Prediction on X-ray output of free electron laser based on artificial neural networks

Abstract Knowledge of x-ray free electron lasers’ (XFELs) pulse characteristics delivered to a sample is crucial for ensuring high-quality x-rays for scientific experiments. XFELs’ self-amplified spontaneous emission process causes spatial and spectral variations in x-ray pulses entering a sample, w...

Full description

Bibliographic Details
Main Authors: Kenan Li, Guanqun Zhou, Yanwei Liu, Juhao Wu, Ming-fu Lin, Xinxin Cheng, Alberto A. Lutman, Matthew Seaberg, Howard Smith, Pranav A. Kakhandiki, Anne Sakdinawat
Format: Article
Language:English
Published: Nature Portfolio 2023-11-01
Series:Nature Communications
Online Access:https://doi.org/10.1038/s41467-023-42573-z
_version_ 1797630132579467264
author Kenan Li
Guanqun Zhou
Yanwei Liu
Juhao Wu
Ming-fu Lin
Xinxin Cheng
Alberto A. Lutman
Matthew Seaberg
Howard Smith
Pranav A. Kakhandiki
Anne Sakdinawat
author_facet Kenan Li
Guanqun Zhou
Yanwei Liu
Juhao Wu
Ming-fu Lin
Xinxin Cheng
Alberto A. Lutman
Matthew Seaberg
Howard Smith
Pranav A. Kakhandiki
Anne Sakdinawat
author_sort Kenan Li
collection DOAJ
description Abstract Knowledge of x-ray free electron lasers’ (XFELs) pulse characteristics delivered to a sample is crucial for ensuring high-quality x-rays for scientific experiments. XFELs’ self-amplified spontaneous emission process causes spatial and spectral variations in x-ray pulses entering a sample, which leads to measurement uncertainties for experiments relying on multiple XFEL pulses. Accurate in-situ measurements of x-ray wavefront and energy spectrum incident upon a sample poses challenges. Here we address this by developing a virtual diagnostics framework using an artificial neural network (ANN) to predict x-ray photon beam properties from electron beam properties. We recorded XFEL electron parameters while adjusting the accelerator’s configurations and measured the resulting x-ray wavefront and energy spectrum shot-to-shot. Training the ANN with this data enables effective prediction of single-shot or average x-ray beam output based on XFEL undulator and electron parameters. This demonstrates the potential of utilizing ANNs for virtual diagnostics linking XFEL electron and photon beam properties.
first_indexed 2024-03-11T11:03:42Z
format Article
id doaj.art-d2d6533216124825a96d2273d4a0d118
institution Directory Open Access Journal
issn 2041-1723
language English
last_indexed 2024-03-11T11:03:42Z
publishDate 2023-11-01
publisher Nature Portfolio
record_format Article
series Nature Communications
spelling doaj.art-d2d6533216124825a96d2273d4a0d1182023-11-12T12:23:12ZengNature PortfolioNature Communications2041-17232023-11-011411910.1038/s41467-023-42573-zPrediction on X-ray output of free electron laser based on artificial neural networksKenan Li0Guanqun Zhou1Yanwei Liu2Juhao Wu3Ming-fu Lin4Xinxin Cheng5Alberto A. Lutman6Matthew Seaberg7Howard Smith8Pranav A. Kakhandiki9Anne Sakdinawat10SLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabSLAC National Accelerator LabAbstract Knowledge of x-ray free electron lasers’ (XFELs) pulse characteristics delivered to a sample is crucial for ensuring high-quality x-rays for scientific experiments. XFELs’ self-amplified spontaneous emission process causes spatial and spectral variations in x-ray pulses entering a sample, which leads to measurement uncertainties for experiments relying on multiple XFEL pulses. Accurate in-situ measurements of x-ray wavefront and energy spectrum incident upon a sample poses challenges. Here we address this by developing a virtual diagnostics framework using an artificial neural network (ANN) to predict x-ray photon beam properties from electron beam properties. We recorded XFEL electron parameters while adjusting the accelerator’s configurations and measured the resulting x-ray wavefront and energy spectrum shot-to-shot. Training the ANN with this data enables effective prediction of single-shot or average x-ray beam output based on XFEL undulator and electron parameters. This demonstrates the potential of utilizing ANNs for virtual diagnostics linking XFEL electron and photon beam properties.https://doi.org/10.1038/s41467-023-42573-z
spellingShingle Kenan Li
Guanqun Zhou
Yanwei Liu
Juhao Wu
Ming-fu Lin
Xinxin Cheng
Alberto A. Lutman
Matthew Seaberg
Howard Smith
Pranav A. Kakhandiki
Anne Sakdinawat
Prediction on X-ray output of free electron laser based on artificial neural networks
Nature Communications
title Prediction on X-ray output of free electron laser based on artificial neural networks
title_full Prediction on X-ray output of free electron laser based on artificial neural networks
title_fullStr Prediction on X-ray output of free electron laser based on artificial neural networks
title_full_unstemmed Prediction on X-ray output of free electron laser based on artificial neural networks
title_short Prediction on X-ray output of free electron laser based on artificial neural networks
title_sort prediction on x ray output of free electron laser based on artificial neural networks
url https://doi.org/10.1038/s41467-023-42573-z
work_keys_str_mv AT kenanli predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT guanqunzhou predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT yanweiliu predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT juhaowu predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT mingfulin predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT xinxincheng predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT albertoalutman predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT matthewseaberg predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT howardsmith predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT pranavakakhandiki predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks
AT annesakdinawat predictiononxrayoutputoffreeelectronlaserbasedonartificialneuralnetworks