Investigating the Impact of Bidispersity on Spin-Coated Polystyrene Thin Films Using Machine Learning
Abstract
The thickness of spin-coated polystyrene (PS) thin films largely influences their physical properties. While industrial applications primarily utilize polydisperse PS, existing models address only monodisperse systems. We created bidisperse PS films across varying concentrations, molecular weights, and blend ratios, evaluated monodisperse models with bidisperse data, and tested other machine learning models. We discovered that bidisperse films were systematically thinner than monodisperse films of equivalent weight-average molecular weight, with the overlap parameter (c/c*) emerging as a key predictor. Our Gaussian Process Regression achieved MAPE = 3.82% (63% improvement over monodisperse models), R^2 = 0.9919, and RMSE = 75.2 Å.
[Manuscript submitted for publication]
Conferences, Distinctions, and Publications
We presented our research at the Garcia Scholars Program end-of-summer symposium (August, 2024)
We shared our research through an oral presentation at the Materials Research Society fall meeting (December, 2024)
I presented our research through an oral presentation at the American Physical Society global summit (March, 2025)
Manuscript submitted for publication to MRS Communications (November, 2025)
Click to see our abstract!
Click to see our abstract!
Click to view the yearbook for the Garcia Scholars Program. See our abstract on pages 67.