Deep learning for visualization and novelty detection in large X-ray diffraction datasets

TL;DR

This paper demonstrates that variational autoencoders can effectively analyze X-ray diffraction data, revealing structural similarities, identifying novel phases, and aiding materials discovery through visualization and novelty detection.

Contribution

The study introduces the application of VAEs to XRD data, showing their ability to learn meaningful representations and detect novel phases, which is a new approach in materials analysis.

Findings

VAEs reveal latent structural information in XRD data.

VAEs can identify novel phases and mixtures rapidly.

Compared to other AI methods, VAEs excel at novelty detection.

Abstract

We apply variational autoencoders (VAE) to X-ray diffraction (XRD) data analysis on both simulated and experimental thin-film data. We show that crystal structure representations learned by a VAE reveal latent information, such as the structural similarity of textured diffraction patterns. While other artificial intelligence (AI) agents are effective at classifying XRD data into known phases, a similarly conditioned VAE is uniquely effective at knowing what it does not know, rapidly identifying novel phases and mixtures. These capabilities demonstrate that a VAE is a valuable AI agent for materials discovery and understanding XRD measurements both on-the-fly and during post hoc analysis.