@inproceedings{0f58808e773444089c737261d7efd48e,
title = "Oil Spill Detection and Mapping Using Sentinel-1 and Sentinel-2 in the Arabian Gulf Coastal Waters",
abstract = "Oil spills can cause long-term damage to the marine ecosystem and force desalination plants to shut down. Thus, this study aims to detect the oil spill in Arabian Gulf which produces a quarter of the world's oil. Sentinel-1 SAR and Sentinel-2 spectral imageries are utilized to detect oil spill. Sentinel-1 SAR is used to perform semantic segmentation with deep convolutional neural networks (DCNNs) using a U-Net structure and Sentinel-2 band ratio for mapping oil spill. Based on the segmentation results, the intersection-over-union (IoU) shows low values of <0.1 for the oil spill incidents along the Gulf coasts, but higher values for the offshore oil spill incidents (>0.65). Coastal land has adversely affected the segmentation process. As for the band ratio approach, it succeeded in distinguishing the oil spill, however prior knowledge or an expert interpretation is needed to verify the presence of the spill.",
keywords = "DCNN, Oil spill, SAR",
author = "Gafoor, {Fahim Abdul} and {Al Shehhi}, {Maryam R.}",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022 ; Conference date: 17-07-2022 Through 22-07-2022",
year = "2022",
doi = "10.1109/IGARSS46834.2022.9883723",
language = "British English",
series = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "6745--6748",
booktitle = "IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium",
address = "United States",
}
