Research Highlight | Center for Nanoscale Materials

Data-driven approach to extract dynamics from coherent X-ray data
In a study published in npj Computational Materials, researchers used machine learning to develop a data-driven platform that models previously inaccessible complex, real-space dynamics from time-resolved coherent X-ray scattering.
Data-driven approach to extract dynamics from coherent X-ray data image
Top: Given the initial system state x0, the neural differential equation (DE), parameterized by trainable weights θ, is integrated numerically to obtain the predicted time evolution of the system state The corresponding scattered intensity is obtained by applying the CXS forward model to the predicted value. The loss function compares the predicted intensity against the target intensity. Bottom: a Schematic of the neural network architecture modeling the fluctuation dynamics. b Illustration of a time-evolving field-of-view as a result of source fluctuation. The black dashed circle denotes one standard deviation from the maximum of the Gaussian illumination function.

Scientific Achievement

A data-driven platform based on scientific machine learning has been developed to model complex, real-space dynamics from time-resolved coherent X-ray scattering (CXS) measurements. These data enable estimation of long-term dynamics well beyond the maximum observation time.

Significance and Impact

The platform allows visualizing previously inaccessible dynamics based on a few initial high-fidelity measurements followed by fast scans to infer dynamics.

Research Details

  • The platform was tested in three simulation cases and an experimental proof-of-concept with an X-ray ptychographic scan.

DOI: 10.1038/s41524-024-01365-9

Download this highlight

About Argonne’s Center for Nanoscale Materials

The Center for Nanoscale Materials is one of the five DOE Nanoscale Science Research Centers, premier national user facilities for interdisciplinary research at the nanoscale supported by the DOE Office of Science. Together the NSRCs comprise a suite of complementary facilities that provide researchers with state-of-the-art capabilities to fabricate, process, characterize and model nanoscale materials, and constitute the largest infrastructure investment of the National Nanotechnology Initiative. The NSRCs are located at DOE’s Argonne, Brookhaven, Lawrence Berkeley, Oak Ridge, Sandia and Los Alamos National Laboratories. For more information about the DOE NSRCs, please visit https://​sci​ence​.osti​.gov/​U​s​e​r​-​F​a​c​i​l​i​t​i​e​s​/​U​s​e​r​-​F​a​c​i​l​i​t​i​e​s​-​a​t​-​a​-​G​lance.

Argonne National Laboratory seeks solutions to pressing national problems in science and technology by conducting leading-edge basic and applied research in virtually every scientific discipline. Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.

The U.S. Department of Energy’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit https://​ener​gy​.gov/​s​c​ience.