Parts | Days | Selection | Search | Updates | Downloads | Help
A: Fachverband Atomphysik
A 30: Atomic Physics, Molecular Physics, and Quantum Optics with X-ray FELs (joint session MO/A)
A 30.3: Talk
Thursday, March 14, 2019, 11:00–11:15, S HS 002 Biologie
Neural Networks for Reconstruction of Nanoclusters from Soft X-Ray Scattering Images — •Thomas Stielow, Robin Schmidt, Thomas Fennel, and Stefan Scheel — Institut für Physik, Universität Rostock, Albert-Einstein-Straße 23, 18059 Rostock
Single-shot diffraction imaging by soft X-ray laser pulses is a valuable tool for structural analyses of unsupported and short-lived nanosystems, although inversion of the scattering patterns still prove challenging. Deep learning, on the other hand, is widely used in data sciences for the extraction of information from images and sees more and more application in various sciences. We demonstrate how neural networks can be utilized for full reconstructions of nanoclusters from single-shot wide angle scattering images. Our networks are trained solely on existing physical theories and can be applied to real-world experimental data without limitation to a specific setup due to its robustness. With deep learning, high quality real time evalutation for the next generation FEL systems can finally be implemented.