Abstract
<jats:p>Accurate prediction of material properties is essential for accelerating the development of advancedengineering materials, particularly those incorporating nanoscale features. Traditional experimentaland physics-based modeling approaches, while reliable, are often limited by high computational costand the complexity of capturing nonlinear nanoscale interactions. This study presents an integratedpredictive modeling framework that combines nanotechnology-derived material descriptors withartificial intelligence techniques to estimate key material properties. Nanoscale parameters such asparticle size, volume fraction, and structural characteristics are used as inputs to train machine learningmodels capable of learning complex structure–property relationships. The performance of AI-basedmodels is evaluated and compared with conventional empirical and physics-based approaches. Resultsdemonstrate that the artificial intelligence–driven framework achieves higher prediction accuracy andsignificantly reduced computational effort while maintaining consistency with experimental observations.The proposed approach highlights the potential of combining nanotechnology and artificial intelligenceto support efficient material design and optimization in advanced engineering applications.</jats:p>