Summer Student Projects Submission 2022

Performance Comparison of Machine Learning Classifiers for the Calibration of the Hard X-Ray Single-Shot Spectrometer at the European XFEL

Not scheduled

20m

Remote project

Description

Single-crystal monochromators are used in free electron lasers for hard x-ray self-seeding, selecting a very narrow spectral range and further amplifying the original SASE signal. When a crystal is rotated, one can exploit several symmetric and asymmetric reflections as established by Bragg's law. A ML classifier is used during experimental setup to identify the crystal indices corresponding to a given reflection, and eventually calculate the difference between the photon energy as measured by the single-shot spectrometer and the actual one.

By comparing a range of ML classifiers in terms of their performance, the student will have the opportunity to work with experimental data from the European XFEL. Moreover, the student will obtain a general overview of several ML classifiers and will be able to carry such knowledge into their future studies.

Special Qualifications:

• Good level of programming in Python (required)
• Prior knowledge in ML tools like Scikit-learn, TensorFlow/Keras, PyTorch (beneficial, but not required)