Crystal structure identification with 3D convolutional neural networks with application to high-pressure phase transitions in SiO${}_2$

Abstract

Efficient, reliable and easy-to-use structure recognition of atomic environments is essential for the analysis of atomic scale computer simulations. In this work, we train two neuronal network (NN) architectures, namely PointNet and dynamic graph convolutional NN (DG-CNN) using different hyperparameters and training regimes to assess their performance in structure identification tasks of atomistic structure data. We show benchmarks on simple crystal structures, where we can compare against established methods. The approach is subsequently extended to structurally more complex SiO${}_2$ phases. By making use of this structure recognition tool, we are able to achieve a deeper understanding of the crystallization process in amorphous SiO${}_2$ under shock compression. Lastly, we show how the NN based structure identification workflows can be integrated into OVITO using its python interface.

References in corpus (11)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• The NumPy array: a structure for efficient numerical computation
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• Structure identification methods for atomistic simulations of crystalline materials
• Robust Structural Identification via Polyhedral Template Matching
• Global transition path search for dislocation formation in Ge on Si(001)
• Insightful classification of crystal structures using deep learning
• Modelling atomic and nanoscale structure in the silicon-oxygen system through active machine learning
• Ab initio studies of phonon softening and high pressure phase transitions of alpha-quartz SiO2
• Thermodynamic and mechanical properties of copper precipitates in alpha-iron from atomistic simulations

Cited by in corpus (3)

• Graph-neural-network predictions of solid-state NMR parameters from spherical tensor decomposition
• Understanding phase transitions of $\alpha$-quartz under dynamic compression conditions by machine-learning driven atomistic simulations
• From diamond to BC8 to simple cubic and back: kinetic pathways to post-diamond carbon phases from metadynamics