DeepXRD, a Deep Learning Model for Predicting of XRD spectrum from Materials Composition

TL;DR

DeepXRD is a deep learning model that predicts XRD spectra from material compositions, enabling rapid structural insights and high-throughput screening for new materials discovery.

Contribution

This work introduces a novel deep learning approach to predict XRD spectra directly from compositions, bypassing the need for expensive structural determination.

Findings

Achieves good performance on benchmark datasets

Enables high-throughput screening of materials

Facilitates structural feature inference from spectra

Abstract

One of the long-standing problems in materials science is how to predict a material's structure and then its properties given only its composition. Experimental characterization of crystal structures has been widely used for structure determination, which is however too expensive for high-throughput screening. At the same time, directly predicting crystal structures from compositions remains a challenging unsolved problem. Herein we propose a deep learning algorithm for predicting the XRD spectrum given only the composition of a material, which can then be used to infer key structural features for downstream structural analysis such as crystal system or space group classification or crystal lattice parameter determination or materials property predictions. Benchmark studies on two datasets show that our DeepXRD algorithm can achieve good performance for XRD prediction as evaluated over our test sets. It can thus be used in high-throughput screening in the huge materials composition space for new materials discovery.