Teaching computers to intelligently design 'billions' of possible materials

April 02, 2019

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."
The study, "Bandgap prediction by deep learning in configurationally hybridized graphene and boron nitride," was published in npj Computational Materials. Other authors were Chuhan Wu, Chi Zhang and Yingda Lu in the College of Engineering. Funding was provided by an MU start up-fund, NASA Missouri Space Consortium project (#00049784), Department of Energy National Energy Technology Laboratory (DE-FE0031645), National Science Foundation (DBI1759934 and IIS1763246), and a U. S. Department of Agriculture award (#2018-67017-27880). The content is solely the responsibility of the authors and does not necessarily represent the official views of the funding agencies.

University of Missouri-Columbia

Related Graphene Articles from Brightsurf:

How to stack graphene up to four layers
IBS research team reports a novel method to grow multi-layered, single-crystalline graphene with a selected stacking order in a wafer scale.

Graphene-Adsorbate van der Waals bonding memory inspires 'smart' graphene sensors
Electric field modulation of the graphene-adsorbate interaction induces unique van der Waals (vdW) bonding which were previously assumed to be randomized by thermal energy after the electric field is turned off.

Graphene: It is all about the toppings
The way graphene interacts with other materials depends on how these materials are brought into contact with the graphene.

Discovery of graphene switch
Researchers at Japan Advanced Institute of Science and Technology (JAIST) successfully developed the special in-situ transmission electron microscope technique to measure the current-voltage curve of graphene nanoribbon (GNR) with observing the edge structure and found that the electrical conductance of narrow GNRs with a zigzag edge structure abruptly increased above the critical bias voltage, indicating that which they are expected to be applied to switching devices, which are the smallest in the world.

New 'brick' for nanotechnology: Graphene Nanomesh
Researchers at Japan advanced institute of science and technology (JAIST) successfully fabricated suspended graphene nanomesh (GNM) by using the focused helium ion beam technology.

Flatter graphene, faster electrons
Scientists from the Swiss Nanoscience Institute and the Department of Physics at the University of Basel developed a technique to flatten corrugations in graphene layers.

Graphene Flagship publishes handbook of graphene manufacturing
The EU-funded research project Graphene Flagship has published a comprehensive guide explaining how to produce and process graphene and related materials (GRMs).

How to induce magnetism in graphene
Graphene, a two-dimensional structure made of carbon, is a material with excellent mechani-cal, electronic and optical properties.

Graphene: The more you bend it, the softer it gets
New research by engineers at the University of Illinois combines atomic-scale experimentation with computer modeling to determine how much energy it takes to bend multilayer graphene -- a question that has eluded scientists since graphene was first isolated.

How do you know it's perfect graphene?
Scientists at the US Department of Energy's Ames Laboratory have discovered an indicator that reliably demonstrates a sample's high quality, and it was one that was hiding in plain sight for decades.

Read More: Graphene News and Graphene Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.