Department of Mathematical Sciences
Colloquium
Friday, November 14th, 2025
11:00AM-11:50AM
Stratton Hall 202
Speaker: Pei Ge, WPI
Title: An Energy-Stable Machine-Learning Model of Non-Newtonian Hydrodynamics with Molecular Fidelity
Abstract: We introduce a machine-learning-based approach for constructing a continuum non-Newtonian fluid dynamics model directly from a micro-scale description. To faithfully retain molecular fidelity, we establish a micro-macro correspondence via a set of encoders for the micro-scale polymer configurations and their macro-scale counterparts, a set of nonlinear conformation tensors. The dynamics of these conformation tensors can be derived from a generalized extendable energy functional structure, and be directly learned from the micro-scale model with clear physical interpretation. The final model, named the deep nonNewtonian model (DeePN^2), takes the form of conventional non-Newtonian fluid dynamics models and ensures energy stability. Numerical results demonstrate the accuracy and robustness of DeePN^2.