Machine-learning approach for local classification of crystalline structures in multiphase systems

Machine learning is one of the most popular fields in computer science and has a vast number of applications. In this work we will propose a method that will use a neural network to locally identify crystal structures in a mixed phase Yukawa system consisting of fcc, hcp, and bcc clusters and disordered particles similar to plasma crystals. We compare our approach to already used methods and show that the quality of identification increases significantly. The technique works very well for highly disturbed lattices and shows a flexible and robust way to classify crystalline structures that can be used by only providing particle positions. This leads to insights into highly disturbed crystalline structures.

Figure 1

Trend of the different crystal structures, which is used to train a MLP network.

Figure 2

Prediction of the MLP network to classify hcp, fcc, and bcc including falsely classified particles.

Figure 3

Structural composition of a slowly cooled down Yukawa system for MCS using machine learning (a) and BCCMSM using manual classification (b).