uncovering nature's patterns at the atomic scale in living color
Machine learning provides a color coded map of X-ray data based on the temperature dependence of each region. X-TEC identified the locations of two sets of sharp peaks (yellow and green squares) in the data, as well as diffuse scattering halos around them (red and blue). Credit: Argonne National Laboratory

Color coding makes aerial maps much more easily understood. Through color, we can tell at a glance where there is a road, forest, desert, city, river or lake.

Working with several universities, the U.S. Department of Energy’s (DOE) Argonne National Laboratory has devised a method for creating color-coded graphs of large volumes of data from X-ray analysis. This new tool uses computational data sorting to find clusters related to physical properties, such as an atomic distortion in a crystal structure. It should greatly accelerate future research on structural changes on the atomic scale induced by varying temperature.

The research team published their findings in the Proceedings of the National Academy of Sciences in an article titled “Harnessing interpretable and unsupervised machine learning to address big data from modern X-ray diffraction.”

“Our method uses machine learning to rapidly analyze immense amounts of data from X-ray diffraction,” said Raymond Osborn, senior physicist in Argonne’s Materials Science division. “What might have taken us months in the past now takes about a quarter hour, with much more fine-grained results.”

For over a century, X-ray diffraction (or XRD) has been one of the most fruitful of all scientific methods for analyzing materials. It has provided key information on the 3D atomic structure of innumerable technologically important materials.

In recent decades, the amount of data being produced in XRD experiments has increased dramatically at large facilities such as the Advanced Photon Source (APS), a DOE Office of Science user facility at Argonne. Sorely lacking, however, are analysis methods that can cope with these immense data sets.

The team calls their new method X-ray Temperature Clustering, or XTEC for short. It accelerates materials discoveries through rapid clustering and color coding of large X-ray data sets to reveal previously hidden structural changes that occur as temperature increases or decreases. A typical large data set would be 10,000 gigabytes, equivalent to roughly 3 million songs of streaming music.

XTEC draws on the power of unsupervised machine learning, using methods developed for this project at Cornell University. This machine learning does not depend on initial training and learning with data already well studied. Instead, it learns by finding patterns and clusters in large data sets without such training. These patterns are then represented by color coding.

“For example, XTEC might assign red to data cluster one, which is associated with a certain property that changes with temperature in a particular way,” Osborn said. “Then, cluster two would be blue, and associated with another property with a different temperature dependence, and so on. The colors tell whether each cluster represents the equivalent of a road, forest or lake in an aerial map.”

As a test case, XTEC analyzed data from beamline 6-ID-D at the APS, taken from two crystalline materials that are superconducting at temperatures close to absolute zero. At this ultralow temperature, these materials switch to a superconducting state, offering no resistance to electrical current. More important for this study, other unusual features emerge at higher temperatures related to changes in the material structure.

By applying XTEC, the team extracted an unprecedented amount of information about changes in atomic structure at different temperatures. Those include not only distortions in the orderly arrangement of atoms in the material, but also fluctuations that occur when such changes happen.

“Because of machine learning, we are able to see materials’ behavior not visible by conventional XRD,” Osborn said. “And our method is applicable to many big data problems in not only superconductors, but also batteries, solar cells, and any temperature-sensitive device.”

The APS is undergoing a massive upgrade that will increase the brightness of its X-ray beams by up to 500 times. Along with the upgrade will come a significant increase in data collected at the APS, and machine learning techniques will be essential to analyzing that data in a timely manner. More information: Harnessing Interpretable and Unsupervised Machine Learning to Address Big Data from Modern X-ray Diffraction, arXiv:2008.03275 [cond-mat.str-el] arxiv.org/abs/2008.03275 Journal information: Proceedings of the National Academy of Sciences

Provided by Argonne National Laboratory Citation: Uncovering nature’s patterns at the atomic scale in living color (2022, August 16) retrieved 16 August 2022 from https://techxplore.com/news/2022-08-uncovering-nature-patterns-atomic-scale.html This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

TECH NEWS RELATED

Smacked asteroid's debris trail more than 6,000 miles long

This image made available by NOIRLab shows a plume of dust and debris blasted from the surface of the asteroid Dimorphos by NASA’s DART spacecraft after it impacted on Sept. 26, 2022, captured by the U.S. National Science Foundation’s NOIRLab’s SOAR telescope in Chile. The expanding, comet-like tail is ...

