Die DPG-Frühjahrstagung in Hannover musste abgesagt werden! Lesen Sie mehr ...

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

MO: Fachverband Molekülphysik

MO 5: MO Poster 1

MO 5.3: Poster

Montag, 9. März 2020, 17:00–19:00, Empore Lichthof

Reconstructing Nanoclusters from Single Wide-Angle Scattering Images with Neural Networks — •Thomas Stielow, 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 [1]. 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. Recently, several advances have showcased how the predictive power of neural networks can be harnessed for extracting certain features from wide angle X-ray scattering patterns [2,3]. We aim to solve the full inversion problem of wide-angle X-ray scattering with neural networks. Our appraoch is based on reconstructing the scatterer’s density based on a training set of arbitrary convex bodies. We demonstrate the predicitve capability of the trained networks by using real-world experimental data.

[1] I. Barke et al., Nat. Comm. 6, 6187 (2015).

[2] J. Zimmermann, et al., Phys. Rev. E, 063309 (2019).

[2] T. Stielow et al., arXiv:1906.06883 (2019).