PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Accelerating the phase identification of multiphase mixtures with deep learning

Researchers develop a deep learning model that can detect a previously unknown quasicrystalline phase present in multiphase crystalline samples

Accelerating the phase identification of multiphase mixtures with deep learning
2023-11-17
(Press-News.org)

Crystalline materials are made up of atoms, ions, or molecules arranged in an ordered, three-dimensional structure. They are widely used for the development of semiconductors, pharmaceuticals, photovoltaics, and catalysts. The type of structures that fall into the category of crystalline materials continues to expand as scientists design novel materials to address emerging challenges pertaining to energy storage, carbon capture, and advanced electronics.

However, the development of such materials necessitates precise ways of identifying them. Currently, powder X-ray diffraction is widely used for this purpose. It identifies the structure of crystalline materials by examining scattered X-rays from a powdered sample. However, the task of identification becomes quite complex when dealing with multiphase samples containing different types of crystals with distinct structures, orientations, or compositions. In such cases, the accurate identification of the various phases present in the sample relies on the expertise of scientists, making the process time-consuming. To expedite this process, innovative data-driven methods, such as machine learning, have been used for distinguishing individual phases within multiphase samples. While substantial progress has been made in utilizing them for collecting information about known phases, the identification of unknown phases in multiphase samples still remains a challenge.

Now, however, researchers have proposed a new machine learning “binary classifier” model that can identify the presence of icosahedral quasicrystal (i-QC) phases—a kind of long-range ordered solids that have self-similarity in their diffraction patterns—from multiphase powder X-ray diffraction patterns. This study involved collaboration among Tokyo University of Science (TUS), National Defense Academy, National Institute for Materials Science, Tohoku University, and The Institute of Statistical Mathematics. It was led by Junior Associate Professor Tsunetomo Yamada from TUS, Japan, and was published in the Advanced Science journal on 14 November 2023.

“Across the world, researchers have made attempts to predict new substances using artificial intelligence and machine learning. However, identifying whether a desired substance is produced takes up substantial time and effort on the part of human experts. Therefore, we came up with the idea of using deep learning to identify new phases,” explains Dr. Yamada.

For developing the said model, the researchers first created a “binary classifier” using 80 types of convolutional neural networks. They next trained the classifier model using synthetic multiphase X-ray diffraction patterns, which were designed as representations of the expected patterns associated with i-QC phases. Following the training phase, the model’s performance was assessed using both synthetic patterns and a database of actual patterns.

Quite interestingly, the model achieved a prediction accuracy of over 92%. It also successfully identified an unknown i-QC phase within multiphase Al–Si–Ru alloys when used for screening 440 measured diffraction patterns from unknown materials in six different alloy systems. The presence of the unknown i-QC phase was further confirmed on analyzing the microstructure and composition of the material using transmission electron microscopy.

Notably, the proposed deep learning method has the ability to identify the i-QC phase even when it is not the most prominent component in the mixture. Moreover, this model can be used for the identification of new decagonal and dodecagonal QCs and can be extended to various types of other crystalline materials as well.

“With the proposed model, we were able to detect unknown quasicrystalline phases present in multiphase samples with high accuracy. The accuracy of this deep learning model thus points to the possibility of accelerating the process of phase identification of multiphase samples,” concludes Dr. Yamada on an optimistic note. Moreover, Dr. Yamada and his team are confident that this model will lead to a breakthrough in the field of materials science.

In summary, this study is a significant step forward in the identification of entirely new phases in quasicrystals commonly found in materials such as mesoporous silica, minerals, alloys, and liquid crystals.

We surely wish that this model opens up avenues for the discovery of interesting new materials in the future!

 

***

 

Reference                    

 

DOI: https://doi.org/10.1002/advs.202304546

 

Authors:                       

Hirotaka Uryu1, Tsunetomo Yamada1, Koichi Kitahara2,3, Alok Singh4, Yutaka Iwasaki5, Kaoru Kimura5, Kanta Hiroki1, Naoki Miyao6, Asuka Ishikawa7, Ryuji Tamura6, Satoshi Ohhashi8, Chang Liu9, and Ryo Yoshida9,10

 

Affiliations:     

1Department of Applied Physics, Tokyo University of Science

2Department of Materials Science and Engineering, National Defense Academy

3Department of Advanced Materials Science, The University of Tokyo

4Electron Microscopy Analysis Station, Structural Materials Microstructure Evaluation Group, National Institute for Materials Science

5Thermal Energy Materials Group, Research Center for Materials Nanoarchitectonics, National Institute for Materials Science

