Engineers use graph networks to accurately predict properties of molecules and crystals
Date | 10th, Jun 2019 |
---|---|
Source | EurekAlert - Scientific News Websites |
DESCRIPTION
Nanoengineers at UC San Diego have developed new deep learning models that can accurately predict the properties of molecules and crystals. The models can enable researchers to rapidly scan the nearly-infinite universe of compounds to discover potentially transformative materials for various applications, cush as high-energy density Li-ion batteries, warm-white LEDs, and better photovoltaics.