Harnessing Machine Learning for the Design of Surface Coatings: Challenges and Opportunities
Tu C. Le, Dang-Nhat Nguyen, Daniel M. Kamiński, Tony Kolver, Priya Subramanian, Stuart Bateman
Abstract
Machine learning (ML) has emerged as a transformative tool for the design and optimization of functional materials, offering significant potential to accelerate the discovery and improve performance. In the field of surface coatings, although still in its early stages, ML is increasingly being applied to create novel coating materials with enhanced properties such as adhesion, hardness, durability, and corrosion inhibition. By using data-driven approaches, researchers can optimize formulations and processing conditions more efficiently than traditional trial-and-error methods, paving the way for innovation in advanced coatings that meet specific requirements. This review paper explores the current applications of ML in surface coating research, emphasizing successful case studies that demonstrate its effectiveness in tailoring and enhancing coating properties. The paper also identifies key opportunities and challenges for further integrating ML into coating design workflows.