The Norwegian Maritime AI Center demonstrates the potential of artificial intelligence through a diverse portfolio of industrial use cases. 

Each use case brings together researchers and user partners to prototype, test, and validate new AI solutions, ranging from ship design and energy optimisation to autonomous navigation and predictive maintenance.

Together, these use cases represent the entire maritime value chain and show how AI can make shipping smarter, safer, and more sustainable.

UC1: AI-Supported Ship Design

Objective: Enhance the efficiency, accuracy, and creativity of the ship design process.

Summary: Developing AI tools for automated design exploration and optimisation. Generative models create and evaluate design variants, integrate simulation data, and build knowledge graphs that connect design requirements, performance, and documentation. This is expected to lead to faster, greener, and safer vessel designs.

UC2: Maritime Traffic Surveillance

Objective: Detect anomalies, security threats, and unsafe ship behaviour using AI.

Summary: Using multimodal AI models that combine AIS, radar, and satellite data to identify abnormal vessel movements and security risks in real time. Results will improve national maritime situational awareness and safety.

UC3: AI-Driven S-100 Electronic Navigational Charts

Objective: Improve navigation safety through smarter digital chart products.

Summary: AI agents enrich and update S-100 ENC data products with predictive insights and uncertainty information, improving the accuracy and responsiveness of navigational data available to vessels and maritime authorities.

UC4: Decision Support for Remote Operation of Uncrewed Vessels

Objective: Simplify and improve situational awareness for operators managing multiple vessels remotely.

Summary: Using AI models trained on alarm and status data to present operators with a clear overview of vessel health and operations, reducing cognitive load and enabling safer, more efficient fleet control.

UC5: Operational Optimisation for Ships with Wind-Assisted Propulsion (WAP)

Objective: Maximise the performance of wind-assisted ships through real-time AI optimisation.

Summary: AI models predict fuel consumption and emissions, while edge-AI agents adjust sails and rudders dynamically for optimal energy efficiency and environmental performance.

UC6: Predictive Maintenance and Continuous Assurance

Objective: Use AI to monitor and predict the health of ship equipment and systems.

Summary: Developing AI-based diagnostics and prognostics for machinery and propulsion systems. Enables proactive maintenance planning and strengthens safety assurance across fleets.

UC7: Situational Awareness for Ship Navigation – Edge AI and Assurance

Objective: Improve navigational safety with AI-enhanced radar and sensor data.

Summary: AI models combine radar, AIS, and rule-based reasoning (COLREG) to detect collision risks and ensure compliance with international navigation rules, paving the way for safer autonomous and crewed navigation.

UC8: AI Agents in System Simulations

Objective: Increase realism and insight in simulation environments.

Summary: Implementing human-like AI agents in dynamic simulations using reinforcement learning and generative AI. The agents simulate operators, enabling better training, validation, and system optimisation.

UC9: Underwater Radiated Noise Monitoring

Objective: Reduce underwater noise pollution and improve propulsion efficiency.

Summary: AI models analyse acoustic data to identify cavitation and vibration sources. Results help optimise propeller design and operation for quieter, more energy-efficient ships.

UC10: Green Energy Storage Systems

Objective: Improve the safety and efficiency of hybrid energy systems.

Summary: AI agents forecast and manage battery and fuel-cell usage in ships and ports. Predictive models support optimal charging, state-of-health monitoring, and integration with shore power systems.

UC11: AI for Smart Testing of Autonomous Navigation Systems

Objective: Automate and accelerate safety testing of complex autonomous systems.

Summary: AI-guided testing frameworks identify critical test cases and reduce verification effort while maintaining reliability and compliance with maritime safety standards.

UC12: Arctic Maritime Operations

Objective: Use AI to enhance safety and efficiency in ice-covered waters.

Summary: Integrating satellite and in-situ sensor data with AI models for ice mapping, forecasting, and dynamic route planning, enabling safer navigation and operations in Arctic environments.

UC13: AI-Based Forecasting and Analytics for Shipbroking

Objective: Improve decision-making in shipping transactions through AI-driven analytics.

Summary: Combining traffic, metocean, and business data to forecast costs, rates, emissions, and port logistics — supporting smarter, more sustainable commercial operations.

Tier-2 Use Cases and Student Projects

In addition to the main cases, MAI supports a range of smaller industrial pilots and student-driven projects exploring AI in shipbuilding, logistics, energy management, and simulation.

Over 200 master’s students will contribute through these use cases, bridging research and practice while preparing for the future of maritime AI.