Parts | Days | Selection | Search | Updates | Downloads | Help

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 1: Poster

AKPIK 1.3: Poster

Monday, March 20, 2023, 16:00–18:00, HSZ OG2

Amortized Bayesian Inference of GISAXS Data with Normalizing Flows — •Maksim Zhdanov¹, Lisa Randolph², Thomas Kluge¹, Motoaki Nakatsutsumi², Christian Gutt³, Michael Bussmann⁵, Marina Ganeva⁴, and Nico Hoffmann¹ — ¹HZDR, Dresden, Germany — ²European XFEL, Germany — ³University of Siegen, Siegen, Germany — ⁴Forschungszentrum Jülich, Jülich, Germany — ⁵CASUS, Görlitz, Germany

Grazing-Incidence Small-Angle X-ray Scattering (GISAXS) is a modern imaging technique used in material research to study nanoscale materials. Reconstruction of the parameters of an imaged object imposes an ill-posed inverse problem that is further complicated when only an in-plane GISAXS signal is available. Traditionally used inference algorithms such as Approximate Bayesian Computation (ABC) rely on computationally expensive scattering simulation software, rendering analysis highly time-consuming. We propose a simulation-based framework that combines variational auto-encoders and normalizing flows to estimate the posterior distribution of object parameters given its GISAXS data. We apply the inference pipeline to experimental data and demonstrate that our method reduces the inference cost by orders of magnitude while producing consistent results with ABC.