Tracking perovskite crystallization via deep learning-based feature detection on 2D X-ray scattering data

TL;DR

This paper introduces a deep learning-based automated pipeline using Faster R-CNN to analyze GIXD data for tracking perovskite crystallization in real-time, enhancing data processing and phase identification.

Contribution

The study develops a modified Faster R-CNN model tailored for scattering data, enabling accurate detection of diffraction features and real-time tracking of perovskite formation.

Findings

High accuracy in detecting diffraction features on noisy data

Successful real-time tracking of perovskite crystallization

Automated phase identification of coexisting phases

Abstract

Understanding the processes of perovskite crystallization is essential for improving the properties of organic solar cells. In situ real-time grazing-incidence X-ray diffraction (GIXD) is a key technique for this task, but it produces large amounts of data, frequently exceeding the capabilities of traditional data processing methods. We propose an automated pipeline for the analysis of GIXD images, based on the Faster R-CNN deep learning architecture for object detection, modified to conform to the specifics of the scattering data. The model exhibits high accuracy in detecting diffraction features on noisy patterns with various experimental artifacts. We demonstrate our method on real-time tracking of organic-inorganic perovskite structure crystallization and test it on two applications: 1. the automated phase identification and unit-cell determination of two coexisting phases of Ruddlesden-Popper 2D perovskites, and 2. the fast tracking of MAPbI$_3$ perovskite formation. By design, our approach is equally suitable for other crystalline thin-film materials.