| Abstract Scope |
Artificial intelligence (AI) and machine learning (ML) are transforming the design and development of natural fiber-reinforced polymer (NFRP) composites by enabling data-driven optimization of materials, manufacturing processes, and structural performance. This review critically examines recent advances in AI and ML applications for predicting mechanical, thermal, and durability properties of NFRP composites. Different learning approaches, including artificial neural networks, support vector machines, random forests, Gaussian process regression, and deep learning, are evaluated with respect to material selection, process optimization, failure prediction, and performance assessment. The integration of experimental databases, multiscale simulations, and explainable AI is discussed to improve prediction reliability and accelerate materials discovery. Current challenges, including limited datasets, data quality, model interpretability, and standardization, are analyzed together with future opportunities involving digital twins, autonomous laboratories, and generative AI. This review highlights the potential of AI-driven methodologies to advance sustainable composite design and engineering applications. |