Machine learning for experimental design of ultrafast electron diffraction

Abstract Ultrafast electron diffraction (UED) experiments can extract insights into material behavior at ultrafast timescales but are limited by the manual analysis required to process several gigabytes of diffraction pattern data. The lack of real-time data prevents in situ tuning of experimental p...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohammad Shaaban, Sami El-Borgi, Aravind Krishnamoorthy
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-06779-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849768819365511168
author Mohammad Shaaban
Sami El-Borgi
Aravind Krishnamoorthy
author_facet Mohammad Shaaban
Sami El-Borgi
Aravind Krishnamoorthy
author_sort Mohammad Shaaban
collection DOAJ
description Abstract Ultrafast electron diffraction (UED) experiments can extract insights into material behavior at ultrafast timescales but are limited by the manual analysis required to process several gigabytes of diffraction pattern data. The lack of real-time data prevents in situ tuning of experimental parameters toward desirable material dynamics or avoid sample damage. We demonstrate that machine learning methods based on Convolutional Neural Networks trained on synthetic and experimental diffraction patterns can perform real-time analysis of diffraction data to resolve dynamical processes in a representative material, $${\textrm{MoTe}_{2}}$$ , and identify signs of material damage. By building on CNN’s ability to learn compressed representations of diffraction patterns that map to distinct material dynamics, we construct Convolutional Variational Autoencoder models to track structural phase transformation in a model material system through the time trajectory of UED images in the low-dimensional latent space. Such models enable real-time steering of experimental parameters towards conditions that realize phase transformations or other desirable outcomes by mapping experimental conditions to distinct regions of the latent space. These examples show the ability of machine learning to design self-correcting diffraction experiments to optimize the use of large-scale user facilities.
format Article
id doaj-art-7e555b940dfd457587a0134ed5b4dd21
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7e555b940dfd457587a0134ed5b4dd212025-08-20T03:03:40ZengNature PortfolioScientific Reports2045-23222025-07-011511910.1038/s41598-025-06779-zMachine learning for experimental design of ultrafast electron diffractionMohammad Shaaban0Sami El-Borgi1Aravind Krishnamoorthy2 Department of Mechanical Engineering, Texas A & M UniversityCollege of Science and Engineering, Hamad Bin Khalifa University Department of Mechanical Engineering, Texas A & M UniversityAbstract Ultrafast electron diffraction (UED) experiments can extract insights into material behavior at ultrafast timescales but are limited by the manual analysis required to process several gigabytes of diffraction pattern data. The lack of real-time data prevents in situ tuning of experimental parameters toward desirable material dynamics or avoid sample damage. We demonstrate that machine learning methods based on Convolutional Neural Networks trained on synthetic and experimental diffraction patterns can perform real-time analysis of diffraction data to resolve dynamical processes in a representative material, $${\textrm{MoTe}_{2}}$$ , and identify signs of material damage. By building on CNN’s ability to learn compressed representations of diffraction patterns that map to distinct material dynamics, we construct Convolutional Variational Autoencoder models to track structural phase transformation in a model material system through the time trajectory of UED images in the low-dimensional latent space. Such models enable real-time steering of experimental parameters towards conditions that realize phase transformations or other desirable outcomes by mapping experimental conditions to distinct regions of the latent space. These examples show the ability of machine learning to design self-correcting diffraction experiments to optimize the use of large-scale user facilities.https://doi.org/10.1038/s41598-025-06779-zMachine learningUltrafast electron diffractionVariational autoencoderSelf-supervised learningExperimental design
spellingShingle Mohammad Shaaban
Sami El-Borgi
Aravind Krishnamoorthy
Machine learning for experimental design of ultrafast electron diffraction
Scientific Reports
Machine learning
Ultrafast electron diffraction
Variational autoencoder
Self-supervised learning
Experimental design
title Machine learning for experimental design of ultrafast electron diffraction
title_full Machine learning for experimental design of ultrafast electron diffraction
title_fullStr Machine learning for experimental design of ultrafast electron diffraction
title_full_unstemmed Machine learning for experimental design of ultrafast electron diffraction
title_short Machine learning for experimental design of ultrafast electron diffraction
title_sort machine learning for experimental design of ultrafast electron diffraction
topic Machine learning
Ultrafast electron diffraction
Variational autoencoder
Self-supervised learning
Experimental design
url https://doi.org/10.1038/s41598-025-06779-z
work_keys_str_mv AT mohammadshaaban machinelearningforexperimentaldesignofultrafastelectrondiffraction
AT samielborgi machinelearningforexperimentaldesignofultrafastelectrondiffraction
AT aravindkrishnamoorthy machinelearningforexperimentaldesignofultrafastelectrondiffraction