Detection of marine oil-like features in Sentinel-1 SAR images by supplementary use of deep learning and empirical methods: Performance assessment for the Great Barrier Reef marine park

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.

Retrieval of pigment concentrations and size structure of algal populations from their absorption spectra using multilayered perceptrons

Spectral absorption coefficients of phytoplankton can now be derived, under some assumptions, from hyperspectral ocean color measurements and thus become accessible from space. In this study, multilayer perceptrons have been developed to retrieve information on the pigment composition and size structure of phytoplankton from these absorption spectra. The retrieved variables are the main pigment groups (chlorophylls a, b, c, and photosynthetic and nonphotosynthetic carotenoids) and the relative contributions of three algal size classes (pico-, nano-, and microphytoplankton) to total chlorophyll a. The networks have been trained, tested, and validated using more than 3,700 simultaneous absorption and pigment measurements collected in the world ocean. Among pigment groups, chlorophyll a is the most accurately retrieved (average relative errors of 17% and 16% for the test and validation data subsets, respectively), while the poorest performances are found for chlorophyll b (average relative errors of 51% and 40%). Relative contributions of algal size classes to total chlorophyll a are retrieved with average relative errors of 19% to 33% for the test subset and of 18% to 47% for the validation subset. The performances obtained for the validation data, showing no strong degradation with respect to test data, suggest that these neural networks might be operated with similar performances for a large variety of marine areas.