Utilizing Machine Learning to Model Interdependency of Bulk Molecular Weight, Solution Concentration, and Thickness of Spin Coated Polystyrene Thin Films

Abstract

Spin coating is a wide-spread, quick, and inexpensive method to create nanometer-thick thin films of various polymers, such as polystyrene, on top of solid substrates. Since the film thickness determines the mechanical, optical, and degradation properties of the coated film, it is essential to develop a simple method to predict thickness based on other manipulatable factors. In this study, a three-dimensional manifold relating initial solution concentration, thin film coverage thickness, and monodisperse bulk molecular weight is developed utilizing curve-fit machine learning. The model is able to receive polystyrene bulk molecular weight and desired thin film thickness as input and output an accurate prediction of initial solution concentration required to generate a coating of a desired thickness.