Tensorial Properties via the Neuroevolution Potential Framework: Fast Simulation of Infrared and Raman Spectra
Artikel i vetenskaplig tidskrift, 2024
Infrared and Raman spectroscopy are widely used for the characterization of gases, liquids, and solids, as the spectra contain a wealth of information concerning, in particular, the dynamics of these systems. Atomic scale simulations can be used to predict such spectra but are often severely limited due to high computational cost or the need for strong approximations that limit the application range and reliability. Here, we introduce a machine learning (ML) accelerated approach that addresses these shortcomings and provides a significant performance boost in terms of data and computational efficiency compared with earlier ML schemes. To this end, we generalize the neuroevolution potential approach to enable the prediction of rank one and two tensors to obtain the tensorial neuroevolution potential (TNEP) scheme. We apply the resulting framework to construct models for the dipole moment, polarizability, and susceptibility of molecules, liquids, and solids and show that our approach compares favorably with several ML models from the literature with respect to accuracy and computational efficiency. Finally, we demonstrate the application of the TNEP approach to the prediction of infrared and Raman spectra of liquid water, a molecule (PTAF-), and a prototypical perovskite with strong anharmonicity (BaZrO3). The TNEP approach is implemented in the free and open source software package gpumd, which makes this methodology readily available to the scientific community.
Författare
[Person f721bea2-15a5-4955-87ba-3e84c9421ea9 not found]
College of Chemical and Biological Engineering, Zhejiang University
Quzhou University
[Person 77506041-5725-4271-b7fe-32d30fe881b8 not found]
Chalmers, Fysik, Kondenserad materie- och materialteori
[Person dfa94d8a-ca1c-4062-a5d1-8e2cef912edf not found]
Chalmers, Fysik, Kondenserad materie- och materialteori
[Person e34efe74-e895-49e8-aebc-93f9f9b29668 not found]
Chalmers, Fysik, Kondenserad materie- och materialteori
[Person 5133d8af-4c72-482d-aa2d-e7e64888d75e not found]
Chalmers, Fysik, Kondenserad materie- och materialteori
[Person 5cd43905-ba40-4dc3-a6d8-a2e6295e6c51 not found]
Quzhou University
College of Chemical and Biological Engineering, Zhejiang University
[Person b8058161-7d43-4874-8b8f-11ed65320b39 not found]
Chinese Academy of Sciences
[Person da057e63-9f1d-48ee-9d95-da76dd2b7c90 not found]
Quzhou University
UW College of Engineering
College of Chemical and Biological Engineering, Zhejiang University
[Person eb2b9109-8818-4753-8e4a-0a418cf82e1a not found]
Bohai University
[Person 610f6bcb-1fdf-42c1-b998-9533bbd833e6 not found]
Chalmers, Fysik, Kondenserad materie- och materialteori
Journal of Chemical Theory and Computation
1549-9618 (ISSN) 1549-9626 (eISSN)
Vol. 20 8 3273-3284Ämneskategorier (SSIF 2011)
Teoretisk kemi
DOI
10.1021/acs.jctc.3c01343
Relaterade dataset
Data for "Tensorial properties via the neuroevolution potential framework: Fast simulation of infrared and Raman spectra" [dataset]
DOI: 10.5281/zenodo.10257363