Romain Gautier is a CNRS research scientist at the Institut des Matériaux de Nantes Jean Rouxel. His expertise lies in the synthesis and structural characterization of new functional inorganic and hybrid materials for optics. He received his Ph.D. in 2010 from the Ecole Nationale Supérieure de Chimie de Rennes and then joined Northwestern University for a postdoc. In recent years, he has employed Machine Learning approaches to assist and accelerate the discovery of new materials. He is the recipient of the CNRS Bronze medal and the National Chinese Award of the "1000 Young Talents Program."

Machine Learning Assisted Discovery of Photoluminescent Materials

The design of photoluminescent materials with specific characteristics is a complicated task as very small modifications in the chemistry or crystal structure of materials can have drastic effects on the optical properties. Thus, the presence of dopants/defects in very low concentrations combined with different phenomena (reabsorption, energy transfer, …) make, in most cases, optical properties difficult to predict prior to synthesis and characterization. 
In this context, we use machine learning approaches to guide the discovery of materials with white-light emission for applications in solid-state lighting. In this talk, different families of materials doped with rare earth metal ions ((CaMg)x(NaSc)1–xSi2O6:Eu2+, Li2BaSiO4:Eu,Ce, …) will be presented. Such materials can exhibit broad or narrow band light emissions and relatively high photoluminescence quantum yields. Machine learning tools were used to identify the key experimental parameters to design phosphors with specific photoemission colors.