Corrosion science is undergoing a major transformation as experimental electrochemistry, computational chemistry, and data-driven methods increasingly converge. Data-Driven Corrosion Science: Artificial Intelligence, Computational Chemistry and Predictive Electrochemistry presents a critical overview of this evolving landscape, with emphasis on how modern computational and artificial intelligence tools can complement mechanistic understanding rather than replace it. The book brings together perspectives spanning physics-informed AI, density functional theory and machine-learning force fields, digital twins, electrochemical impedance spectroscopy, generative molecular design, materials informatics, explainable and trustworthy AI, and autonomous experimentation. Across these themes, particular attention is given to data quality, uncertainty, model interpretability, mechanistic consistency, validation, and the challenge of translating laboratory or computational success into reliable engineering prediction. The volume is intended for researchers, students, corrosion scientists, materials engineers, electrochemists, and data-science practitioners seeking an integrated understanding of emerging computational approaches in corrosion research. It also highlights the limitations, evidence gaps, and methodological priorities that must be addressed before data-driven corrosion science can achieve robust, transferable, and practically meaningful predictive capability.
Author(s)
Dr. Anil Kumar
P.G. Department of Chemistry, Sahibganj College Sahibganj, Jharkhand-816109, India.
ISBN 978-81-69986-99-1 (Print)
ISBN 978-81-69986-98-4 (eBook)
DOI: https://doi.org/10.9734/bpi/mono/978-81-69986-99-1
Corrosion science is undergoing a major transformation as experimental electrochemistry, computational chemistry, and data-driven methods increasingly converge. Data-Driven Corrosion Science: Artificial Intelligence, Computational Chemistry and Predictive Electrochemistry presents a critical overview of this evolving landscape, with emphasis on how modern computational and artificial intelligence tools can complement mechanistic understanding rather than replace it. The book brings together perspectives spanning physics-informed AI, density functional theory and machine-learning force fields, digital twins, electrochemical impedance spectroscopy, generative molecular design, materials informatics, explainable and trustworthy AI, and autonomous experimentation. Across these themes, particular attention is given to data quality, uncertainty, model interpretability, mechanistic consistency, validation, and the challenge of translating laboratory or computational success into reliable engineering prediction. The volume is intended for researchers, students, corrosion scientists, materials engineers, electrochemists, and data-science practitioners seeking an integrated understanding of emerging computational approaches in corrosion research. It also highlights the limitations, evidence gaps, and methodological priorities that must be addressed before data-driven corrosion science can achieve robust, transferable, and practically meaningful predictive capability.