Application of artificial intelligence in predicting and optimizing material properties

Abstract Artificial intelligence (AI) has become an important and powerful tool in materials science for faster prediction of material properties, new material discovery, and improvement of processing methods. This review presents the use of AI in predicting material properties, optimizing processing parameters, analyzing microstructures, and evaluating material degradation and failure. Machine learning and deep learning techniques used to build structure–property-process relationships and to enable automatic microstructural analysis are discussed under a common AI-based workflow. Major challenges like data quality, model interpretability, and real-world implementation are critically examined, along with recent solutions like physics-informed AI and explainable AI. The main contribution of this review is a process-oriented and framework-based overview that links AI methods with material processing, microstructure development, and lifecycle performance, which makes it different from existing reviews that mainly focus on individual applications.