X-ray free-electron lasers (XFELs) are the world's fastest X-ray cameras, providing ultrashort exposure times in combination with a spatial resolution limit down to the sub-nanometer range, which allows for time-resolved experiments'freezing' the motion of atoms and molecules. In fact, XFELs have revolutionized several fields of science enabling us to observe the role of transient structures and resonances in atoms1 as well as single-molecule or cluster imaging2, investigations of ultrafast processes at element-specific observer sites3, and the study of nonlinear light–matter interaction in the X-ray regime4. Over the past decade, further development of the underlying machine operation techniques has enabled increasingly sophisticated control over the photon pulse parameters. One of the most recent major upgrades is the increased repetition rate of XFELs that is anticipated to initiate a leap from proof-of-principle experiments to advanced applications of interdisciplinary importance, thus representing a cornerstone of modern XFEL science5. Most of the FELs and in fact all XFELs worldwide are currently based on the principle of self-amplification of spontaneous emission (SASE)6. More precisely, their pulses are formed stochastically through the interplay between the relativistically accelerated electron bunches themselves and the spontaneously emitted synchrotron radiation, caused by their sinusoidal trajectories inside magnetic structures with periodically changing polarity, so-called undulators.

Ultrafast pulses from X-ray lasers reveal how atoms move at timescales of a femtosecond. However, measuring the properties of the pulses themselves is challenging. While determining a pulse's maximum strength, or'amplitude,' is straightforward, the time at which the pulse reaches the maximum, or'phase,' is often hidden. A new study trains neural networks to analyze the pulse to reveal these hidden sub-components. Physicists also call these sub-components'real' and'imaginary.' Starting from low-resolution measurements, the neural networks reveal finer details with each pulse, and they can analyze pulses millions of times faster than previous methods.

X-ray free-electron lasers (XFELs) as the world`s most brilliant light sources provide ultrashort X-ray pulses with durations typically on the order of femtoseconds. Recently, they have approached and entered the attosecond regime, which holds new promises for single-molecule imaging and studying nonlinear and ultrafast phenomena like localized electron dynamics. The technological evolution of XFELs toward well-controllable light sources for precise metrology of ultrafast processes was, however, hampered by the diagnostic capabilities for characterizing X-ray pulses at the attosecond frontier. In this regard, 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 artificial intelligence algorithms, in particular convolutional neural networks, we here show how this technique can be leveraged from its proof-of-principle stage toward routine diagnostics at XFELs, thus enhancing and refining their scientific access in all related disciplines.

Current Flash X-ray single-particle diffraction Imaging (FXI) experiments, which operate on modern X-ray Free Electron Lasers (XFELs), can record millions of interpretable diffraction patterns from individual biomolecules per day. Due to the stochastic nature of the XFELs, those patterns will to a varying degree include scatterings from contaminated samples. Also, the heterogeneity of the sample biomolecules is unavoidable and complicates data processing. Reducing the data volumes and selecting high-quality single-molecule patterns are therefore critical steps in the experimental set-up. In this paper, we present two supervised template-based learning methods for classifying FXI patterns. Our Eigen-Image and Log-Likelihood classifier can find the best-matched template for a single-molecule pattern within a few milliseconds. It is also straightforward to parallelize them so as to fully match the XFEL repetition rate, thereby enabling processing at site.

An investigation, recently published in Nature, and carried out by scientists at Stockholm University has shown that liquid water is much more complex than meets the eye. With the use of the x-ray laser at the SLAC National Accelerator Laboratory in California the team of scientists have probed the finer movements of liquid water on incredibly short timescales. 'A schematic of the approach used to capture water dynamics on the ultrafast timescale. If one were able to photograph the molecules in real space with different exposure times, the image would become gradually blurry because of the motion of the molecules. This is done with x-ray scattering in the so-called reciprocal space, where the diffraction pattern is gradually smoother for longer pulse durations.' This experimental investigation is the first of its kind to'photograph' water molecules on timescales as short as millionths of a billionth of a second.