Freiburg 2024 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

A: Fachverband Atomphysik

A 18: Attosecond Physics II / Interaction with VUV and X-ray Light (joint session A/MO)

A 18.7: Talk

Wednesday, March 13, 2024, 12:45–13:00, HS 1010

Towards AI-enhanced online-characterization of ultrashort X-ray free-electron laser pulses — •Thorsten Otto^1,2,4, Kristina Dingel², Lars Funke³, Sara Savio³, Lasse Wülfing³, Bernhard Sick², Wolfram Helml³, and Markus Ilchen⁴ — ¹Deutsches Elektronen-Synchrotron DESY, Notkestraße 85, 22607 Hamburg, Germany — ²Intelligent Embedded Systems, University of Kassel, Wilhelmshöher Allee 73, 34121 Kassel, Germany — ³Technische Universität Dortmund, Fakultät für Physik, Maria- Göppert-Mayer-Straße, 44227 Dortmund, Germany — ⁴Universität Hamburg, Institut für Experimentalphysik, Luruper Chaussee 149 22761 Hamburg

X-ray free-electron lasers provide ultrashort X-ray pulses with durations typically in the order of femtoseconds, but recently even entering the attosecond regime. The technological evolution of XFELs towards well-controllable light sources for precise metrology of ultrafast processes can only be achieved using new diagnostic capabilities for characterizing X-ray pulses at the attosecond frontier. The spectroscopic technique of photoelectron angular streaking has successfully proven how to non-destructively retrieve the exact time-energy structure of XFEL pulses on a single-shot basis. By using deep learning algorithms, we show how this technique can be leveraged from its proof-of-principle stage towards routine diagnostics at XFELs providing precise feedback in real time.

Keywords: Free-electron laser; Artificial intelligence; Machine learning; Angular streaking; Online pulse characterization