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...
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |