Random Forest Prediction of Crystal Structure from Electron Diffraction Patterns Incorporating Multiple Scattering

TL;DR

This paper introduces a hierarchical random forest approach to predict crystal structures from electron diffraction patterns, achieving high accuracy and enabling real-time analysis in electron microscopy.

Contribution

It presents a novel machine learning architecture that accurately predicts crystal systems, space groups, and lattice parameters from electron diffraction data, including unknown and nanoscale materials.

Findings

67% correct crystal system identification from a single simulated pattern

79% accuracy when aggregating predictions from 10 patterns

70-90% accuracy in space group and lattice predictions

Abstract

Diffraction is the most common method to solve for unknown or partially known crystal structures. However, it remains a challenge to determine the crystal structure of a new material that may have nanoscale size or heterogeneities. Here we train an architecture of hierarchical random forest models capable of predicting the crystal system, space group, and lattice parameters from one or more unknown 2D electron diffraction patterns. Our initial model correctly identifies the crystal system of a simulated electron diffraction pattern from a 20 nm thick specimen of arbitrary orientation 67% of the time. We achieve a topline accuracy of 79% when aggregating predictions from 10 patterns of the same material but different zone axes. The space group and lattice predictions range from 70-90% accuracy and median errors of 0.01-0.5 angstroms, respectively, for cubic, hexagonal, trigonal and tetragonal crystal systems while being less reliable on orthorhombic and monoclinic systems. We apply this architecture to a 4D-STEM scan of gold nanoparticles, where it accurately predicts the crystal structure and lattice constants. These random forest models can be used to significantly accelerate the analysis of electron diffraction patterns, particularly in the case of unknown crystal structures. Additionally, due to the speed of inference, these models could be integrated into live TEM experiments, allowing real-time labeling of a specimen.