Data-Driven Development of Phosphors for LED Lighting

Abstract

The development of new phosphors that are necessary for the next generation of high efficiency LED lighting requires a unique approach for materials discovery. Researchers often rely on chemical substitution or serendipity to identify new materials; however, this inevitably leads to slow, incremental advances in technology development. Our work has recently created a new approach using data science and synthesis in tandem to produce new materials with impressive optical properties. Using data mining techniques, we extract experimental optical properties from the peer-review literature and then use these data to predict quantum yield, thermal quenching, and excitation and emission wavelength. Following this methodology, our research has developed several materials ranging from borates to nitrides. Moreover, the complementary use of computational modeling provides additional insight into the fundamental composition, structure, and property relationship, which is necessary for the continued advanced optical materials.