Research Interest

Machine learning methodology for multiscale modeling (model reduction)

Manybody Non-Markivan Dissipative Particle Dynamics, State-dependent General Lagenvin Dynamics.

Publications

  1. Pei Ge, Zhongqiang Zhang, Huan Lei*. 2024. "Data-Driven Learning of the Generalized Langevin Equation with State-Dependent Memory" Physical Review Letters
  2. Pei Ge, Linfeng Zhang, Huan Lei*. 2023. "Machine learning assisted coarse-grained molecular dynamics modeling of meso-scale interfacial fluids" The Journal of Chemical Physics
  3. Zhiyuan She, Pei Ge, Huan Lei*. 2023. "Data-driven construction of stochastic reduced dynamics encoded with non-Markovian features" The Journal of Chemical Physics
  4. Lidong Fang, Pei Ge, Lei Zhang, Weinan E, Huan Lei*. 2022. "DeePN2: A Deep Learning-Based Non-Newtonian Hydrodynamic Model" Journal of Machine Learning

© * represent the corresponding author..

Talks & Presentations

  • SIAM CSE25, "An Energy-Stable Machine-Learning Model of Non-Newtonian Hydrodynamics with Molecular Fidelity", Fort Worth, USA, Mar 2025.
  • The NSF Computational Mathematics PI Meeting , Seattle, WA, USA, Jul 2024.
  • Scale Bridging Meeting and Workshop , Los Alamos, NM, USA, Apr 2024.
  • SIAM-NNP, "Data-driven Learning of Generalized Langevin Equations with State-dependent Memory" , New Jersey, USA, Oct 2023.