DONUT: Physics-aware Machine Learning for Real-time X-ray Nanodiffraction Analysis

TL;DR

DONUT is a physics-aware neural network that enables real-time, automated analysis of nanobeam diffraction data, significantly reducing computational time and eliminating the need for labeled training data.

Contribution

The paper introduces DONUT, a novel physics-informed neural network architecture that performs rapid, unsupervised analysis of X-ray nanodiffraction data by integrating a differentiable diffraction model.

Findings

Achieves over 200x faster analysis than traditional methods.

Accurately predicts crystal lattice strain and orientation.

Operates without labeled datasets or pre-training.

Abstract

Coherent X-ray scattering techniques are critical for investigating the fundamental structural properties of materials at the nanoscale. While advancements have made these experiments more accessible, real-time analysis remains a significant bottleneck, often hindered by artifacts and computational demands. In scanning X-ray nanodiffraction microscopy, which is widely used to spatially resolve structural heterogeneities, this challenge is compounded by the convolution of the divergent beam with the sample's local structure. To address this, we introduce DONUT (Diffraction with Optics for Nanobeam by Unsupervised Training), a physics-aware neural network designed for the rapid and automated analysis of nanobeam diffraction data. By incorporating a differentiable geometric diffraction model directly into its architecture, DONUT learns to predict crystal lattice strain and orientation in real-time. Crucially, this is achieved without reliance on labeled datasets or pre-training, overcoming a fundamental limitation for supervised machine learning in X-ray science. We demonstrate experimentally that DONUT accurately extracts all features within the data over 200 times more efficiently than conventional fitting methods.