Abstract
Polymer science, a discipline focusing on the synthesis, characterization, and application of macromolecules, has increasingly benefited from the adoption of machine learning (ML) techniques. Among these, Support Vector Machines (SVMs) stand out for their ability to handle nonlinear relationships and high-dimensional datasets, which are common in polymer research. This review explores the diverse applications of SVM in polymer science. Key examples include the prediction of mechanical and thermal properties, optimization of polymerization processes, and modeling of degradation mechanisms. The advantages of SVM are contrasted with its challenges, including computational cost, data dependency, and the need for hyperparameter tuning. Future opportunities, such as the development of polymer-specific kernels and integration with real-time manufacturing systems, are also discussed.