6Department of Materials Science and Technology, Tokyo University of Science

7Research Institute of Science and Technology, Tokyo University of Science, Tokyo 125-8585, Japan

8Institute of Multidisciplinary Research for Advanced Materials, Tohoku University

9The Institute of Statistical Mathematics, Research Organization of Information and Systems

10Department of Statistical Science, The Graduate University for Advanced Studies

 

Funding information
This work was supported in part by an MEXT KAKENHI Grant-in-Aid for Scientific Research on Innovative Areas (Grant Numbers 19H05818 and 19H05820), JST CREST Grant (Grant Number JPMJCR22O3), Grant-in-Aid for Scientific Research (A) (Grant Number 19H01132) from the Japan Society for the Promotion of Science (JSPS) and JST CREST Grant (Grant Number JPMJCR19I3).

END


[Attachments] See images for this press release:
Accelerating the phase identification of multiphase mixtures with deep learning

ELSE PRESS RELEASES FROM THIS DATE:

First comprehensive guideline on using biomarkers for monitoring Crohn’s disease

2023-11-17
Bethesda, MD (Nov. 17, 2023) — The American Gastroenterological Association (AGA) released a new evidence-based guideline recommending the use of blood and stool-based biomarkers to help manage Crohn’s disease, a type of inflammatory bowel disease (IBD). IBD is estimated to affect 2.74 million people in the U.S. The guideline was published today in Gastroenterology.  Biomarkers are blood or stool tests that can give more information on an underlying disease process. In the context of IBD, biomarkers such as C-reactive protein (CRP) in blood and fecal calprotectin ...

The future of supply chains: 3 essential elements to stay in business

The future of supply chains: 3 essential elements to stay in business
2023-11-17
Why should supply chains matter to you? The products on your store shelves, the packages arriving at your doorstep, and even the food on your table all rely on these intricate networks. Imagine a world where these lifelines are disrupted, where shelves sit empty, and essential goods remain out of reach. In Supply Chain 5.0: The Next Generation of Business Success Through Customer Centricity, Sustainability & Human Rights and Digitalization, we unveil the critical factors shaping the future of supply chains and how they impact your everyday life. This book holds a crucial revelation about the future of our supply chains. It ...

Fishing chimpanzees found to enjoy termites as a seasonal treat

Fishing chimpanzees found to enjoy termites as a seasonal treat
2023-11-17
The discovery that chimpanzees use tools to fish for termites revolutionized our understanding of their abilities — but we still don’t have crucial context to help us understand termite fishing and chimpanzee minds. Are chimpanzees fishing for a seasonal treat or trying their luck? Researchers based at the University of California Santa Cruz (UCSC) and University College London (UCL) investigated the relationship between termite availability and chimpanzee fishing. They found that termites are most available early in the wet season. Although other ...

Children’s brains shaped by their time on tech devices, research to-date shows

2023-11-17
Time spent watching television or playing computer games has measurable and long-term effects on children’s brain function, according to a review of 23 years of neuroimaging research, which while showing negative impacts also demonstrates some positive effects. However, the researchers stop short of advocating limits on screen time, which they say can lead to confrontation. Instead, they urge policymakers to help parents navigate the digital world by promoting programs which support positive brain development. The evidence review, published today in the peer-reviewed journal Early Education ...

Discovery of hemoglobin in the epidermis sheds new light on our skin's protective properties

Discovery of hemoglobin in the epidermis sheds new light on our skins protective properties
2023-11-17
Philadelphia, November 17, 2023 – Researchers have shown for the first time that hemoglobin, a protein found in red blood cells where it binds oxygen, is also present in the epidermis, our skin's outermost body tissue. The study, which appears in the Journal of Investigative Dermatology, published by Elsevier, provides important insights into the properties of our skin's protective external layer. This research was driven by a curiosity about how the epidermis protects our delicate body from the environment and what unexpected ...

A highly efficient open-shell singlet luminescent diradical with strong magnetoluminescence properties

A highly efficient open-shell singlet luminescent diradical with strong magnetoluminescence properties
2023-11-17
Open-shell singlet (OS) diradicals are important building blocks for functional molecular materials,with a large number of pioneering works by researchers advancing their development and applications across various fields. Despite this progress, there remains a lack of research regarding luminescent OS diradicals, hindering their potential use in optoelectronic applications. In fact, the luminescent diradicals are rare chemical species, there are only a few reports to date.   Magnetic field effects (MFE) on the luminescence, i.e., magnetoluminescence (ML) of radicals, hold great promise for developing novel exciton spin manipulation ...

