(Digital Presentation) Data-Driven Discovery of Luminescent Materials

Abstract

Luminescent materials play an important roles in lighting, display, plant growth, anti-counterfeit, medical and bio-technologies. The search for luminescent materials with desired properties never stops, but relies mostly on the trial-and-error approach, which is time-consuming and labor-intensive. Several methods have been proposed to accelerate the discovery of new luminescent materials, among them the data-driven one attracts much attention. In this presentation, two types of luminescent materials for different applications will be reported. Firstly, we build an emission-prediction model based on machine learning, and using this model found five Eu2+-doped nitride phosphors with highly efficient near-infrared (NIR) emissions. Secondly, we propose selection rules to discover laser phosphors and mechanoluminescent materials based on the structure-property relations, respectively. The applications of these phosphors in NIR detectors, laser lighting and stress mapping will also demonstrated.