A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis
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 fro...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC and ACA
2022-09-01
|
| Series: | Structural Dynamics |
| Online Access: | http://dx.doi.org/10.1063/4.0000161 |
| _version_ | 1817976763448295424 |
|---|---|
| author | Sathya R. Chitturi Nicolas G. Burdet Youssef Nashed Daniel Ratner Aashwin Mishra T. J. Lane Matthew Seaberg Vincent Esposito Chun Hong Yoon Mike Dunne Joshua J. Turner |
| author_facet | Sathya R. Chitturi Nicolas G. Burdet Youssef Nashed Daniel Ratner Aashwin Mishra T. J. Lane Matthew Seaberg Vincent Esposito Chun Hong Yoon Mike Dunne Joshua J. Turner |
| author_sort | Sathya R. Chitturi |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-13T22:07:55Z |
| format | Article |
| id | doaj.art-41bc58124b1d48d8a8f90cfc53d183a9 |
| institution | Directory Open Access Journal |
| issn | 2329-7778 |
| language | English |
| last_indexed | 2024-04-13T22:07:55Z |
| publishDate | 2022-09-01 |
| publisher | AIP Publishing LLC and ACA |
| record_format | Article |
| series | Structural Dynamics |
| spelling | doaj.art-41bc58124b1d48d8a8f90cfc53d183a92022-12-22T02:27:53ZengAIP Publishing LLC and ACAStructural Dynamics2329-77782022-09-0195054302054302-1410.1063/4.0000161A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysisSathya R. Chitturi0Nicolas G. Burdet1Youssef Nashed2Daniel Ratner3Aashwin Mishra4T. J. Lane5Matthew Seaberg6Vincent Esposito7Chun Hong Yoon8Mike Dunne9Joshua J. Turner10 Department of Materials Science and Engineering, Stanford University, Stanford, California 94305, USA SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA Deutsches Elektronen-Synchrotron, Hamburg, Germany SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA SLAC National Accelerator Laboratory, Menlo Park, California 94025, USA SLAC National Accelerator Laboratory, Menlo Park, California 94025, USAX-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.http://dx.doi.org/10.1063/4.0000161 |
| spellingShingle | Sathya R. Chitturi Nicolas G. Burdet Youssef Nashed Daniel Ratner Aashwin Mishra T. J. Lane Matthew Seaberg Vincent Esposito Chun Hong Yoon Mike Dunne Joshua J. Turner A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis Structural Dynamics |
| title | A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis |
| title_full | A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis |
| title_fullStr | A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis |
| title_full_unstemmed | A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis |
| title_short | A machine learning photon detection algorithm for coherent x-ray ultrafast fluctuation analysis |
| title_sort | machine learning photon detection algorithm for coherent x ray ultrafast fluctuation analysis |
| url | http://dx.doi.org/10.1063/4.0000161 |
| work_keys_str_mv | AT sathyarchitturi amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT nicolasgburdet amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT youssefnashed amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT danielratner amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT aashwinmishra amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT tjlane amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT matthewseaberg amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT vincentesposito amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT chunhongyoon amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT mikedunne amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT joshuajturner amachinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT sathyarchitturi machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT nicolasgburdet machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT youssefnashed machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT danielratner machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT aashwinmishra machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT tjlane machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT matthewseaberg machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT vincentesposito machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT chunhongyoon machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT mikedunne machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis AT joshuajturner machinelearningphotondetectionalgorithmforcoherentxrayultrafastfluctuationanalysis |