A team of MU researchers are applying one of the first uses of artificial intelligence principles to the field of materials science
Discovering how atoms — such as a single layer of carbon atoms found in graphene, one of the world’s strongest materials — work to create a solid material is currently a major research topic in the field of materials science, or the design and discovery of new materials. At the University of Missouri, researchers in the College of Engineering are applying one of the first uses of deep learning — the technology computers use to intelligently perform tasks such as recognizing language and driving autonomous vehicles — to the field of materials science.
“You can train a computer to do what it would take many years for people to otherwise do,” said Yuan Dong, a research assistant professor of mechanical and aerospace engineering and lead researcher on the study. “This is a good starting point.”
Dong worked with Jian Lin, an assistant professor of mechanical and aerospace engineering, to determine if there was a way to predict the billions of possibilities of material structures created when certain carbon atoms in graphene are replaced with non-carbon atoms.
“If you put atoms in certain configurations, the material will behave differently,” Lin said. “Structures determine the properties. How can you predict these properties without doing experiments? That’s where computational principles come in.”
Lin and Dong partnered with Jianlin Cheng, a William and Nancy Thompson Professor of Electrical Engineering and Computer Science at MU, to input a few thousand known combinations of graphene structures and their properties into deep learning models. From there, it took about two days for the high-performance computer to learn and predict the properties of the billions of other possible structures of graphene without having to test each one separately.
Researchers envision future uses of this artificial intelligence assistive technology in designing many different graphene related or other two-dimensional materials. These materials could be applied to the construction of LED televisions, touch screens, smartphones, solar cells, missiles and explosive devices.
“Give an intelligent computer system any design, and it can predict the properties,” Cheng said. “This trend is emerging in the material science field. It’s a great example of applying artificial intelligence to change the standard process of material design in this field.”
Learn more: Teaching computers to intelligently design ‘billions’ of possible materials
The Latest on: Material science
[google_news title=”” keyword=”material science” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Material science
- Warner Bros. lands seven-figure rights deal for Avengelyne starring Margot Robbie with Olivia Wilde set to direct the comic book adaptationon April 30, 2024 at 5:00 pm
He said the project, 'started through my relationship with super-producer Simon Kinberg who told me he had a perfect fit for the material and asked me to trust him. 'Next thing I’m meeting with Margot ...
- Scientists find new porous material that stores greenhouse gaseson April 30, 2024 at 9:35 am
A team of scientists led by Heriot-Watt University developed a new type of porous material comprising hollow, cage-like molecules that can store greenhouse gases.
- Physicists show that light can generate electricity even in translucent materialson April 30, 2024 at 8:38 am
Some materials are transparent to light of a certain frequency. When such light is shone on them, electrical currents can still be generated, contrary to previous assumptions. Scientists have managed ...
- New class of spongy materials can self-assemble into precisely controllable structureson April 30, 2024 at 8:02 am
A team of researchers led by the University of Massachusetts Amherst has drawn inspiration from a wide variety of natural geometric motifs—including those of 12-sided dice and potato chips—in order to ...
- Dow showcases circular and innovative materials science solutions and industry collaborations at Chinaplas 2024on April 29, 2024 at 7:11 pm
Dow (NYSE: DOW), announced two new partnerships at Chinaplas 2024 to develop solutions that meet both performance and circular demands.
- Scientists Say New Material Can Suck Carbon Out of Atmosphere Faster Than Treeson April 29, 2024 at 4:30 pm
Scientific Alchemy A team of scientists in the United Kingdom say they have discovered a porous material that has the potential capacity to store large quantities of greenhouse gases, The Independent ...
- Scientists develop strong yet reusable adhesive from smart materialson April 29, 2024 at 11:53 am
Scientists from Nanyang Technological University, Singapore (NTU Singapore) have developed a smart, reusable adhesive more than 10 times stronger than a gecko's feet adhesion, pointing the way for ...
- Quantum challenge to be solved one mile undergroundon April 29, 2024 at 8:32 am
Radiation from space is a challenge for quantum computers as their computation time becomes limited by cosmic rays. Researchers from Chalmers University of Technology, Sweden, and University of ...
- Beyond Graphene: A New World of 2D Materials Is Opening Upon April 28, 2024 at 9:07 pm
Materials that are incredibly thin, only a few atoms thick, exhibit unique properties that make them appealing for energy storage, catalysis, and water purification. Researchers at Linköping ...
- The Novel Material Revolutionizing Energy Storageon April 28, 2024 at 10:00 am
Washington University in St. Louis scientists have developed a novel material that supercharges innovation in electrostatic energy storage, with the potential to revolutionize electronic devices.
via Bing News