Laserlab-Europe Talk on AI for X-ray scattering
We are pleased to announce the Laserlab-Europe Talk on AI for X-ray scattering that will take place on Wednesday, 8 June 2022, at 4pm CET
Speaker: Nico Hoffman (HZDR)
Moderation: Dusan Chorvat (ILC)
The long term and sustainable success of the X-ray community essentially depends on its ability to meet growing challenges in handling and analyzing data of increasing volume and complexity.
Machine Learning (ML) provide a smart solution enabling dramatically increasing the output of X-ray scattering facilities regarding acceleration of the data analysis, optimization of beam time usage and, consequently, growth of publication rate. Analysis of scattering data is a very time-consuming process as it requires solving an ill-posed inverse problem to infer properties of the imaged object.
We will be discussing two state-of-the-art methods to solve this task: 1) ML-based estimation of the most important parameters of the object in a single step given the experimentally acquired scattering image; 2) Iterative ML-assisted phasing based on automatic differentiation that can be very easily used for fast reconstruction of multiple X-ray scattering modalities such as CDI, mono- & polychromatic Ptychography as well as Holography.
Some parameters exhibit low contribution to the acquired data which also hampers reliable predictions and discrimination of these parameters. We show that normalising flows can be used to recover the predictive posterior distribution of these parameters to resolve ambiguous situations and provide information about the reliability of the estimate.
---
The Laserlab-Europe Talks consist of a series of online seminars and panel discussions proposed and organised by our community on specific topics (thematic or research-specific) and provide a platform for regular information exchange and knowledge sharing.
The talks take place bi-weekly on Wednesday afternoons at 16h00 CET and are open to all interested parties, from PhD students to experts in the field and industrial and medical partners as appropriate.