Machine Learning Enables Highly Accurate Predictions of Photophysical Properties of Organic Fluorescent Materials: Emission Wavelengths and Quantum Yields.

Abstract

The development of functional organic fluorescent materials calls for fast and accurate predictions of photophysical parameters for processes such as high-throughput virtual screening, while the task is challenged by the limitations of quantum mechanical calculations. We establish a database covering >4300 solvated organic fluorescent dyes with 3000 distinct compounds and develop a new machine learning approach aimed at efficient and accurate predictions of emission wavelength and photoluminescence quantum yield (PLQY). Our feature engineering has given rise to a functionalized structure descriptor (FSD) and a comprehensive general solvent descriptor (CGSD), whereby a highly black-box computational framework is realized with consistently good accuracy across different dye families, ability of describing substitution effects and solvent effects, efficiency for large-scale predictions, and workability with on-the-fly learning. Evaluations with unseen molecules suggest a remarkable mean absolute error of 0.13 for PLQY and 0.080 eV for emission energy, the latter comparable to time-dependent density functional theory (TD-DFT) calculations. An online prediction platform was constructed based on the ensemble model to make predictions in various solvents. Our statistical learning methodology will complement quantum mechanical calculations as an efficient alternative approach for the prediction of these parameters.