Deep neural networks for classifying complex features in diffraction images

Zimmermann, Julian; Langbehn, Bruno; Cucini, Riccardo; Di Fraia, Michele; Finetti, Paola; LaForge, Aaron C.; Nishiyama, Toshiyuki; Oycharenko, Yevheniy; Piseri, Paolo; Plekan, Oksana; Prince, Kevin C.; Stienkemeier, Frank; Ueda, Kiyoshi; Callegari, Carlo; Moeller, Thomas; Rupp, Daniela: Phys. Rev. E 99 (2019) 063309 [DOI: 10.1103/PhysRevE.99.063309]

Intense short-wavelength pulses from free-electron lasers and high-harmonic-generation sources enable diffractive imaging of individual nanosized objects with a single x-ray laser shot. The enormous data sets with up to several million diffraction patterns present a severe problem for data analysis because of the high dimensionality of imaging data. Feature recognition and selection is a crucial step to reduce the dimensionality. Usually, custom-made algorithms are developed at a considerable effort to approximate the particular features connected to an individual specimen, but because they face different experimental conditions, these approaches do not generalize well. On the other hand, deep neural networks are the principal instrument for today's revolution in automated image recognition, a development that has not been adapted to its full potential for data analysis in science. We recently published {[}Langbehn et al., Phys. Rev. Lett. 121, 255301 (2018)] the application of a deep neural network as a feature extractor for wide-angle diffraction images of helium nanodroplets. Here we present the setup, our modifications, and the training process of the deep neural network for diffraction image classification and its systematic bench marking. We find that deep neural networks significantly outperform previous attempts for sorting and classifying complex diffraction patterns and are a significant improvement for the much-needed assistance during postprocessing of large amounts of experimental coherent diffraction imaging data.

Affiliation: Zimmermann, J (Reprint Author), Max Born Inst Nichtlineare Opt & Kurzzeitspektros, D-12489 Berlin, Germany. Zimmermann, Julian; Rupp, Daniela, Max Born Inst Nichtlineare Opt & Kurzzeitspektros, D-12489 Berlin, Germany. Langbehn, Bruno; Oycharenko, Yevheniy; Moeller, Thomas, Tech Univ Berlin, Inst Opt & Atomare Phys, D-10623 Berlin, Germany. Cucini, Riccardo; Di Fraia, Michele; Finetti, Paola; Plekan, Oksana; Prince, Kevin C.; Callegari, Carlo, Elettra Sincrotrone Trieste SCpA, I-34149 Trieste, Italy. Di Fraia, Michele; Callegari, Carlo, CNR, Ist Struttura Mat, LD2 Unit, I-34149 Trieste, Italy. LaForge, Aaron C.; Stienkemeier, Frank, Univ Freiburg, Inst Phys, D-79104 Freiburg, Germany. Nishiyama, Toshiyuki, Kyoto Univ, Div Phys & Astron, Grad Sch Sci, Kyoto 6068502, Japan. Oycharenko, Yevheniy, European XFEL GmbH, D-22869 Schenefeld, Germany. Piseri, Paolo, Univ Milan, CIMAINA, I-20133 Milan, Italy. Piseri, Paolo, Univ Milan, Dipartimento Fis, I-20133 Milan, Italy. Prince, Kevin C., Swinburne Univ Technol, Dept Chem & Biotechnol, Hawthorn, Vic 3122, Australia. Ueda, Kiyoshi, Tohoku Univ, Inst Multidisciplinary Res Adv Mat, Sendai, Miyagi 9808577, Japan.