2026 ASEE Annual Conference & Exposition

Interdisciplinary Learning Design: Machine Learning Assisted Brewster Angle Microscopy Image Analysis for Biodegradable Poly(caprolactone)-based Langmuir Films

Presented at Materials Division (MATS) Poster Session

Abstract: Interdisciplinary learning and collaboration skills have become critically important in the age of artificial intelligence. In this study, a team spanning physical chemistry and polymer sciences, mathematics, as well as computer science and engineering was formed to explore the applications of advanced machine learning (ML) algorithms in analyzing Brewster angle microscopy (BAM) images. While ML techniques have gained significant attention for microscopy image analysis, this study represents a pioneering effort to harness their power for analyzing BAM images. The BAM technique is one of the most effective methods for in-situ visualizing the surface morphology of quasi-two-dimensional (2D) condensed phases formed at the air/water (A/W) interface. BAM’s real-time imaging capability arises from the differences in refractive index among the gaseous (G), liquid-expanded (LE), liquid-condensed (LC), and solid phases of the Langmuir film formed at the A/W interface. This paper highlights the design framework and research outcomes of three modules: (a) crystallization and phase separation of biodegradable poly(caprolactone) (PCL)/oligomeric polystyrene (o-PS)-based binary blends at the A/W interface; (b) advanced ML workflows for denoising and enhancing BAM images using a generative AI–based deep learning framework. The workflow leverages Python and PyTorch/TensorFlow on CPUs or GPUs to accelerate model training and improve overall efficiency, and (c) segmentation and quantitative analysis workflow using MATLAB for raw and ML-processed images to identify, refine, and measure the phase-separated domains.

Authors

Yeonhyang Kim Central Michigan University
Hiruni Kamali Pallage http://orcid.org/0009-0003-7686-1915 Central Michigan University [biography]

Hiruni Pallage is an Assistant Professor of Mathematics at Centre College. She earned her Ph.D. in Mathematics from Central Michigan University, where her research focused on interpolation and data-driven methods for improving brain imaging techniques.

Her research lies in applied and interdisciplinary mathematics, including image processing, data analysis, and mathematical modeling, with applications in neuroscience and materials science. Her work spans topics such as interpolation on spherical domains, dynamical sampling, and image-based analysis of polymer morphologies, and has been published in journals including the Journal of Mathematical Analysis and Applications and Colloids and Surfaces A.

Dr. Pallage is committed to integrating research into undergraduate education. At Centre College, she teaches courses in calculus, linear algebra, operations research, and advanced interpolation methods, emphasizing mathematical modeling, computation, and real-world applications. She has presented her work at national conferences, including invited sessions at the Joint Mathematics Meetings.
Linxi Zhang Central Michigan University
Grant Wang University of Michigan
Prof. Bingbing Li Central Michigan University [biography]

Prof. Bingbing Li (the corresponding author), the Department of Chemistry and Biochemistry, Central Michigan University. Dr. Li is a Professor and Chair of Chemistry and Biochemistry at Central Michigan University.
Address: Department of Chemistry and Biochemistry, Central Michigan University, Mt Pleasant, MI 48859, USA.
Corresponding author email: li3b@cmich.edu

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 21, 2026, and to all visitors after the conference ends on June 24, 2026

« View session

For those interested in:

computer science
engineering
Faculty
undergraduate