Close

Search

Search Menu
Photonics Media Photonics Buyers' Guide Photonics Spectra BioPhotonics EuroPhotonics Vision Spectra Photonics Showcase Photonics ProdSpec Photonics Handbook
More News

Neural Networks Predict Crystal Stability

Facebook Twitter LinkedIn Email Comments
SAN DIEGO, Sept. 21, 2018 — Researchers at the University of California, San Diego (UCSD) are using neural networks to predict the stability of materials in two classes of crystals: garnets and perovskites.

They trained artificial neural networks to predict a crystal’s formation energy using just two inputs: electronegativity and ionic radius of the constituent atoms. Based on this work, they developed models that can identify stable materials in two classes of crystals. According to the team, its models are up to 10× more accurate than previous machine learning models and are fast enough to efficiently screen thousands of materials in a matter of hours on a laptop.

Using NNs to predict the stability of materials, UCSD.

Schematic of an artificial neural network predicting a stable garnet crystal prototype. Courtesy of Weike Ye.

“Garnets and perovskites are used in LED lights, rechargeable lithium-ion batteries, and solar cells. These neural networks have the potential to greatly accelerate the discovery of new materials for these and other important applications,” said researcher Weike Ye.

The team has made their models publicly accessible via a web application at http://crystals.ai so that others can use the neural networks to compute the formation energy of any garnet or perovskite composition on the fly.

“Predicting the stability of materials is a central problem in materials science, physics and chemistry,” said professor Shyue Ping Ong. "On one hand, you have traditional chemical intuition such as Linus Pauling’s five rules . . . On the other, you have expensive quantum mechanical computations to calculate the energy gained from forming a crystal . . . What we have done is to use artificial neural networks to bridge these two worlds.”

The research was published in Nature Communications (doi:10.1038/s41467-018-06322-x).

Photonics.com
Sep 2018
Research & TechnologyeducationAmericasUniversity of California San Diegomaterialsmaterials processingperovskitescrystalsenergyenvironmentindustrialneural networksdeep neural networkssolar

Comments
back to top
Facebook Twitter Instagram LinkedIn YouTube RSS
©2019 Photonics Media, 100 West St., Pittsfield, MA, 01201 USA, info@photonics.com

Photonics Media, Laurin Publishing
x We deliver – right to your inbox. Subscribe FREE to our newsletters.
We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.