A convolutional neural network for defect classification in Bragg coherent X-ray diffraction
Abstract Coherent diffraction imaging enables the imaging of individual defects, such as dislocations or stacking faults, in materials. These defects and their surrounding elastic strain fields have a critical influence on the macroscopic properties and functionality of materials. However, their ide...
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/d32e14700bf3406999829daa027da33c |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:d32e14700bf3406999829daa027da33c |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:d32e14700bf3406999829daa027da33c2021-12-02T17:55:12ZA convolutional neural network for defect classification in Bragg coherent X-ray diffraction10.1038/s41524-021-00583-92057-3960https://doaj.org/article/d32e14700bf3406999829daa027da33c2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00583-9https://doaj.org/toc/2057-3960Abstract Coherent diffraction imaging enables the imaging of individual defects, such as dislocations or stacking faults, in materials. These defects and their surrounding elastic strain fields have a critical influence on the macroscopic properties and functionality of materials. However, their identification in Bragg coherent diffraction imaging remains a challenge and requires significant data mining. The ability to identify defects from the diffraction pattern alone would be a significant advantage when targeting specific defect types and accelerates experiment design and execution. Here, we exploit a computational tool based on a three-dimensional (3D) parametric atomistic model and a convolutional neural network to predict dislocations in a crystal from its 3D coherent diffraction pattern. Simulated diffraction patterns from several thousands of relaxed atomistic configurations of nanocrystals are used to train the neural network and to predict the presence or absence of dislocations as well as their type (screw or edge). Our study paves the way for defect-recognition in 3D coherent diffraction patterns for material science.Bruce LimEwen BellecMaxime DuprazSteven LeakeAndrea RestaAlessandro CoatiMichael SprungEhud AlmogEugen RabkinTobias SchulliMarie-Ingrid RichardNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-8 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 |
| spellingShingle |
Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Bruce Lim Ewen Bellec Maxime Dupraz Steven Leake Andrea Resta Alessandro Coati Michael Sprung Ehud Almog Eugen Rabkin Tobias Schulli Marie-Ingrid Richard A convolutional neural network for defect classification in Bragg coherent X-ray diffraction |
| description |
Abstract Coherent diffraction imaging enables the imaging of individual defects, such as dislocations or stacking faults, in materials. These defects and their surrounding elastic strain fields have a critical influence on the macroscopic properties and functionality of materials. However, their identification in Bragg coherent diffraction imaging remains a challenge and requires significant data mining. The ability to identify defects from the diffraction pattern alone would be a significant advantage when targeting specific defect types and accelerates experiment design and execution. Here, we exploit a computational tool based on a three-dimensional (3D) parametric atomistic model and a convolutional neural network to predict dislocations in a crystal from its 3D coherent diffraction pattern. Simulated diffraction patterns from several thousands of relaxed atomistic configurations of nanocrystals are used to train the neural network and to predict the presence or absence of dislocations as well as their type (screw or edge). Our study paves the way for defect-recognition in 3D coherent diffraction patterns for material science. |
| format |
article |
| author |
Bruce Lim Ewen Bellec Maxime Dupraz Steven Leake Andrea Resta Alessandro Coati Michael Sprung Ehud Almog Eugen Rabkin Tobias Schulli Marie-Ingrid Richard |
| author_facet |
Bruce Lim Ewen Bellec Maxime Dupraz Steven Leake Andrea Resta Alessandro Coati Michael Sprung Ehud Almog Eugen Rabkin Tobias Schulli Marie-Ingrid Richard |
| author_sort |
Bruce Lim |
| title |
A convolutional neural network for defect classification in Bragg coherent X-ray diffraction |
| title_short |
A convolutional neural network for defect classification in Bragg coherent X-ray diffraction |
| title_full |
A convolutional neural network for defect classification in Bragg coherent X-ray diffraction |
| title_fullStr |
A convolutional neural network for defect classification in Bragg coherent X-ray diffraction |
| title_full_unstemmed |
A convolutional neural network for defect classification in Bragg coherent X-ray diffraction |
| title_sort |
convolutional neural network for defect classification in bragg coherent x-ray diffraction |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/d32e14700bf3406999829daa027da33c |
| work_keys_str_mv |
AT brucelim aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT ewenbellec aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT maximedupraz aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT stevenleake aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT andrearesta aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT alessandrocoati aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT michaelsprung aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT ehudalmog aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT eugenrabkin aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT tobiasschulli aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT marieingridrichard aconvolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT brucelim convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT ewenbellec convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT maximedupraz convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT stevenleake convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT andrearesta convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT alessandrocoati convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT michaelsprung convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT ehudalmog convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT eugenrabkin convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT tobiasschulli convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction AT marieingridrichard convolutionalneuralnetworkfordefectclassificationinbraggcoherentxraydiffraction |
| _version_ |
1718379135991021568 |