Unsupervised anomaly detection in MeV ultrafast electron diffraction

MeV ultrafast electron diffraction (MUED) is a pump-probe characterization technique for studying ultrafast processes in materials. The use of relativistic beams leads to decreased space-charge effects compared to typical ul-trafast electron diffraction experiments employing energies in the keV range [1, 2]. Compared to other ultrafast probes such as X-ray free electron lasers, MUED has a higher scattering cross section with material samples and allows access to higher order reflections in the diffraction patterns due to the short electron wavelengths. However, this is a relatively young technology and several factors contribute to making it challenging to utilize, such as beam instabilities which can lower the effective spatial and temporal resolution. In the past years, machine learning (ML) approaches to materials and characterization techniques have provided a new path towards unlocking new physics by improving existing probes and increasing the user's ability to interpret data.