Home // ALLDATA 2018, The Fourth International Conference on Big Data, Small Data, Linked Data and Open Data // View article

Monitoring of Coastal Environments Using Data Mining

Authors:
Corneliu Octavian Dumitru
Gottfried Schwarz
Mihai Datcu

Keywords: coastal monitring; data mining; Sentinel-1; Sentinel-2; TerraSAR-X

Abstract:
Current satellite images provide us with detailed information about the state of our planet, as well as about our technical infrastructure and human activities. A range of already existing commercial and scientific applications try to analyze the physical content and meaning of satellite images by exploiting the data of individual, multiple or temporal sequences of images. However, what we still need today are advanced tools to automatically analyze the image data in order to extract and understand their full content. In this paper, we propose a highly automated approach for application-adapted image content exploration, targeting coastal environmental monitoring. For the selected coastal areas, different use cases can be considered such as: detection of wind turbines vs. boats, differences between beaches, tidal flats, and dams, and identification of fish cages/aquaculture. The average accuracy is ranging from 80% to 95% depending on the satellite images.

Pages: 34 to 39

Copyright: Copyright (c) IARIA, 2018

Publication date: April 22, 2018

Published in: conference

ISSN: 2519-8386

ISBN: 978-1-61208-631-6

Location: Athens, Greece

Dates: from April 22, 2018 to April 26, 2018