Research Interest

Research on RTP materials has recently gained momentum because of their potential applications in the fields of organic light-emitting diodes (OLEDs), anti-counterfeiting and bioimaging techniques. Constructing RTP materials with high phosphorescence quantum yield (Փp) and longer lifetime (Ʈp) is very crucial but challenging. Synthetic strategies will be developed based on a) theory-driven approach and b) data-driven approach to construct effective RTP materials.

​

An experienced chromophoric chemist can predict compositions of chromophores with a naked eye based on his experience by differentiating the color of the chromophores and it requires high skill and expertise in the relevant field. On the other hand, for beginners, it is a really difficult task. Recently, artificial intelligence (AI) has changed many aspects of modern science. Machine learning (ML), as a subset of AI, is a fast-growing technique to recognize and classify patterns rapidly within data and discover unforeseen trends from the same which is impossible for an ordinary human being. In order to bridge the knowledge gap between an experienced chemist and a beginner, and to enhance the capability of analytical skills in the prediction of chromophoric mixtures, ML can be employed by integrating the digital images of chromophoric solutions with deep learning techniques, a sort of ML.