(Press-News.org) HOUSTON - (April 30, 2021) - The microscopic structures and properties of materials are intimately linked, and customizing them is a challenge. Rice University engineers are determined to simplify the process through machine learning.
To that end, the Rice lab of materials scientist Ming Tang, in collaboration with physicist Fei Zhou at Lawrence Livermore National Laboratory, introduced a technique to predict the evolution of microstructures -- structural features between 10 nanometers and 100 microns -- in materials.
Their open-access paper in the Cell Press journal Patterns shows how neural networks (computer models that mimic the brain's neurons) can train themselves to predict how a structure will grow under a certain environment, much like a snowflake forms from moisture in nature.
In fact, snowflake-like, dendritic crystal structures were one of the examples the lab used in its proof-of-concept study.
"In modern material science, it's widely accepted that the microstructure often plays a critical role in controlling a material's properties," Tang said. "You not only want to control how the atoms are arranged on lattices, but also what the microstructure looks like, to give you good performance and even new functionality.
"The holy grail of designing materials is to be able to predict how a microstructure will change under given conditions, whether we heat it up or apply stress or some other type of stimulation," he said.
Tang has worked to refine microstructure prediction for his entire career, but said the traditional equation-based approach faces significant challenges to allow scientists to keep up with the demand for new materials.
"The tremendous progress in machine learning encouraged Fei at Lawrence Livermore and us to see if we could apply it to materials," he said.
Fortunately, there was plenty of data from the traditional method to help train the team's neural networks, which view the early evolution of microstructures to predict the next step, and the next one, and so on.
"This is what machinery is good at, seeing the correlation in a very complex way that the human mind is not able to," Tang said. "We take advantage of that."
The researchers tested their neural networks on four distinct types of microstructure: plane-wave propagation, grain growth, spinodal decomposition and dendritic crystal growth.
In each test, the networks were fed between 1,000 and 2,000 sets of 20 successive images illustrating a material's microstructure evolution as predicted by the equations. After learning the evolution rules from these data, the network was then given from 1 to 10 images to predict the next 50 to 200 frames, and usually did so in seconds.
The new technique's advantages quickly became clear: The neural networks, powered by graphic processors, sped the computations up to 718 times for grain growth, compared to the previous algorithm. When run on a standard central processor, they were still up to 87 times faster than the old method. The prediction of other types of microstructure evolution showed similar, though not as dramatic, speed increases.
Comparisons with images from the traditional simulation method proved the predictions were largely on the mark, Tang said. "Based on that, we see how we can update the parameters to make the prediction more and more accurate," he said. "Then we can use these predictions to help design materials we have not seen before.
"Another benefit is that it's able to make predictions even when we do not know everything about the material properties in a system," Tang said. "We couldn't do that with the equation-based method, which needs to know all the parameter values in the equations to perform simulations."
Tang said the computation efficiency of neural networks could accelerate the development of novel materials. He expects that will be helpful in his lab's ongoing design of more efficient batteries. "We're thinking about novel three-dimensional structures that will help charge and discharge batteries much faster than what we have now," Tang said. "This is an optimization problem that is perfect for our new approach."
INFORMATION:
Rice graduate student Kaiqi Yang is lead author of the paper. Co-authors are Rice alumnus Yifan Cao and graduate students Youtian Zhang and Shaoxun Fan; and researchers Daniel Aberg and Babak Sadigh of Lawrence Livermore. Zhou is a physicist at Lawrence Livermore. Tang is an assistant professor of materials science and nanoengineering at Rice.
The Department of Energy, the National Science Foundation and the American Chemical Society Petroleum Research Fund supported the research.
Read the paper at https://www.cell.com/patterns/fulltext/S2666-3899(21)00063-5.
This news release can be found online at https://news.rice.edu/2021/04/30/neural-nets-used-to-rethink-material-design/.
Follow Rice News and Media Relations via Twitter @RiceUNews.
Related materials:
Mesoscale Materials Science Group: http://tanggroup.rice.edu/research/
Department of Materials Science and NanoEngineering: https://msne.rice.edu
George R. Brown School of Engineering: https://engineering.rice.edu
Video:
https://youtu.be/nWXuAb_JJ0Y
Image for download:
https://news-network.rice.edu/news/files/2021/04/0503_MICROSTRUCTURE-1-WEB.jpg
Engineers at Rice University and Lawrence Livermore National Laboratory are using neural networks to accelerate the prediction of how microstructures of materials evolve. This example predicts snowflake-like dendritic crystal growth. (Credit: Mesoscale Materials Science Group/Rice University)
Located on a 300-acre forested campus in Houston, Rice University is consistently ranked among the nation's top 20 universities by U.S. News & World Report. Rice has highly respected schools of Architecture, Business, Continuing Studies, Engineering, Humanities, Music, Natural Sciences and Social Sciences and is home to the Baker Institute for Public Policy. With 3,978 undergraduates and 3,192 graduate students, Rice's undergraduate student-to-faculty ratio is just under 6-to-1. Its residential college system builds close-knit communities and lifelong friendships, just one reason why Rice is ranked No. 1 for lots of race/class interaction and No. 1 for quality of life by the Princeton Review. Rice is also rated as a best value among private universities by Kiplinger's Personal Finance.
