Combining Machine Learning and Physics to Understand Glassy Systems

TL;DR

This paper reviews recent advances in understanding glassy systems by integrating machine learning techniques with physical theories to identify structural signatures predictive of dynamics in disordered materials.

Contribution

It introduces a data-driven approach that combines machine learning with physical insights to develop a phenomenological theory of glasses and disordered systems.

Findings

Machine learning helps identify structural features linked to dynamics.

The approach offers new insights into non-equilibrium effects in glasses.

Combining data-driven methods with physics advances understanding of disordered materials.

Abstract

Our understanding of supercooled liquids and glasses has lagged significantly behind that of simple liquids and crystalline solids. This is in part due to the many possibly relevant degrees of freedom that are present due to the disorder inherent to these systems and in part to non-equilibrium effects which are difficult to treat in the standard context of statistical physics. Together these issues have resulted in a field whose theories are under-constrained by experiment and where fundamental questions are still unresolved. Mean field results have been successful in infinite dimensions but it is unclear to what extent they apply to realistic systems and assume uniform local structure. At odds with this are theories premised on the existence of structural defects. However, until recently it has been impossible to find structural signatures that are predictive of dynamics. Here we summarize and recast the results from several recent papers offering a data driven approach to building a phenomenological theory of disordered materials by combining machine learning with physical intuition.