咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >Extending the atomic decomposi... 收藏
arXiv

Extending the atomic decomposition and many-body representation, a chemistry-motivated monomer-centered approach for machine learning potentials

作     者:Yu, Qi Ma, Ruitao Qu, Chen Conte, Riccardo Nandi, Apurba Pandey, Priyanka Houston, Paul L. Zhang, Dong H. Bowman, Joel M. 

作者机构:Department of Chemistry Fudan University Shanghai200438 China Independent Researcher TorontoONM9B0E3 Canada Dipartimento di Chimica Università degli Studi di Milano via Golgi 19 Milano20133 Italy Department of Physics and Materials Science University of Luxembourg Luxembourg CityL-1511 Luxembourg Department of Chemistry Cherry L. Emerson Center for Scientific Computation Emory University AtlantaGA30322 United States Department of Chemistry and Chemical Biology Cornell University IthacaNY14853 United States State Key Laboratory of Molecular Reaction Dynamics Dalian Institute of Chemical Physics Chinese Academy of Sciences Dalian116023 China Department of Chemistry and Biochemistry Georgia Institute of Technology AtlantaGA30332 United States 

出 版 物:《arXiv》 (arXiv)

年 卷 期:2024年

核心收录:

主  题:Monomers 

摘      要:Most widely used machine learned (ML) potentials for condensed phase applications rely on many-body permutationally invariant polynomial (PIP) or atom-centered neural networks (NN). However, these approaches often lack chemical interpretability in atomistic energy decomposition and the computational efficiency of traditional force fields has not been fully achieved. Here, we present a novel method that combines aspects of both approaches, and achieves state-of-the-art balance of accuracy and force field-level speed. This method utilizes a monomer-centered representation, where the potential energy is decomposed into the sum of chemically meaningful monomeric energies. Without sophisticated neural network design, the structural descriptors of monomers are described by 1-body and 2-body effective interactions, enforced by appropriate sets of PIPs as inputs to the feed forward *** demonstrate the performance of this method through systematic assessments of models for gas-phase water trimer, liquid water, and also liquid CO2. The high accuracy, fast speed, and flexibility of this method provide a new route for constructing accurate ML potentials and enabling large-scale quantum and classical simulations for complex molecular systems. © 2024, CC BY.

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分