Elucidation of Relaxation Dynamics Beyond Equilibrium Through AI-informed X-ray Photon Correlation Spectroscopy

TL;DR

This paper introduces an AI-driven deep learning framework for analyzing X-ray photon correlation spectroscopy data, enabling automated interpretation of relaxation dynamics in materials without prior physical knowledge, thus advancing autonomous materials discovery.

Contribution

The work presents a novel unsupervised deep learning approach for classifying and interpreting relaxation dynamics from XPCS data, independent of specific material or process details.

Findings

Successfully classified relaxation dynamics in experimental datasets

Enabled rapid exploration of large datasets for materials analysis

Correlated bulk properties with microscopic dynamics

Abstract

Understanding and interpreting dynamics of functional materials \textit{in situ} is a grand challenge in physics and materials science due to the difficulty of experimentally probing materials at varied length and time scales. X-ray photon correlation spectroscopy (XPCS) is uniquely well-suited for characterizing materials dynamics over wide-ranging time scales, however spatial and temporal heterogeneity in material behavior can make interpretation of experimental XPCS data difficult. In this work we have developed an unsupervised deep learning (DL) framework for automated classification and interpretation of relaxation dynamics from experimental data without requiring any prior physical knowledge of the system behavior. We demonstrate how this method can be used to rapidly explore large datasets to identify samples of interest, and we apply this approach to directly correlate bulk properties of a model system to microscopic dynamics. Importantly, this DL framework is material and process agnostic, marking a concrete step towards autonomous materials discovery.