Unsupervised learning for structure detection in plastically deformed crystals

• Published in: Computational materials science Vol. 230; p. 112459
• Main Authors: Barbot, Armand, Gatti, Riccardo
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 25.10.2023; Elsevier
• Subjects: Chemical Sciences; Computer Science; Crystal; Engineering Sciences; Machine Learning; Molecular dynamics; Physics; Plastic deformation; Structure detection; Unsupervised learning; 0000; Structure detection; 1111; Molecular dynamics; Plastic deformation; Unsupervised learning; Crystal; Molecular Dynamics; Structure Detection; algorithme d'apprentissage; dynamique moléculaire; déformation plastique; apprentissage non supervisé
• ISSN: 0927-0256; 1879-0801
• DOI: 10.1016/j.commatsci.2023.112459

Detecting structures at the particle scale within plastically deformed crystalline materials allows a better understanding of the occurring phenomena. While previous approaches mostly relied on applying hand-chosen criteria on different local parameters, these approaches could only detect already known structures. We introduce an unsupervised learning algorithm to automatically detect structures within a crystal under plastic deformation. This approach is based on a study developed for structural detection on colloidal materials. This algorithm has the advantage of being computationally fast and easy to implement. We show that by using local parameters based on bond-angle distributions, we are able to detect more structures and with a higher degree of precision than traditional hand-made criteria. •Most structure detection methods rely on hand-made criteria.•These methods tend to focus on the main crystalline structures.•More sub-structures can be detected with unsupervised-learning based criteria.•Our approach combines two machine-learning methods: autoencoder and clustering. [Display omitted]