Deep learning of structural morphology imaged by scanning X-ray diffraction microscopy
Abstract Scanning X-ray nanodiffraction microscopy is a powerful technique for spatially resolving nanoscale structural morphologies by diffraction contrast. One of the critical challenges in experimental nanodiffraction data analysis is posed by the convergence angle of nanoscale focusing optics wh...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-97183-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849769382832504832 |
|---|---|
| author | Aileen Luo Tao Zhou Martin V. Holt Andrej Singer Mathew J. Cherukara |
| author_facet | Aileen Luo Tao Zhou Martin V. Holt Andrej Singer Mathew J. Cherukara |
| author_sort | Aileen Luo |
| collection | DOAJ |
| description | Abstract Scanning X-ray nanodiffraction microscopy is a powerful technique for spatially resolving nanoscale structural morphologies by diffraction contrast. One of the critical challenges in experimental nanodiffraction data analysis is posed by the convergence angle of nanoscale focusing optics which creates simultaneous dependency of the far-field scattering data on three independent components of the local strain tensor—corresponding to dilation and two potential rigid body rotations of the unit cell. All three components are in principle resolvable through a spatially mapped sample tilt series; however, traditional data analysis is computationally expensive and prone to artifacts. In this study, we implement NanobeamNN, a convolutional neural network specifically tailored to the analysis of scanning probe X-ray microscopy data. NanobeamNN learns lattice strain and rotation angles from simulated diffraction of a focused X-ray nanobeam by an epitaxial thin film and can directly make reasonable predictions on experimental data without the need for additional fine-tuning. We demonstrate that this approach represents a significant advancement in computational speed over conventional methods, as well as a potential improvement in accuracy over the current standard. |
| format | Article |
| id | doaj-art-b593b3c3adef4506a68f604f8d42dbde |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b593b3c3adef4506a68f604f8d42dbde2025-08-20T03:03:25ZengNature PortfolioScientific Reports2045-23222025-07-0115111010.1038/s41598-025-97183-0Deep learning of structural morphology imaged by scanning X-ray diffraction microscopyAileen Luo0Tao Zhou1Martin V. Holt2Andrej Singer3Mathew J. Cherukara4Department of Materials Science and Engineering, Cornell UniversityCenter for Nanoscale Materials, Argonne National LaboratoryCenter for Nanoscale Materials, Argonne National LaboratoryDepartment of Materials Science and Engineering, Cornell UniversityAdvanced Photon Source, Argonne National LaboratoryAbstract Scanning X-ray nanodiffraction microscopy is a powerful technique for spatially resolving nanoscale structural morphologies by diffraction contrast. One of the critical challenges in experimental nanodiffraction data analysis is posed by the convergence angle of nanoscale focusing optics which creates simultaneous dependency of the far-field scattering data on three independent components of the local strain tensor—corresponding to dilation and two potential rigid body rotations of the unit cell. All three components are in principle resolvable through a spatially mapped sample tilt series; however, traditional data analysis is computationally expensive and prone to artifacts. In this study, we implement NanobeamNN, a convolutional neural network specifically tailored to the analysis of scanning probe X-ray microscopy data. NanobeamNN learns lattice strain and rotation angles from simulated diffraction of a focused X-ray nanobeam by an epitaxial thin film and can directly make reasonable predictions on experimental data without the need for additional fine-tuning. We demonstrate that this approach represents a significant advancement in computational speed over conventional methods, as well as a potential improvement in accuracy over the current standard.https://doi.org/10.1038/s41598-025-97183-0 |
| spellingShingle | Aileen Luo Tao Zhou Martin V. Holt Andrej Singer Mathew J. Cherukara Deep learning of structural morphology imaged by scanning X-ray diffraction microscopy Scientific Reports |
| title | Deep learning of structural morphology imaged by scanning X-ray diffraction microscopy |
| title_full | Deep learning of structural morphology imaged by scanning X-ray diffraction microscopy |
| title_fullStr | Deep learning of structural morphology imaged by scanning X-ray diffraction microscopy |
| title_full_unstemmed | Deep learning of structural morphology imaged by scanning X-ray diffraction microscopy |
| title_short | Deep learning of structural morphology imaged by scanning X-ray diffraction microscopy |
| title_sort | deep learning of structural morphology imaged by scanning x ray diffraction microscopy |
| url | https://doi.org/10.1038/s41598-025-97183-0 |
| work_keys_str_mv | AT aileenluo deeplearningofstructuralmorphologyimagedbyscanningxraydiffractionmicroscopy AT taozhou deeplearningofstructuralmorphologyimagedbyscanningxraydiffractionmicroscopy AT martinvholt deeplearningofstructuralmorphologyimagedbyscanningxraydiffractionmicroscopy AT andrejsinger deeplearningofstructuralmorphologyimagedbyscanningxraydiffractionmicroscopy AT mathewjcherukara deeplearningofstructuralmorphologyimagedbyscanningxraydiffractionmicroscopy |