning potential}},
url = {{http://doi.org/10.1021/acs.jctc.1c00978}},
volume = {{18}},
year = {{2022}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: