Graduation Year
2025
Document Type
Thesis
Degree
M.S.C.S.
Degree Name
MS in Computer Science (M.S.C.S.)
Degree Granting Department
Computer Science and Engineering
Major Professor
Lawrence Hall, Ph.D.
Committee Member
Dimitry B. Goldgof, Ph.D.
Committee Member
Shaun Canavan, Ph.D.
Keywords
AI Aided Molecular Design, Data Efficient Design, Deep Neural Network, Priming and Tuning
Abstract
In polymer chemistry, compatibilization involves adding a substance often a block or graft copolymerto stabilize polymer blends that would otherwise not mix well, leading to rough structures and weak me- chanical properties. Compatibilizers improve miscibility and reduce interfacial tension, which is critical for applications such as mixed-waste polymer recycling. Sequence-controlled polymers offer unique potential by combining the tunable chemistry of synthetic polymers with the precise, function-driven design of biological macromolecules, but unlike proteins, they lack large, evolution-shaped datasets to guide discovery. This research develops a deep learning framework to predict the surface tension of sequence-controlled copolymer compatibilizers across varying concentrations. Measuring surface tension experimentally is time-consuming, so we evaluate several machine learning approaches and find deep neural networks most effective, achieving an R2 of 0.91. To address data scarcity, we propose a priming-and-tuning strategy, where a model trained on a low-fidelity sequence–property dataset is efficiently fine-tuned for high-fidelity predictions under new con- ditions. This reduces data requirements, accelerates the design of polymer compatibilizers, and demonstrates the broader potential of AI-guided molecular desig
Scholar Commons Citation
Islam, Md Mushfiqul, "Reducing Data Requirements in Polymer Science: Deep Neural Networks For Predicting Surface Tension of Copolymer Compatibilizers" (2025). USF Tampa Graduate Theses and Dissertations.
https://digitalcommons.usf.edu/etd/11088
