A novel deep learning method for marine oil spill detection from satellite synthetic aperture radar imagery. (June 2022)

• Record Type: Journal Article
• Authors: Huang, Xudong; Zhang, Biao; Perrie, William; Lu, Yingcheng; Wang, Chen
• Is Part Of: Marine pollution bulletin. Volume 179(2022)
• Publication Date: 2022-06
• Subjects: Oil spill -- Synthetic aperture radar -- Convolutional neural network -- Faster R-CNN; Marine pollution -- Periodicals; Marine Biology -- Periodicals; Water Pollution -- Periodicals; Mer -- Pollution -- Périodiques; Publications périodiques; Pollution des mers; Lutte antipollution; Electronic journals; 363.7394
• DOI: 10.1016/j.marpolbul.2022.113666
• Languages: English
• ISSNs: 0025-326X

Abstract

Abstract: Oil spill discharges from operational maritime activities like ships, oil rigs and other structures, leaking pipelines, as well as natural hydrocarbon seepage pose serious threats to marine ecosystems and fisheries. Satellite synthetic aperture radar (SAR) is a unique microwave instrument for marine oil spill monitoring, as it is not dependent on weather or sunlight conditions. Existing SAR oil spill detection approaches are limited by algorithm complexity, imbalanced data sets, uncertainties in selecting optimal features, and relatively slow detection speed. To overcome these restrictions, a fast and effective SAR oil spill detection method is presented, based a novel deep learning model, named the Faster Region-based Convolutional Neural Network (Faster R-CNN). This approach is capable of achieving fast end-to-end oil spill detection with reasonable accuracy. A large data set consisting of 15, 774 labeled oil spill samples derived from 1786C-band Sentinel-1 and RADARSAT-2 vertical polarization SAR images is used to train, validate and test the Faster R-CNN model. Our experimental results show that the proposed method exhibits good performance for detection of oil spills with wide swath SAR imagery. The Precision and Recall metrics are 89.23% and 89.14%, respectively. The average Precision is 92.56%. The effects of environmental conditions and sensor parameters on oil spill detection are analyzed. The expected detection results are obtained when wind speeds and incidence angles are between 3 m/s and 10 m/s, and 21 ° and 45 °, respectively. Furthermore, the computer runtime for oil spill detection is less than 0.05 s for each full SAR image, using a workstation with NVIDIA GeForce RTX 3090 GPU. This suggests that the present approach has potential for applications that require fast oil spill detection from spaceborne SAR images. Highlights: A deep learning-based method for C-band SAR oil spill detection is presented. Precision and recall of oil spill detection are 89.23% and 89.14%, respectively. The proposed method can achieve fast and effective end-to-end oil spill detection. Oil spill detections are validated using collocated optical satellite observations.