TY  - EJOU
AU  - Kaur, Manjodh 
AU  - Randhawa, Princy 
AU  - Jaiswal, Jitendra 
AU  - Dubal, Deepak 
AU  - Bulakhe, Ravindra N. 
AU  - Balakrishnan, Deepanraj 
AU  - Naik, Nithesh 

TI  - Data-Driven Materials Science Using Machine Learning and Computational Modeling
T2  - Computers, Materials \& Continua

PY  - 2026
VL  - 88
IS  - 2
SN  - 1546-2226

AB  - This review emphasizes the growing role of artificial intelligence (AI) in transforming the materials discovery process into a data-driven and autonomous approach. It systematically traces the evolution of scientific paradigms in materials science and examines how machine learning, generative models, and AI agents are revolutionizing the design, screening, and optimization of materials. A key contribution is a detailed, step-by-step machine learning framework that guides researchers through data collection, preprocessing, feature engineering, model development, and validation, utilizing publicly available materials databases and computational tools. Additionally, the review discusses the latest advances in generative AI and autonomous research systems, highlighting their potential to enable inverse design and closed-loop experiments. It includes a tutorial case study on sodium-ion battery materials to demonstrate practical application in formation energy prediction via machine learning, along with comparisons to high-throughput screening accuracy using density functional theory (DFT). The article also addresses current challenges such as data limitations, model interpretability, and physics-based approaches. Overall, this publication serves as both a conceptual and practical guide for integrating AI into materials research, aiming to accelerate the discovery process and improve efficiency.
KW  - Artificial intelligence; materials science; materials discovery; energy materials; computational modeling

DO  - 10.32604/cmc.2026.079503