Inversion of Ultrafast X-ray Scattering with Dynamics Constraints

Martin Asenov, Nikola Zotev, Subramanian Ramamoorthy, Adam Kirrander

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Studying molecular transformations on an ultrafast time-scale is vital for understanding chemical reactivity, but interpreting the relevant experiments is challenging because chemical dynamics need to be inferred from an indirect and often incomplete sequence of observations. We propose a method that uses a form of variational recurrent neural network to tackle the problem of inversion of time resolved X-ray scattering from molecules recorded on a detector. By training our model with molecular trajectories, dynamic correlations and constraints associated with molecular motion can be learned. We show this leads to a more accurate inversion from a detector signal to atom-atom distances, compared to the traditional frame-by-frame approach.
Original languageEnglish
Title of host publicationMachine Learning and the Physical Sciences
Subtitle of host publicationWorkshop at the 34th Conference on Neural Information Processing Systems (NeurIPS) December 11, 2020
Number of pages7
Publication statusE-pub ahead of print - 11 Dec 2020
EventMachine Learning and the Physical Sciences: Workshop at the 34th Conference on Neural Information Processing Systems (NeurIPS) - Online
Duration: 11 Dec 2020 → …
https://ml4physicalsciences.github.io/2020/

Workshop

WorkshopMachine Learning and the Physical Sciences
Period11/12/20 → …
Internet address

Fingerprint

Dive into the research topics of 'Inversion of Ultrafast X-ray Scattering with Dynamics Constraints'. Together they form a unique fingerprint.

Cite this