Evidence of cerebral microstructural reorganization in symptomatic children following mild traumatic brain injury

Evidence of cerebral microstructural reorganization in symptomatic children following mild traumatic brain injury
2023-11-17
A new study published in the peer-reviewed Journal of Neurotrauma shows that children with persistent symptoms following mild traumatic brain injury had evidence of ongoing cerebral microstructural changes. Click here to read the article now. Athena Stein, from The University of Queensland, and coauthors, used brain MRI-based orientation dispersion index (ODI) metrics to study the microstructural damage in the brains of pediatric patients following “mild” TBI. The investigators studied children with persistent symptoms after injury and children displaying clinical recovery at 1 and 2-3 months post-TBI compared to healthy controls. Whole-brain ODI was significantly ...

Unveiling the future of tropical cyclones: A call to enhance identification and simulation in climate models

Unveiling the future of tropical cyclones: A call to enhance identification and simulation in climate models
2023-11-17
Tropical cyclones in the western North Pacific (WNP) stand as formidable natural forces, wreaking havoc on Earth and posing significant challenges to disaster preparedness. As we grapple with the uncertainties of future projections for WNP tropical cyclone activities, a recent study published in Environmental Research Letters sheds light on the crucial need to enhance identification and simulation techniques in climate models. Led by Dr. Xin Huang from the Shanghai Typhoon Institute of China Meteorological Administration and Professor Tianjun Zhou from the Institute ...

The FinTech Nation

The FinTech Nation
2023-11-17
In a world where digital innovation reigns supreme, Singapore's ascent to FinTech prominence is nothing short of extraordinary. With a reputation for integrity, a conducive business environment, and unwavering support for financial innovation, this small island nation has defied all odds, to emerge as The FinTech Nation. Embark on an exhilarating journey through the dynamic world of FinTech in the heart of Asia with The FinTech Nation: Excellence Unlocked in Singapore. This captivating book unveils the secrets behind Singapore's meteoric rise as a global financial powerhouse, offering an intricate tapestry of ...

Like the phoenix, Australia’s giant birds of prey rise again from limestone caves

Like the phoenix, Australia’s giant birds of prey rise again from limestone caves
2023-11-17
Australia’s only vulture, and a fearsome extinct eagle, are among the earliest recorded birds of prey from the Pleistocene period more than 50,000 years ago – and now Flinders University researchers are bringing them to life again.    Along with new scientific information published in Alcheringa: An Australasian Journal of Palaeontology, a bold new pictorial reconstruction of a newly named eagle and the only known Australian vulture will be unveiled at the World Heritage-listed Naracoorte Caves in South Australia’s Limestone Coast this month.   “Imagine these majestic birds competing ...

LAST 30 PRESS RELEASES:

Caltech's new fingerprint mass spectrometry method paves the way to solving the proteome

Invasive flathead catfish impacting Susquehanna’s food chain, researchers find

Javadi receives DOE Early Career Award to study qubit hosts

Obesity Medicine Fellowship created at Pennington Biomedical

Structural biology analysis of a Pseudomonas bacterial virus reveals a genome ejection motor

Remote tool developed to helped detect autism and developmental delay in children with limited access to specialists

Texas Accounting Chair Steven Kachelmeier garners coveted award for scholarship

CABHI launches funding program that ignites innovation to advance healthy aging

A fully automated AI-based system for assessing IVF embryo quality

Senolytics dasatinib and quercetin for prevention of pelvic organ prolapse in mice

UCLA efforts to provide prostate cancer treatment in the community gets $6 million boost

Study asks: Can cell phone signals help land a plane?

Artificial intelligence is creating a new way of thinking, an external thought process outside of our minds

Reaction conditions tune catalytic selectivity

Verified users on social media networks drive polarization and the formation of echo chambers

Get a grip: The best thumb position for disc launch speed and spin rate

Maternal eating disorders, BMI, and offspring psychiatric diagnoses

Geometric mechanics shape the dog's nose

‘Visual clutter’ alters information flow in the brain

Researchers succeed in taking 3D x-ray images of a skyrmion

MRI can save rectal cancer patients from surgery, study suggests

Fyodor Urnov on clinical crisis in CRISPR genome editing

People with type 2 diabetes who eat low-carb may be able to discontinue medication

Air pollution linked to having a peanut allergy during childhood

Dangers of the metaverse and VR for US youth revealed in new research

A national indicator for a just energy transition

Cognitive effort whets the appetite for reward

European funders and organizations partner to promote sustainable research

A model for the decline of trends, fads, and information sharing

Plastic mulch is contaminating agricultural fields

[Press-News.org] Accelerating the phase identification of multiphase mixtures with deep learning
Researchers develop a deep learning model that can detect a previously unknown quasicrystalline phase present in multiphase crystalline samples