Jeff Falk
713-348-6775
jfalk@rice.edu
Mike Williams
713-348-6728
mikewilliams@rice.edu
CHARLOTTESVILLE, Va. - In 2018, industry and academic researchers revealed a potentially devastating hardware flaw that made computers and other devices worldwide vulnerable to attack.
Researchers named the vulnerability END ...
CHICAGO --- Itch torments its sufferers and can be as debilitating as chronic pain.
But it's a hard symptom to measure -- particularly for the 10 million U.S. children with atopic dermatitis, also known as eczema. They can't always verbalize or quantify their suffering via a survey or scale.
It can also be difficult to objectively measure itch for adults with liver disease, kidney disease and certain cancers who experience its symptoms.
So, it's hard to track how well treatments and drugs are working.
But now there is a soft, wearable sensor that actually quantifies itch by measuring scratching when placed on the hand developed by Northwestern University scientists. While it was tested ...
Boston, MA (April 30, 2021) - A new study, presented today at the AATS 101st Annual Meeting, shows significant reduction in post-operative use of Schedule II opioids for pain management following robotic surgery. To address the on-going issues of opioid overuse and abuse, the study aimed to examine the use of painkillers in Enhanced Recovery After Thoracic Surgery (ERATS) protocols and determine the impact of alternative pain management approaches on clinical outcomes.
An Institutional Review Board-approved retrospective analysis of a prospectively maintained ...
Boston, MA (April 30, 2021) - A new set of guidelines, developed by AATS and ESTS (European Society for Thoracic Surgery) presented today at the AATS 101st Annual Meeting, recommends a 30-day course of Venous Thromboembolism (VTE) prophylaxis post-discharge for patients undergoing surgical resection for lung or esophagus cancer. The AATS and ESTS formed a multidisciplinary guideline panel that included broad membership to minimize potential bias when formulating recommendations. The McMaster University GRADE Centre supported the guideline development process, including updating or performing systematic reviews and meta-analyses. The results are endorsed by the American Society of Hematology (ASH) and the International Society ...
Global sea level rise associated with the possible collapse of the West Antarctic Ice Sheet has been significantly underestimated in previous studies, meaning sea level in a warming world will be greater than anticipated, according to a new study from Harvard researchers.
The report, published in Science Advances, features new calculations for what researchers refer to as a water expulsion mechanism. This occurs when the solid bedrock the West Antarctic Ice Sheet sits on rebounds upward as the ice melts and the total weight of the ice sheet decreases. The bedrock sits below sea level so when it lifts, it pushes water from the surrounding area into the ocean, adding to global ...
An international research group led by Prof. WANG Bo and Prof. SHI Gongle from the Nanjing Institute of Geology and Palaeontology of the Chinese Academy of Sciences (NIGPAS) collected approximately 25,000 fossil-containing amber samples and about 5,000 fossil plants in Zhangpu County, Fujian Province, southeast China from 2010 to 2019.
Their findings were published in Science Advances on April 30.
The Zhangpu biota, including amber biota and co-occurring megafossils, is the richest tropical seasonal rainforest biota discovered so far. It reveals that ...
Researchers from the Carl R. Woese Institute for Genomic Biology in collaboration with scientists at Oxford University have published a paper in Cell reporting the function of LanCL proteins. These proteins are found in eukaryotic cells but their function was previously unknown. The study is the first step towards understanding the importance of these ubiquitous proteins.
Bacteria contain enzymes called LanC that are capable of producing small proteins called lanthipeptides, which are characterized by the addition of a thiol group to a modified serine or threonine amino acid. Similar proteins--called LanC-like ...
UNIVERSITY PARK, Pa.-- Not all public figures are equally beloved, and sometimes when more controversial celebrities get sick, it may negatively affect people's health intentions. In a study of people's reactions to radio host Rush Limbaugh's announcement of a lung cancer diagnosis and Kentucky Sen. Rand Paul's announcement of a diagnosis of COVID-19, researchers at Penn State found that those who took pleasure in their misfortune were themselves less likely to take steps to prevent lung cancer or COVID-19.
"Schadenfreude is the emotion of feeling pleasure in another's misfortune," said Jessica Gall Myrick, associate professor of media studies. "In our study, after learning the news of a politician's ...
Passed in 2018, the First Step Act sought to address re-entry challenges for inmates in the federal prison system. The legislation called for developing an assessment tool to identify inmates for release who had the lowest likelihood of recidivism. A new study assessed how the tool was developed and is used, finding that a greater proportion of inmates could reduce their risk and become eligible for early release over time if they participated in a re-entry program and did not incur infractions. This finding has implications for efforts to reduce prison populations during the COVID-19 pandemic.
The study, by researchers at the University of Nebraska ...
eNeuro is publishing a special collection of commentaries on April 30, 2021 on the neuroscience documentary In Silico. The collection, titled "Epistemological Lessons from the Blue and Human Brain Projects," features reactions to the documentary from leading neuroscientists as well as a discussion on brain modelling and massive research collaborations in general.
Noah Hutton's In Silico follows neuroscientist Henry Markram and his attempt to develop a computer model of the brain. The collaboration, called The Human Brain Project, received €1 billion in funding and pledged to build a full model within ten years. The documentary chronicles Markram and ...
