Monomeric Neural Network Potential for General Covalent Molecules: Linear Alkanes as an Example
electronic energies and reliably captures key molecular properties, including torsional potential energy profiles, harmonic vibrational frequencies, and vibrational power spectra obtained from molecular dynamics simulations. Importantly, MB-PIPNet demonstrates a substantial advantage in computational efficiency over other MLP models for combined energy and force evaluations. These results establish MB-PIPNet as a scalable and efficient framework for constructing MLPs, providing an additional route for large-scale quantum and classical simulations of complex molecular systems.
Authors
- Qi Yu (ORCID: https://orcid.org/0000-0002-2030-0671)
- Ruitao Ma
- Dong Hui Zhang (ORCID: https://orcid.org/0000-0001-9426-8822)
- Xinze Li (ORCID: https://orcid.org/0000-0003-3513-209X)
- Chen Qu (ORCID: https://orcid.org/0000-0001-8889-4851)
Institutions
- Dalian Institute of Chemical Physics (CN)
- Chinese Academy of Sciences (CN)
- Fudan University (CN)
- ECSI Fibrotools (United States) (US)
Publication Details
- Journal
- Journal of Chemical Theory and Computation
- Published
- 2026-04-27
- DOI
- https://doi.org/10.1021/acs.jctc.6c00290
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Shanghai Municipal Commission of Economy and Informatization