Physics informed neural networks for maritime energy systems and blue economy innovations

Abstract

Sustainable development in the blue economy demands innovative approaches to address marine challenges such as energy services, climate change, overfishing, and pollution. This paper reviews physics-informed artificial intelligence (AI) and machine learning (ML) techniques, focusing on physics-informed neural networks (PINNs) methods and their transformative application to maritime systems. PINNs integrate physical laws directly into data-driven models, ensuring that simulations adhere to fundamental principles while assimilating real-world data. The study reviews how these advanced methods have been adapted, from fields such as energy, healthcare, and aerospace, for blue economy applications such as modeling ocean currents, optimizing marine renewable energy systems, and forecasting coastal hazards. The paper explores how PINN-based approaches can enhance decision-making in sustainable fisheries management, harmful algal bloom detection, coral reef health monitoring, marine debris and plastic pollution identification, fish stock and biodiversity assessment, and oil spill and anomaly detection. By bridging empirical data with the governing equations of marine ecosystems, physics-based techniques provide scalable, high-fidelity solutions that empower policymakers and industry leaders to make informed decisions. Ultimately, this study assesses the potential of physics-informed AI/ML (PIAI/PIML)—especially PINNs—to drive transformative progress in the blue economy, by promoting sustainable use of marine resources and resilient coastal management.