Details

Autor(en) / Beteiligte

• Ziletti, Angelo
• Kumar, Devinder
• Scheffler, Matthias
• Ghiringhelli, Luca M.

Titel

Insightful classification of crystal structures using deep learning

Ist Teil von

• Nature communications, 2018-07, Vol.9 (1), p.2775-10, Article 2775

Ort / Verlag

London: Nature Publishing Group UK

Erscheinungsjahr

2018

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Computational methods that automatically extract knowledge from data are critical for enabling data-driven materials science. A reliable identification of lattice symmetry is a crucial first step for materials characterization and analytics. Current methods require a user-specified threshold, and are unable to detect average symmetries for defective structures. Here, we propose a machine learning-based approach to automatically classify structures by crystal symmetry. First, we represent crystals by calculating a diffraction image, then construct a deep learning neural network model for classification. Our approach is able to correctly classify a dataset comprising more than 100,000 simulated crystal structures, including heavily defective ones. The internal operations of the neural network are unraveled through attentive response maps, demonstrating that it uses the same landmarks a materials scientist would use, although never explicitly instructed to do so. Our study paves the way for crystal structure recognition of—possibly noisy and incomplete—three-dimensional structural data in big-data materials science. Classifying crystal structures using their space group is important to understand material properties, but the process currently requires user input. Here, the authors use machine learning to automatically classify more than 100,000 simulated perfect and defective crystal structures.