DONUT: physics-aware machine learning for real-time X-ray nanodiffraction analysis

Journal Article · Tue Dec 16 00:00:00 UTC 2025 · npj Computational Materials

DOI: https://doi.org/10.1038/s41524-025-01860-7 · OSTI ID:3366212

Luo, Aileen ^[1]; Zhou, Tao ^[2]; Du, Ming ^[2]; Holt, Martin V. ^[2]; Singer, Andrej ^[3]; Cherukara, Mathew J. ^[2]

---

1. Argonne National Laboratory (ANL), Argonne, IL (United States); Cornell University, Ithaca, NY (United States)
2. Argonne National Laboratory (ANL), Argonne, IL (United States)
3. Cornell University, Ithaca, NY (United States)

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.

• Research Organization: Cornell University, Ithaca, NY (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR); USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)
• Grant/Contract Number: AC02-06CH11357; SC0014664; SC0019414
• OSTI ID: 3366212
• Journal Information: npj Computational Materials, Journal Name: npj Computational Materials Journal Issue: 1 Vol. 11; ISSN 2057-3960
• Publisher: Nature Publishing GroupCopyright Statement
• Country of Publication: United States
• Language: English