Constructing Custom Thermodynamics Using Deep Learning

TL;DR

This paper introduces a deep learning platform based on a generalized Onsager principle that learns macroscopic thermodynamic descriptions from microscopic data, demonstrated on polymer stretching experiments.

Contribution

It develops a novel method to automatically derive thermodynamic coordinates and dynamics from microscopic trajectories, aiding scientific discovery in complex systems.

Findings

Successfully learned thermodynamic coordinates for polymer stretching

Built a dynamical landscape including stable and transition states

Validated the approach experimentally on polymer chains

Abstract

One of the most exciting applications of artificial intelligence (AI) is automated scientific discovery based on previously amassed data, coupled with restrictions provided by known physical principles, including symmetries and conservation laws. Such automated hypothesis creation and verification can assist scientists in studying complex phenomena, where traditional physical intuition may fail. Here we develop a platform based on a generalized Onsager principle to learn macroscopic dynamical descriptions of arbitrary stochastic dissipative systems directly from observations of their microscopic trajectories. Our method simultaneously constructs reduced thermodynamic coordinates and interprets the dynamics on these coordinates. We demonstrate its effectiveness by studying theoretically and validating experimentally the stretching of long polymer chains in an externally applied field. Specifically, we learn three interpretable thermodynamic coordinates and build a dynamical landscape of polymer stretching, including the identification of stable and transition states and the control of the stretching rate. Our general methodology can be used to address a wide range of scientific and technological applications.