Abstract: Dramatic improvements in x-ray scattering experiments generate complex, voluminous data at a rate outpacing the speed of conventional data analysis. This calls for fast and interpretable machine-learning approaches to harness the data for scientific insights.

In this talk, I will discuss a novel unsupervised machine learning technique we developed, called X-ray Temperature Clustering (X-TEC), that separates the scattering data into clusters of distinct physical origins. Using X-TEC to analyze the temperature evolution of X-ray data from the Advanced Photon Source, we identified scattering signatures of charge density waves, Goldstone mode fluctuations, and quasi-long-range order in disordered systems.  I will also discuss the broad applicability of X-TEC to other scattering probes like time-resolved resonant X-ray diffraction and 4D scanning tunneling electron microscopy (4D-STEM).

Work supported by the US Department of Energy, Office of Science, Office of Basic Energy Sciences, Division of Material Sciences and Engineering.