Real-time X-ray data analysis with DONUT accelerates materials science

Phys · 🇺🇸 public United States · Aug 11, 2026 · 899 words · By Amber Rose

Scientific Innovation Department of Energy Initiatives Artificial Intelligence in Research

headphones Listen to the eFinder podcast briefing

Generate a natural audio summary of this story

Daily briefing

What to know about Scientific Innovation

Researchers at Argonne National Laboratory have developed DONUT, a physics-aware machine learning tool that enables real-time analysis of X-ray nanodiffraction data. The tool aims to accelerate materials science research by reducing data processing time from weeks to seconds and lowering the barrier for new users.

Propaganda risk 10%

Claims checked 10

Techniques found 1

Topics 3

Coverage spectrum

Coverage gap: Low Left coverage

Left0%

Center100%

Right0%

1 source compared across this story cluster. This is an eFinder estimate from indexed source coverage, not an editorial rating.

What happened

Real-time X-ray data analysis with DONUT accelerates materials science Sadie Harley Scientific Editor Robert Egan Senior Editor What if scientists could get a taste of discovery as soon as their experiment finishes?

Why it matters

Thanks to a new machine learning tool called DONUT, researchers at the U.S.

Common ground

Department of Energy's (DOE) Argonne National Laboratory are transforming how experiments are run at the Advanced Photon Source (APS), a DOE Office of Science user facility.

Perspective signals

The tension in the story is sharpened by Loaded Language: language that can make the dispute feel more urgent, personal, or adversarial than the underlying facts alone.

Follow-up questions

What new context would change how readers understand this Scientific Innovation story?
What evidence would most clearly confirm or weaken the claim that The CNM is also a DOE Office of Science user facility at Argonne?
How does this story connect Scientific Innovation with Department of Energy Initiatives over the next few days?

open_in_new Read the original article: https://phys.org/news/2026-08-real-ray-analysis-donut-materials.html

analyticsAnalysis

10%

Propaganda Score

confidence: 100%

Low risk. This article shows minimal use of propaganda techniques.

psychologyPropaganda Techniques Detected

eFinder identified 1 propaganda technique in this article. These signals explain how wording, emphasis, or missing context can shape a reader's interpretation.

warning

Loaded Language 80% confidence

Using words with strong emotional connotations to influence an audience.

Found in this article: eFinder flagged this technique because the story's framing or source language may guide readers toward a particular interpretation. Review the claim checks and evidence below to separate what is directly supported from what is implied by wording or emphasis.

Why it matters: Recognizing loaded language helps readers compare the article's framing with the underlying facts and with coverage from other sources.

fact_checkClaims Checked

eFinder analyzed this article and checked 10 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.

info Single Source 4

check_circle Corroborated 3

help Insufficient Evidence 2

verified Verified By Reference 1

verified

Claim 1: “The CNM is also a DOE Office of Science user facility at Argonne.”

VERIFIED BY REFERENCE

Wikipedia and multiple other sources confirm that the Center for Nanoscale Materials (CNM) is a DOE Office of Science user facility located at Argonne National Laboratory.

menu_book

wikipedia NEUTRAL — Argonne National Laboratory (ANL) is a federally funded research and development center in the Downers Grove Township of DuPage County, Illinois, United States, with a Lemont address. Founded in 1946,…
https://en.wikipedia.org/wiki/Argonne_National_Laboratory

menu_book

wikipedia NEUTRAL — The Center for Nanoscale Materials is one of five Nanoscale Science Research Centers the United States Department of Energy sponsors. The Center is at Argonne National Laboratory location in Lemont, I…
https://en.wikipedia.org/wiki/Center_for_Nanoscale_Materials

menu_book

wikipedia NEUTRAL — The United States Department of Energy National Laboratories and Technology Centers is a system of laboratories overseen by the United States Department of Energy (DOE) for scientific and technologica…
https://en.wikipedia.org/wiki/United_States_Department_of_En…

