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

arXiv: https://arxiv.org/abs/2507.14038 · HTML: https://mlsanity.com/paper/2507.14038/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 53 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## Builds on (most cited first, 11 of 11)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Automatic differentiation in machine learning: a survey](https://mlsanity.com/paper/1502.05767/) (2015)
- [Medical image denoising using convolutional denoising autoencoders](https://mlsanity.com/paper/1608.04667/) (2016)
- [Test Selection for Deep Learning Systems](https://mlsanity.com/paper/1904.13195/) (2019)
- [AutoPhaseNN: Unsupervised Physics-aware Deep Learning of 3D Nanoscale Bragg Coherent Diffraction Imaging](https://mlsanity.com/paper/2109.14053/) (2021)
- [Real-time coherent diffraction inversion using deep generative networks](https://mlsanity.com/paper/1806.03992/) (2018)
- [Deep learning at the edge enables real-time streaming ptychographic imaging](https://mlsanity.com/paper/2209.09408/) (2022)
- [Physics Constrained Unsupervised Deep Learning for Rapid, High Resolution Scanning Coherent Diffraction Reconstruction](https://mlsanity.com/paper/2306.11014/) (2023)
- [Adorym: A multi-platform generic x-ray image reconstruction framework based on automatic differentiation](https://mlsanity.com/paper/2012.12686/) (2020)
- [Combining Variational Autoencoders and Physical Bias for Improved Microscopy Data Analysis](https://mlsanity.com/paper/2302.04216/) (2023)
- [Enhanced Confocal Laser Scanning Microscopy with Adaptive Physics Informed Deep Autoencoders](https://mlsanity.com/paper/2501.14709/) (2025)

## Built on by (most cited first, 1 of 1)

- [Unlocking Latent Dimensions: Exploring Representations of Large-Scale X-ray Scattering Data using Variational Autoencoders](https://mlsanity.com/paper/2606.14999/) (2026)

## Abstract (arXiv)

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.