Non-equilibrium phenomena are ubiquitous across material systems and of great technological relevance. Examples of such phenomena include diffusions in liquid and gases, viscoelasticity and plasticity in solids, and rheological behavior of colloidal and granular media. Despite their ubiquity and importance, the understanding of non-equilibrium phenomena remains in its infancy compared with classical equilibrium thermodynamics and statistical mechanics. Consequently, current modeling and simulation strategies, including multiscale paradigms, are mostly trapped within a compromise between computational efficiency and physical fidelity.
In this talk, I will leverage recent advances in non-equilibrium physics, together with emerging machine learning techniques, to develop data-driven computational strategies for learning continuum evolution equations. First, I will talk about a proposed machine learning architecture called Variational Onsager Neural Networks (VONNs) to learn the non-equilibrium evolution PDEs based on the Onsager's variational principle. Second, I will present a new strategy for continuum model discovery applicable to small stochastic systems, by using fluctuation theorems, particularly, the Jarzynski equality. Finally, I will introduce a statistical mechanics framework with quantified uncertainty to extrapolate material behavior to different loading conditions (including far-from-equilibrium conditions) or material systems.
Copyright. All Rights Reserved.