View more: Smacked asteroid's debris trail more than 6,000 miles long

Engineering students create a 3D-printed functional robotic arm

Detail of the 3D-printed transradial myoelectric prosthesis. Credit: Polytechnic University of Catalonia Fifteen bachelor’s and master’s degree students from the Barcelona School of Industrial Engineering (ETSEIB) of the Universitat Politècnica de Catalunya · BarcelonaTech (UPC) share the same dream: improving the quality of life of people with disabilities using ...

View more: Engineering students create a 3D-printed functional robotic arm

Crash test dummies for e-scooters

In the crash tests, the e-scooter and dummy were driven against a curb at speeds of 10, 20 and 30 km/h. Even at 10 km/h, there is a significant risk of injury. Credit: Fraunhofer EMI Practical and environmentally friendly, e-scooters offer great flexibility. It is no wonder that more ...

View more: Crash test dummies for e-scooters

LiDAR and radar sensors—space-saving headlight installation

LED headlight model with multispectral combiners for coaxially merging optical light, LiDAR (red) and radar beams (green), with the aim of achieving space-saving sensor integration for next-generation driver assistance systems. Credit: Fraunhofer FHR People use their eyes and ears to pick up on traffic situations involving potential hazards. For ...

View more: LiDAR and radar sensors—space-saving headlight installation

New genetic variation from old and exotic varieties for environmentally friendly wheat cultivation

In addition to the almost 9,000 winter wheat accessions, the scientists also grew elite varieties in the trial field and investigated resistance to yellow rust, among other traits. Credit: IPK Leibniz Institute/ C. Martin Gene banks worldwide make an important contribution to the conservation of biological diversity. In the ...

View more: New genetic variation from old and exotic varieties for environmentally friendly wheat cultivation

Multi-organ chip detects dangerous nanoparticles

Computational grid for thermal simulation with a magnified representation of the NanoCube exposure device. The aerosol sections are in yellow, the other sections are either components or air sections. Credit: Fraunhofer SCAI What happens when we breathe in nanoparticles emitted by, for example, a laser printer? Could these nanoparticles ...

View more: Multi-organ chip detects dangerous nanoparticles

Bad roads reduce trade volumes by 18%

Distance versus travel time in intra- and international bilateral links. Notes: Average excess distance is the %-ratio between road distance and great circle distance, both in km. Avg. road speed denotes the average travel speed on the fastest road connection, in km/h, while avg. direct speed refers to the ...

View more: Bad roads reduce trade volumes by 18%

New online portal aims to improve parks and green spaces around the world

Credit: Pixabay/CC0 Public Domain The Parks & Green Space Research Portal promotes collaboration and shared research between academics and parks professionals worldwide. The portal—a collaboration between the Department of Landscape Architecture, University of Leeds, the Green Flag Award scheme and environmental charity Keep Britain Tidy—enables users to exchange expertise ...

View more: New online portal aims to improve parks and green spaces around the world

Manufacturing microscopic octopuses with a 3D printer

Protein family shows how life adapted to oxygen

Driving high? Chemists make strides toward marijuana breath analyzer

Alain Aspect, Nobel-winning father of quantum entanglement

Reports say the CIA is trying to resurrect woolly mammoths

Hackers are breaching scam sites to hijack crypto transactions

Businesses Move to Combat Waning Customer Loyalty with Pre-Emptive Service Technology, Says Pega Study

Is your business ready for web 3.0?

Pentest People launches SecurePortal 2.0, expands PTaaS and hires senior Incident Response specialist

Why emergency landing site evaluation for autonomous aircraft systems is a data problem

Lack of digital skills is jeopardising UK business growth, AND Digital reveals

Swedish-based SaaS platform partners with travel risk intelligence company 

OTHER TECH NEWS

Top Car News Car News