Machine Learning Classifies Carbon Nanotube and Graphene Composites with 94.7% Accuracy
bioengineer.orgResearchers developed an XGBoost model that classifies nanocomposite materials using structural and thermal characterization data, achieving 94.7% accuracy and an F1-score of 95%. The study focused on composites reinforced with carbon nanotubes and graphene, materials important for lightweight and high-strength applications in aerospace, automotive, and renewable energy systems. Traditional material testing is slow and labor-intensive. This automated approach uses hyperparameter optimization and 10-fold cross-validation to quickly identify material components, potentially accelerating screening for advanced composites. The findings, published in the Journal of Materials Science: Materials in Engineering, show how AI can support faster material selection for next-generation engineering and biomedical applications.
