Learning the GENERIC evolution

2021/09/26 by Martin Šípka, Šípka, Martin, Michal Pavelka +1
Computer Science · Materials Science · Physics and Astronomy · #Computational Physics (physics.comp-ph) #FOS: Physical sciences #Machine Learning in Materials Science #Model Reduction and Neural Networks #Neural Networks and Applications

paper · pdf · doi:10.48550/arxiv.2109.12659

openalex publication_date 2021/09/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a novel approach for learning the evolution that employs differentiable neural networks to approximate the full GENERIC structure. Instead of manually choosing the fitted parameters, we learn the whole model together with the evolution equations. We can reconstruct the energy and entropy functions for the system under various assumptions and accurately capture systems behaviour for a double thermoelastic pendulum and a rigid body.

Citations

• Dynamics and thermodynamics of complex fluids. I. Development of a general formalism

Related

• Self-Supervised Evolution Operator Learning for High-Dimensional Dynamical Systems
• ModLaNets: Learning Generalisable Dynamics via Modularity and Physical Inductive Bias
• HybridNet: Integrating Model-based and Data-driven Learning to Predict Evolution of Dynamical Systems
• SyReNets: Symbolic Residual Neural Networks
• Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics