Dynamics of supercooled liquids from static averaged quantities using machine learning

TL;DR

This paper presents a machine learning approach that predicts supercooled liquids' dynamics from static averaged quantities, enabling easier application in experiments and revealing the underlying memory function as a sum of two stretched exponentials.

Contribution

It introduces a neural network model to predict dynamics from static data and develops an evolutionary strategy to characterize the memory function of supercooled liquids.

Findings

Neural network accurately predicts the self intermediate scattering function within the training temperature range.

Model shows transferability to lower temperatures and similar systems.

Memory function can be effectively modeled as the sum of two stretched exponentials.

Abstract

We introduce a machine-learning approach to predict the complex non-Markovian dynamics of supercooled liquids from static averaged quantities. Compared to techniques based on particle propensity, our method is built upon a theoretical framework that uses as input and output system-averaged quantities, thus being easier to apply in an experimental context where particle resolved information is not available. In this work, we train a deep neural network to predict the self intermediate scattering function of binary mixtures using their static structure factor as input. While its performance is excellent for the temperature range of the training data, the model also retains some transferability in making decent predictions at temperatures lower than the ones it was trained for, or when we use it for similar systems. We also develop an evolutionary strategy that is able to construct a realistic memory function underlying the observed non-Markovian dynamics. This method lets us conclude that the memory function of supercooled liquids can be effectively parameterized as the sum of two stretched exponentials, which physically corresponds to two dominant relaxation modes.