Prediction of light absorption properties of organic dyes using machine learning technology

The organic dye molecules have attracted significant attention due to their wide range of potential applications. However, the traditional method is time-consuming, while experimental synthesis methods involve complex processes. To streamline the performance evaluation process, we focus on predicting the absorption spectra of organic dyes without using excited states calculations. We built four prediction models of machine learning algorithms and used them to predict the absorption spectra of organic dyes. We obtained a machine learning model that can efficiently predict the absorption spectrum of dye molecules by optimizing the structure and energy level information of the ground state of dyes.