Machine learning has become powerful tool in modern computational materials science. Among diverse applications, molecular dynamics (MD) simulation based on neural network (NN) has been attracting great attentions. With the highly accurate energy landscape encoded by ab-initio molecular dynamics training dataset, our goal is to develop an efficient and robust neural network quantum molecular dynamics (NNQMD) framework to perform multimillion atom and long-time nano seconds to microsecond simulations that provide unprecedented access to materials processes and properties. We have developed a scalable NNQMD simulation framework that has been successfully applied to different class of materials to compute their structural, dynamical and dielectric properties. In this talk, I will discuss our recent progress and applications to water and intermediate range order in covalent glasses. The static dielectric constant, ε<sub>0</sub>, and its temperature dependence for liquid water is investigated using NNQMD. We compute the exact dielectric constant in canonical ensemble from NNQMD trajectories using fluctuations in macroscopic polarization computed from maximally localized Wannier functions (MLWF). We investigate prototypical intermediate range order in GeSe<sub>2 </sub>glass and melt using NNQMD, which allows large simulation sizes with validated quantum mechanical accuracy to make quantitative comparison with experimental neutron diffraction data.

Neural network quantum molecular dynamics (NNQMD) for water and covalent glasses

ACS Fall 2021

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.