Artificial neural networks--algorithms inspired by connections in the brain--have "learned" to perform a variety of tasks, from pedestrian detection in self-driving cars, to analyzing medical images, to translating languages. Now, researchers at the University of California San Diego are training artificial neural networks to predict new stable materials.
"Predicting the stability of materials is a central problem in materials science, physics and chemistry," said senior author Shyue Ping Ong, a nanoengineering professor at the UC San Diego Jacobs School of Engineering.
"On one hand, you have traditional chemical intuition such as Linus Pauling's five rules that describe stability for crystals in terms of the radii and packing of ions. On the other, you have expensive quantum mechanical computations to calculate the energy gained from forming a crystal that have to be done on supercomputers. What we have done is to use artificial neural networks to bridge these two worlds."
By training artificial neural networks to predict a crystal's formation energy using just two inputs--electronegativity and ionic radius of the constituent atoms--Ong and his team at the Materials Virtual Lab have developed models that can identify stable materials in two classes of crystals known as garnets and perovskites.
These models are up to 10 times 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. The team details the work in a paper published Sept. 18 in Nature Communications.
"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," noted first author Weike Ye, a chemistry Ph.D. student in Ong's Materials Virtual Lab.
The team has made their models publicly accessible via a web application at http://crystals.
The researchers are planning to extend the application of neural networks to other crystal prototypes as well as other material properties.
Paper title: "Deep Neural Networks for Accurate Predictions of Crystal Stability." Co-authors include Chi Chen, Zhenbin Wang and Iek-Heng Chu, UC San Diego.
This work is supported by the Samsung Advanced Institute of Technology's Global Research Outreach Program.
Liezel Labios | EurekAlert!
Research on light-matter interaction could improve electronic and optoelectronic devices
11.10.2018 | Rensselaer Polytechnic Institute
Unique Deep Learning Infrastructure - DFKI receives first NVIDIA DGX-2 supercomputer in Europe
11.10.2018 | Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI
Scientists at the Max Planck Institute for Polymer Research (MPI-P) in Mainz (Germany) together with scientists from Dresden, Leipzig, Sofia (Bulgaria) and Madrid (Spain) have now developed and characterized a novel, metal-organic material which displays electrical properties mimicking those of highly crystalline silicon. The material which can easily be fabricated at room temperature could serve as a replacement for expensive conventional inorganic materials used in optoelectronics.
Silicon, a so called semiconductor, is currently widely employed for the development of components such as solar cells, LEDs or computer chips. High purity...
Augsburg chemists present a new technology for compressing, storing and transporting highly volatile gases in porous frameworks/New prospects for gas-powered vehicles
Storage of highly volatile gases has always been a major technological challenge, not least for use in the automotive sector, for, for example, methane or...
When we put water in a freezer, water molecules crystallize and form ice. This change from one phase of matter to another is called a phase transition. While this transition, and countless others that occur in nature, typically takes place at the same fixed conditions, such as the freezing point, one can ask how it can be influenced in a controlled way.
We are all familiar with such control of the freezing transition, as it is an essential ingredient in the art of making a sorbet or a slushy. To make a cold...
Thin organic layers provide machines and equipment with new functions. They enable, for example, tiny energy recuperators. In future, these will be installed...
Das Zusammenspiel aus Struktur und Dynamik bestimmt die Funktion von Proteinen, den molekularen Werkzeugen der Zelle. Durch Fortschritte in der...
17.10.2018 | Event News
16.10.2018 | Event News
02.10.2018 | Event News
18.10.2018 | Life Sciences
17.10.2018 | Trade Fair News
17.10.2018 | Life Sciences