Accessibility navigation


Intelligent Marine Pollution Analysis on Spectral Data

Prakash, N., Stahl, F. ORCID: https://orcid.org/0000-0002-4860-0203, Mueller, C. L., Ferdinand, O. and Zielinski, O. (2022) Intelligent Marine Pollution Analysis on Spectral Data. In: OCEANS 2021, 20-23 SEPT 2021, San Diego, Porto, pp. 1-6, https://doi.org/10.23919/OCEANS44145.2021.9706056.

[img]
Preview
Text - Accepted Version
· Please see our End User Agreement before downloading.

2MB

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.23919/OCEANS44145.2021.9706056

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.

Item Type:Conference or Workshop Item (Paper)
Refereed:Yes
Divisions:Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
ID Code:106763

Downloads

Downloads per month over past year

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation