DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis

Abstract

X-ray free electron laser experiments have brought unique capabilities and opened new directions in research, such as creating new states of matter or directly measuring atomic motion. One such area is the ability to use finely spaced sets of coherent x-ray pulses to be compared after scattering from a dynamic system at different times. This enables the study of fluctuations in many-body quantum systems at the level of the ultrafast pulse durations, but this method has been limited to a select number of examples and required complex and advanced analytical tools. By applying a new methodology to this problem, we have made qualitative advances in three separate areas that will likely also find application to new fields. As compared to the “droplet-type” models, which typically are used to estimate the photon distributions on pixelated detectors to obtain the coherent x-ray speckle patterns, our algorithm achieves an order of magnitude speedup on CPU hardware and two orders of magnitude improvement on GPU hardware. We also find that it retains accuracy in low-contrast conditions, which is the typical regime for many experiments in structural dynamics. Finally, it can predict photon distributions in high average-intensity applications, a regime which up until now hasmore » not been accessible. Our artificial intelligence-assisted algorithm will enable a wider adoption of x-ray coherence spectroscopies, by both automating previously challenging analyses and enabling new experiments that were not otherwise feasible without the developments described in this work.« less

Authors:
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [2];  [2]; ORCiD logo [3]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [4]
  1. Stanford Univ., CA (United States); SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States). Stanford Institute for Materials and Energy Science (SIMES)
  2. SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States)
  3. Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany)
  4. SLAC National Accelerator Laboratory (SLAC), Menlo Park, CA (United States). Stanford Institute for Materials and Energy Science (SIMES)
Publication Date:
Research Org.:
Stanford Univ., CA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Basic Energy Sciences (BES). Materials Sciences & Engineering Division; USDOE
OSTI Identifier:
1888368
Alternate Identifier(s):
OSTI ID: 1893224
Grant/Contract Number:  
AC02-76SF00515; SC0022216
Resource Type:
Accepted Manuscript
Journal Name:
Structural Dynamics
Additional Journal Information:
Journal Volume: 9; Journal Issue: 5; Related Information: Dataset10.5281/zenodo.6643622; Journal ID: ISSN 2329-7778
Publisher:
American Crystallographic Association/AIP
Country of Publication:
United States
Language:
English
Subject:
47 OTHER INSTRUMENTATION; Machine Learning; Ultrafast X-ray Diffraction; X-ray Photon Correlation Spectroscopy; Ultrafast X-rays; Algorithms and data structure; Artificial neural networks; Coherent spectroscopy; Quantum mechanical systems and processes

Citation Formats

Chitturi, Sathya R., Burdet, Nicolas G., Nashed, Youssef, Ratner, Daniel, Mishra, Aashwin, Lane, T. J., Seaberg, Matthew, Esposito, Vincent, Yoon, Chun Hong, Dunne, Mike, and Turner, Joshua J. A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis. United States: N. p., 2022. Web. doi:10.1063/4.0000161.
Chitturi, Sathya R., Burdet, Nicolas G., Nashed, Youssef, Ratner, Daniel, Mishra, Aashwin, Lane, T. J., Seaberg, Matthew, Esposito, Vincent, Yoon, Chun Hong, Dunne, Mike, & Turner, Joshua J. A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis. United States. https://doi.org/10.1063/4.0000161
Chitturi, Sathya R., Burdet, Nicolas G., Nashed, Youssef, Ratner, Daniel, Mishra, Aashwin, Lane, T. J., Seaberg, Matthew, Esposito, Vincent, Yoon, Chun Hong, Dunne, Mike, and Turner, Joshua J. Mon . "A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis". United States. https://doi.org/10.1063/4.0000161. https://www.osti.gov/servlets/purl/1888368.
@article{osti_1888368,
title = {A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis},
author = {Chitturi, Sathya R. and Burdet, Nicolas G. and Nashed, Youssef and Ratner, Daniel and Mishra, Aashwin and Lane, T. J. and Seaberg, Matthew and Esposito, Vincent and Yoon, Chun Hong and Dunne, Mike and Turner, Joshua J.},
abstractNote = {X-ray free electron laser experiments have brought unique capabilities and opened new directions in research, such as creating new states of matter or directly measuring atomic motion. One such area is the ability to use finely spaced sets of coherent x-ray pulses to be compared after scattering from a dynamic system at different times. This enables the study of fluctuations in many-body quantum systems at the level of the ultrafast pulse durations, but this method has been limited to a select number of examples and required complex and advanced analytical tools. By applying a new methodology to this problem, we have made qualitative advances in three separate areas that will likely also find application to new fields. As compared to the “droplet-type” models, which typically are used to estimate the photon distributions on pixelated detectors to obtain the coherent x-ray speckle patterns, our algorithm achieves an order of magnitude speedup on CPU hardware and two orders of magnitude improvement on GPU hardware. We also find that it retains accuracy in low-contrast conditions, which is the typical regime for many experiments in structural dynamics. Finally, it can predict photon distributions in high average-intensity applications, a regime which up until now has not been accessible. Our artificial intelligence-assisted algorithm will enable a wider adoption of x-ray coherence spectroscopies, by both automating previously challenging analyses and enabling new experiments that were not otherwise feasible without the developments described in this work.},
doi = {10.1063/4.0000161},
journal = {Structural Dynamics},
number = 5,
volume = 9,
place = {United States},
year = {2022},
month = {10}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Figures / Tables:

FIG. 1 FIG. 1: (a) An example of an XPFS detector image over a 90x90 pixelated detector. (b) Corresponding image of the photon map produced by the simulator for the detector image, plotted as the photon distribution per speckle.

Save / Share:

Works referenced in this record:

Linac Coherent Light Source: The first five years
journal, March 2016


Simulated X-ray Photon Fluctuation Spectroscopy Dataset
dataset, January 2022


An unexpectedly low oscillator strength as the origin of the Fe xvii emission problem
journal, December 2012

  • Bernitt, S.; Brown, G. V.; Rudolph, J. K.
  • Nature, Vol. 492, Issue 7428
  • DOI: 10.1038/nature11627

The impact of class imbalance in classification performance metrics based on the binary confusion matrix
journal, July 2019


A compact X-ray free-electron laser emitting in the sub-ångström region
journal, June 2012


Noise reduction in X-ray photon correlation spectroscopy with convolutional neural networks encoder–decoder models
journal, July 2021


First lasing and operation of an ångstrom-wavelength free-electron laser
journal, August 2010


Towards ultrafast dynamics with split-pulse X-ray photon correlation spectroscopy at free electron laser sources
journal, April 2018


Investigation of Nonequilibrium Electronic Dynamics of Warm Dense Copper with Femtosecond X-Ray Absorption Spectroscopy
journal, October 2021


Application of an ePix100 detector for coherent scattering using a hard X-ray free-electron laser
journal, August 2016

  • Sikorski, Marcin; Feng, Yiping; Song, Sanghoon
  • Journal of Synchrotron Radiation, Vol. 23, Issue 5
  • DOI: 10.1107/S1600577516010869

Enhanced charge density wave coherence in a light-quenched, high-temperature superconductor
journal, May 2022


X-ray speckle visibility spectroscopy in the single-photon limit
journal, February 2013

  • DeCaro, Curt; Karunaratne, Vidanage Nuwan; Bera, Sambhunath
  • Journal of Synchrotron Radiation, Vol. 20, Issue 2
  • DOI: 10.1107/S0909049512051825

Resonant inelastic x-ray scattering studies of elementary excitations
journal, June 2011

  • Ament, Luuk J. P.; van Veenendaal, Michel; Devereaux, Thomas P.
  • Reviews of Modern Physics, Vol. 83, Issue 2
  • DOI: 10.1103/RevModPhys.83.705

Ultrafast processing of pixel detector data with machine learning frameworks
conference, January 2019

  • Blaj, G.; Chang, C. -E.; Kenney, C. J.
  • PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON SYNCHROTRON RADIATION INSTRUMENTATION – SRI2018, AIP Conference Proceedings
  • DOI: 10.1063/1.5084708