+ 3 more evidence sources

info

Claim 2: “DONUT changes the recipe by combining artificial intelligence (AI) with a built-in physics model. This allows the system to learn directly from experimental data without needing labeled training examples”

SINGLE SOURCE

The specific mechanism of combining AI with a physics model to learn without labeled examples is part of the primary narrative, but the provided search results for 'DONUT' in this context were either irrelevant or referred to different AI models (like OCR DONUT).

travel_explore

web search NEUTRAL — micro1 launches Flow-gen: physics-based simulation and generative AI that produce controlled synthetic sensor data to close coverage gaps in perception model training.
https://www.micro1.ai/blog/generating-the-training-data-that…

travel_explore

web search NEUTRAL — The authors suggest that combining DONUT with Textract could yield promising results, leveraging the strengths of both models. They emphasize the need for a substantial amount of training data for DON…
https://readmedium.com/text-extraction-comparing-donut-and-a…

travel_explore

web search NEUTRAL — It learns visual concepts from natural language supervision. It bridges the gap between text and visual data by jointly training a CLIP model on a large-scale dataset containing images and their corre…
https://viso.ai/deep-learning/clip-machine-learning/

info

Claim 3: “DONUT, short for Diffraction with Optics for Nanobeam by Unsupervised Training, is a physics-aware neural network.”

SINGLE SOURCE

While the general context of DONUT as a tool is established in claim 0, the specific expansion of the acronym and the 'physics-aware neural network' description is only present in the primary source context; the provided search results for 'DONUT' were largely irrelevant (food-related).

travel_explore

web search NEUTRAL — We specialize in artisanal vegan donuts and ice creams, made from scratch with local, fresh and sometimes unusual ingredients. Quality always takes precedence over quantity. We love to sell out and we…
https://www.doedonuts.com/

travel_explore

web search NEUTRAL — Welcome to our guide to the best donuts in Portland, Oregon. We’re going to cut straight to the chase and let you know that Portland is one of the best donut cities in the entire country if not the ve…
https://www.femalefoodie.com/restaurant-reviews/best-donuts-…

travel_explore

web search NEUTRAL — "Great little spot for unique and delicious donuts. The person helping me was sweet and helpful." more. 4. Voodoo Doughnut. "Overall, Voodoo Doughnut has some amazing and delicious donuts. Do note the…
https://www.yelp.com/search?cflt=donuts&find_loc=portland,+o…

check_circle

Claim 4: “SXDM is a powerful technique that uses a focused X-ray beam to scan across a sample, collecting information about its crystal structure.”

CORROBORATED

Multiple technical sources confirm that SXDM uses a focused X-ray beam to scan samples and resolve nanoscale structural morphologies/crystal structures.

travel_explore

web search NEUTRAL — Scanning X-ray nanodiffraction microscopy is a powerful technique for spatially resolving. nanoscale structural morphologies by diffraction contrast. One of the critical challenges in.SXDM is performe…
https://www.researchgate.net/publication/381372404_Deep_Lear…

travel_explore

web search NEUTRAL — Scanning X-ray nanodiffraction microscopy is a powerful technique for spatially resolving nanoscale structural morphologies by diffraction contrast.
https://www.nature.com/articles/s41598-025-97183-0?error=coo…

travel_explore

web search NEUTRAL — The use of focused X-ray beams in the micron and sub-micron range has fostered the progress of a wide range of scanning microscopy approaches that exploit the numerous interactions of X-rays with matt…
https://wrap.warwick.ac.uk/id/eprint/175070/1/1-s2.0-S016858…

info

Claim 5: “The work is published in the journal npj Computational Materials.”

