A reliable characterization of x-ray pulses is critical to optimally exploit advanced photon sources, such as free-electron lasers. The authors present a method based on machine learning which improves the resolution and signal-to-noise ratio of the non-invasive spectral diagnostics available at European XFEL, and streamlines its operation.
- Danilo Enoque Ferreira de Lima
- Arman Davtyan
- Luca Gelisio