Atomic-Scale Perspective of Ultrafast Charge Transfer at a Dye–Semiconductor Interface
journal, July 2014

  • Siefermann, Katrin R.; Pemmaraju, Chaitanya D.; Neppl, Stefan
  • The Journal of Physical Chemistry Letters, Vol. 5, Issue 15
  • DOI: 10.1021/jz501264x

A MHz-repetition-rate hard X-ray free-electron laser driven by a superconducting linear accelerator
journal, May 2020


Hard X-ray free-electron laser with femtosecond-scale timing jitter
journal, October 2017


Direct measurement of antiferromagnetic domain fluctuations
journal, May 2007

  • Shpyrko, O. G.; Isaacs, E. D.; Logan, J. M.
  • Nature, Vol. 447, Issue 7140
  • DOI: 10.1038/nature05776

Speckle-visibility spectroscopy: A tool to study time-varying dynamics
journal, September 2005

  • Bandyopadhyay, R.; Gittings, A. S.; Suh, S. S.
  • Review of Scientific Instruments, Vol. 76, Issue 9
  • DOI: 10.1063/1.2037987

Bootstrap Methods: Another Look at the Jackknife
book, January 1992


A review of online learning in supervised neural networks
journal, December 2013

  • Jain, Lakhmi C.; Seera, Manjeevan; Lim, Chee Peng
  • Neural Computing and Applications, Vol. 25, Issue 3-4
  • DOI: 10.1007/s00521-013-1534-4

Creation and diagnosis of a solid-density plasma with an X-ray free-electron laser
journal, January 2012

  • Vinko, S. M.; Ciricosta, O.; Cho, B. I.
  • Nature, Vol. 482, Issue 7383
  • DOI: 10.1038/nature10746

A compact and cost-effective hard X-ray free-electron laser driven by a high-brightness and low-energy electron beam
journal, November 2020


Evaluating collaborative filtering recommender systems
journal, January 2004

  • Herlocker, Jonathan L.; Konstan, Joseph A.; Terveen, Loren G.
  • ACM Transactions on Information Systems, Vol. 22, Issue 1
  • DOI: 10.1145/963770.963772

NN-SVG: Publication-Ready Neural Network Architecture Schematics
journal, January 2019


Compact hard x-ray split-delay system based on variable-gap channel-cut crystals
journal, January 2019

  • Sun, Yanwen; Wang, Nan; Song, Sanghoon
  • Optics Letters, Vol. 44, Issue 10
  • DOI: 10.1364/OL.44.002582

Absolute contrast estimation for soft X-ray photon fluctuation spectroscopy using a variational droplet model
journal, September 2021


Tunable x-ray free electron laser multi-pulses with nanosecond separation
journal, February 2022


Accurate contrast determination for X-ray speckle visibility spectroscopy
journal, June 2020

  • Sun, Yanwen; Montana-Lopez, Jordi; Fuoss, Paul
  • Journal of Synchrotron Radiation, Vol. 27, Issue 4
  • DOI: 10.1107/S1600577520006773

Outlook for artificial intelligence and machine learning at the NSLS-II
journal, March 2021

  • Campbell, Stuart I.; Allan, Daniel B.; Barbour, Andi M.
  • Machine Learning: Science and Technology, Vol. 2, Issue 1
  • DOI: 10.1088/2632-2153/abbd4e

A review of X-ray intensity fluctuation spectroscopy
journal, June 2008


Orbital-specific mapping of the ligand exchange dynamics of Fe(CO)5 in solution
journal, April 2015


Nanosecond X-Ray Photon Correlation Spectroscopy on Magnetic Skyrmions
journal, August 2017


A snapshot review—Fluctuations in quantum materials: from skyrmions to superconductivity
journal, April 2021


High Contrast X-ray Speckle from Atomic-Scale Order in Liquids and Glasses
journal, November 2012


Measuring temporal speckle correlations at ultrafast x-ray sources
journal, December 2008


Natively Inhibited Trypanosoma brucei Cathepsin B Structure Determined by Using an X-ray Laser
journal, November 2012