Abstract/Summary

Maritime ship traffic is globally increasing, with 90% of the world trade carried over the ocean. The emissions of marine traffic and coastal population, especially in ports and along shipping lanes with dense workloads, are a severe threat to the marine environment. Therefore, we propose a complete monitoring network to continuously monitor ship emissions by identifying oil soot, exhaust fumes and plastic litter on the sea surface. It is an intelligent integrated on-board system for spatial-spectral marine pollution analysis on buoys and static platforms. The system architecture consists of spectral vision systems (VIS, IR-thermal) with radiometers (UV-VIS-NIR) for spot data analysis. The study describes the proposed sensor system architecture evaluated with synthetic data analysis using a state-of-the-art Deep Learning algorithm. Combining our sensor system with other environmental observations will eventually integrate multi-sensor information towards a reliable holistic situational awareness of the marine ecosystem. Index Terms—Maritime traffic, marine pollution, ship emissions, black carbon, oil soot, plastic litter, buoy, artificial intelligence, spectral data analysis, machine learning, sensor data fusion.