Crystallography companion agent for high-throughput materials discovery

TL;DR

This paper introduces an AI-driven autonomous XRD analysis tool that accelerates materials discovery by providing probabilistic classifications, reducing manual effort, and integrating seamlessly with robotic labs.

Contribution

The authors develop a novel AI-based program for autonomous XRD data analysis, enabling faster, more accurate material identification in high-throughput discovery workflows.

Findings

AI model improves classification accuracy over traditional methods

Significant time savings demonstrated in diverse material challenges

Applicable to various characterization techniques beyond XRD

Abstract

The discovery of new structural and functional materials is driven by phase identification, often using X-ray diffraction (XRD). Automation has accelerated the rate of XRD measurements, greatly outpacing XRD analysis techniques that remain manual, time-consuming, error-prone, and impossible to scale. With the advent of autonomous robotic scientists or self-driving labs, contemporary techniques prohibit the integration of XRD. Here, we describe a computer program for the autonomous characterization of XRD data, driven by artificial intelligence (AI), for the discovery of new materials. Starting from structural databases, we train an ensemble model using a physically accurate synthetic dataset, which output probabilistic classifications -- rather than absolutes -- to overcome the overconfidence in traditional neural networks. This AI agent behaves as a companion to the researcher, improving accuracy and offering significant time savings. It was demonstrated on a diverse set of organic and inorganic materials characterization challenges. This innovation is directly applicable to inverse design approaches, robotic discovery systems, and can be immediately considered for other forms of characterization such as spectroscopy and the pair distribution function.