YOLO algorithm for shipping waste discharges detection at Swedish waters based on fused satellite images with ship AIS data

Conference poster, 2025

The tank cleaning operations may pose a threat to the marine environment. Reports from the Swedish national audit office indicate that ships planning to clean sometimes deviate from routine routes, which suggest a role for analytics based on their navigation data e.g., AIS data and remote sensing data. By examining trajectories and their spatial and temporal attributes, it is possible to identify unusual movement patterns and flag potential non-compliant operations.
• Develop a feature engineered ML framework for anomaly detection
• Leverage image-processing algorithms on satellite images to cross-check detected anomalies