P‐111: A Machine Learning Perspective for the Optimization of Annealing Parameters in Solution Processed Thin Film Devices

Abstract

This work adopts machine learning to refine the annealing process in solution‐processed thin films, such as QDs, perovskites, and organic semiconductors. The annealing temperature and time of PbS QD thin film is optimized using a machine learning algorithm. This method offers a systematic approach to determine the optimal annealing parameters, surpassing the traditional, less‐efficient methods. This adaptive model minimizes human bias, handles complex nonlinear relationships, and capable of optimizing multiple parameters simultaneously. By introducing machine learning algorithm, this method provides a universal and effective strategy for the optimization of parameters during the fabrication of thin films.