Artificial intelligence and machine learning for sustainable polymeric marine antifouling coatings: current evidence, challenges, and future perspectives

Marine biofouling causes significant economic and environmental impacts by increasing drag, fuel consumption, emissions, maintenance costs, and material degradation. Despite advances in sustainable antifouling coatings, their development still relies largely on trial-and-error approaches. Recent advances in AI, ML, and materials informatics can accelerate the discovery and optimization of sustainable marine antifouling coatings by predicting performance, identifying structure–property relationships, and optimizing formulations while reducing experimental effort. Nevertheless, the direct application of AI and ML specifically to marine antifouling coating design remains relatively limited, and much of the available evidence originates from broader materials science and coating research. Therefore, this review critically examines the emerging application of AI and ML to sustainable polymeric marine antifouling coatings, while distinguishing between directly demonstrated antifouling applications and transferable approaches from related materials systems. The review focuses on the application of AI for predicting fouling resistance, durability, corrosion protection, and environmental sustainability and evaluates the extent to which these approaches can be translated to marine antifouling systems. Key challenges, including data scarcity, heterogeneous experimental datasets, lack of standardized testing protocols, limited field validation, and model interpretability, are highlighted, together with future opportunities in digital twins, explainable AI, generative AI, and autonomous materials discovery for next-generation sustainable antifouling coatings. By critically assessing the current evidence, methodological limitations, and research gaps, this review identifies priorities for developing reliable AI-assisted antifouling coating design frameworks and proposes a staged pathway from standardized data generation and predictive modeling toward experimental validation, active learning, and autonomous materials discovery. AI and machine learning approaches for sustainable marine antifouling coatings are critically reviewed. Current evidence is distinguished between direct antifouling applications and transferable materials-science approaches. Key challenges include data scarcity, heterogeneous datasets, limited standardization, and field validation. Emerging tools include explainable AI, generative AI, digital twins, and autonomous experimentation. A staged roadmap toward predictive, validated, and sustainable antifouling coating design is proposed.