Park, S.-H.; Jung, H.-S.; Lee, M.-J.; Lee, W.-J., and Choi, M.-J., 2019. Oil spill detection from PlanetScope satellite image: Application to oil spill accident near Ras Al Zour area, Kuwait in August 2017. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue No. 90, pp. 251-260. Coconut Creek (Florida), ISSN 0749-0208.
Oil spill accidents are major marine disasters that can destroy the ocean ecosystem. Satellite images are widely used to respond immediately to oil spill accidents. A miniaturized satellite equipped with an optical sensor has an advantage that the imaging period is very short because a large number of satellites can be operated. In this study, oil slick areas were detected by applying the artificial neural network (ANN) technique to the PlanetScope satellite optical image captured near Ras Al Zour, Kuwait on August 10, 2017. However, the image included sunglint effects owing to ocean waves and yellow dust areas, making it difficult to classify the oil slick area. In addition, the spilled oil had three different spectral information characteristics through interaction with the sea surface of the Persian Gulf. The image processing was divided into the pre-processing step and the oil slick classification step to detect the oil slick area and to mitigate these limitations. In the pre-processing step, a directional median filter was applied to reduce the sunglint effects caused by ocean waves, and the negative effects from the sea surface and dust were mitigated using the differences with the low-pass filtered image. In the oil slick detection step, three types of oil probability maps and one sea surface probability map were produced using the ANN technique. Subsequently, an oil slick classification map was produced by applying the maximum probability choosing method and dust area rejection. Through validation, the overall accuracy of the oil classification map was obtained to be 82.01 % and the kappa coefficient was 72.42 %. The proposed oil detection method can effectively detect different types of oil spill areas in optical images with sunglint and dust handicaps. Moreover, it has high potential to be used in the future because the revisit time of the satellite image used is shorter than that of other optical images.