Data-Driven Prediction of Polymer Nanocomposite Tensile Strength Through Gaussian Process Regression and Monte Carlo Simulation with Enhanced Model Reliability

This study presents a robust machine learning framework based on Gaussian process regression (GPR) to predict the tensile strength of polymer nanocomposites reinforced with various nanofillers and processed under diverse techniques. A comprehensive dataset comprising 25 polymer matrices, 22 surface functionalization methods, and 24 processing routes was constructed from the literature. GPR, coupled with Monte Carlo sampling across 2000 randomized iterations, was employed to capture nonlinear dependencies and uncertainty propagation within the dataset. The model achieved a mean coefficient of determination (R²) of 0.96, RMSE of 12.14 MPa, MAE of 7.56 MPa, and MAPE of 31.73% over 2000 Monte Carlo iterations, outperforming conventional models such as support vector machine (SVM), regression tree (RT), and artificial neural network (ANN). Sensitivity analysis revealed the dominant influence of Carbon Nanotubes (CNT) weight fraction, matrix tensile strength, and surface modification methods on predictive accuracy. The findings demonstrate the efficacy of the proposed GPR framework for accurate, reliable prediction of composite mechanical properties under data-scarce conditions, supporting informed material design and optimization.