SINGLE SOURCE

One web search result explicitly states the work is published in npj Computational Materials. Other results mention the journal but not this specific paper.

menu_book

wikipedia NEUTRAL — Exient Limited is a British video game developer and publisher based in Kings Langley, England. Developing for handheld, mobile, console, VR and PC platforms, Having studios in the United Kingdom and …
https://en.wikipedia.org/wiki/Exient

menu_book

wikipedia NEUTRAL — A shape is a graphical representation of an object's form or its external boundary, outline, or external surface. It is distinct from other object properties, such as color, texture, or material type.…
https://en.wikipedia.org/wiki/Shape

menu_book

wikipedia NEUTRAL — In applied mathematics, topological data analysis (TDA) is an approach to the analysis of datasets using techniques from topology. Extraction of information from datasets that are high-dimensional, in…
https://en.wikipedia.org/wiki/Topological_data_analysis

+ 3 more evidence sources

help

Claim 6: “DONUT's physics-aware training framework is expected to support major initiatives like the DOE's Genesis Mission.”

INSUFFICIENT EVIDENCE

No evidence was found in the provided search results regarding the 'Genesis Mission'.

check_circle

Claim 7: “researchers at the U.S. Department of Energy's (DOE) Argonne National Laboratory are transforming how experiments are run at the Advanced Photon Source (APS), a DOE Office of Science user facility.”

CORROBORATED

Multiple web search results confirm that researchers at Argonne National Laboratory are using a tool called DONUT to transform experiments at the Advanced Photon Source (APS).

menu_book

wikipedia NEUTRAL — Fermi National Accelerator Laboratory (FNAL; branded as Fermilab) is a national laboratory for high-energy particle physics, located in Batavia, Illinois, United States, near Chicago. It is sponsored …
https://en.wikipedia.org/wiki/Fermi_National_Accelerator_Lab…

menu_book

wikipedia NEUTRAL — A particle accelerator is a machine that uses electromagnetic fields to propel ions to very high speeds and energies to contain them in well-defined beams. Small accelerators are used for fundamental …
https://en.wikipedia.org/wiki/Particle_accelerator

menu_book

wikipedia NEUTRAL — Steven David Levitt (born May 29, 1967) is an American economist and co-author of the best-selling book Freakonomics and its sequels (along with Stephen J. Dubner). Levitt is a professor emeritus at t…
https://en.wikipedia.org/wiki/Steven_Levitt

+ 3 more evidence sources

check_circle

Claim 8: “Developed and tested using data from the Hard X-ray Nanoprobe beamline shared by the APS and the Center for Nanoscale Materials (CNM), DONUT helps scientists quickly interpret complex X-ray images produced by scanning X-ray nanodiffraction microscopy (SXDM)”

CORROBORATED

Web search results explicitly confirm that DONUT was developed using data from the Hard X-ray Nanoprobe beamline shared by the APS and CNM to interpret SXDM images.

travel_explore

web search NEUTRAL — Developed and tested using data from the Hard X-ray Nanoprobe beamline shared by the APS and the Center for Nanoscale Materials (CNM), DONUT helps scientists quickly interpret complex X-ray images pro…
https://www.anl.gov/article/a-taste-of-discovery-realtime-xr…

travel_explore

web search NEUTRAL — The Hard X-ray Nanoprobe Beamline (or Nanoprobe Beamline) is an X-ray. microscopy facility incorporating diffraction, ﬂuorescence and full-ﬁeld imaging. capabilities designed and operated by the Cente…
https://www.researchgate.net/publication/232649301_A_hard_X-…

travel_explore

web search NEUTRAL — The Center for Nanoscale Materials' newly operational Hard X-ray Nanoprobe at the US Department of Energy's Argonne National Laboratory is one of the world's most powerful X-ray microscopes. It has be…
https://www.eurekalert.org/news-releases/877336

help

Claim 9: “Aileen Luo et al, DONUT: physics-aware machine learning for real-time X-ray nanodiffraction analysis, npj Computational Materials (2025). DOI: 10.1038/s41524-025-01860-7”

INSUFFICIENT EVIDENCE

No evidence was found in the provided search results to verify the specific author, title, date, or DOI of the paper.

info

Claim 10: “With DONUT, researchers can get results in real time, sometimes hundreds of times faster than traditional methods.”

SINGLE SOURCE

The claim that results are obtained in real time and hundreds of times faster is mentioned in one relevant web search result; other results for 'DONUT' were irrelevant food searches.

travel_explore

info Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.