Abstract
Continuous monitoring of oil discharges in coastal and open ocean waters using Earth Observation (EO) has undeniably contributed to diminishing their occurrence wherever a detection system was in place, such as in Europe (EMSA's CleanSeaNet) or in the United States (NOAA's OR&R). This study describes the development and testing of a semi-automated oil slick detection system tailored to the Great Barrier Reef (GBR) marine park solely based on EO data as no such service was routinely available in Australia until recently. In this study, a large, curated, historical global dataset of SAR imagery acquired by Sentinel-1 SAR, now publicly available, is used to assess classification techniques, namely an empirical approach and a deep learning model, to discriminate between oil-like features and look-alikes in the scenes acquired over the marine park. An evaluation of this detection system on 10 Sentinel-1 SAR images of the GBR using two performance metrics - the detection accuracy and the false-positive rate (FPR) - shows that the classifiers perform best when combined (accuracy >98 %; FPR 0.01) rather than when used separately. This study demonstrates the benefit of sequentially combining classifiers to improve the detection and monitoring of unreported oil discharge events in SAR imagery. The workflow has also been tested outside the GBR, demonstrating its robustness when applied to other regions such as Australia's Northwest Shelf, Southeast Asia and the Pacific.
| Original language | English |
|---|---|
| Article number | 114598 |
| Pages (from-to) | 1-20 |
| Number of pages | 20 |
| Journal | Marine Pollution Bulletin |
| Volume | 188 |
| DOIs | |
| Publication status | Published - Mar 2023 |
Bibliographical note
Funding Information:The authors are grateful to the Australian Maritime Safety Authority (AMSA) for in-kind support, Dr. Weihao Li, Dr. Lars Petersson and Dr. Zheng-Shu Zhu (CSIRO Data61) for valuable guidance in the use of deep learning and SAR, and CSIRO IM&T for technical support. Dr. Zhibin Li acknowledges continued support from the CSIRO's Machine Learning and Artificial Intelligence Future Science Platform. The contributions of Dr. Gopika Suresh were solely due to her expertise, thus voluntary and not tied to any funding. The lead author is thankful to the European Space Agency for the invitation to attend the 5 th ESA Advanced Training on Ocean Remote Sensing and Synergy course, and Oceandatalab ( https://www.oceandatalab.com ). This research would not have been possible without the satellite data stream provided by the European Space Agency, the Copernicus Sentinel satellites programme and Brockmann Consult for the development and access to SNAP, and the Sentinel Australasia Regional Access (SARA; https://copernicus.nci.org.au/sara.client/#/home ) data access hub (National Computational Infrastructure (NCI); Geoscience Australia). The authors also thank Ms. Kate Shannon and the journal's production team for the professional proof editing of the manuscript, and the two anonymous reviewers for their valuable comments.
Funding Information:
This research, led and largely funded by CSIRO under eReefs (a public-private collaborative project between CSIRO, the Australian Institute of Marine Science, the Bureau of Meteorology, the Great Barrier Reef Foundation and the Queensland Department of Environment and Science; https://ereefs.org.au ), was conducted in close cooperation with the Queensland Department of Environment and Science (DES) and the Australian Maritime Safety Authority (AMSA). An initial three-year funding was provided by the Queensland Government through an Advance Queensland Early Career fellowship. The authors are also thankful to Dr. Alistair Hobday for the additional funding provided under the CSIRO Coasts and Ocean Research (COR) program.
Publisher Copyright:
© 2023
