Detection of Oil Spills in the Northern South China Sea Using Landsat-8 OLI

Abstract

Petroleum extraction, transportation, and consumption in the marine environment contribute to a large portion of anthropogenic oil spills into the ocean. While previous research focuses more on large oil spill accidents from oil tankers or offshore oil platforms, there are few systematic records on occasional regional oil spills. In this study, optical imagery from Landsat-8 OLI was used to detect oil slicks on the ocean surface through spatial analysis and spectral diagnosis in the northern South China Sea (NSCS). The source of the slicks was identified through datasets from traffic density and platform locations. A total of 632 oil slicks were detected in the NSCS from 2015 to 2019, where 57 were from platforms sources, and 490 were from ships. The average area of the detected slicks was 4.8 km2, and half of the slicks had areas <1.7 km2. Major oil spill hot spots included coastal Guangdong (ship origins), southeast and northeast Dongsha Island (ship origins), middle of south Beibu Gulf (ship and platform origins), and southeast Pearl River Estuary (platform origins). Through this study, we demonstrate the capability of medium-resolution optical imagery in monitoring regional oil spills. Such results and methods may help in near real-time oil spill monitoring and further environmental assessments.

Detection of Massive Oil Spills in Sun Glint Optical Imagery through Super-Pixel Segmentation

“…When evaluating the performance of the approach, both the positive contrast and negative contrast oil objects were regarded as oil targets, while other targets were regarded as background targets. To objectively evaluate the performance of the approach, the oil slicks in the images were visually interpreted and manually delineated in ArcMap software (version 10.8, Environment System Research Institute, Redlands, CA, USA) [33]. These interpreted oil slicks were used to assess the performance using the approach proposed in this study.…”

“…While many semi-/automatic oil spill extraction algorithms have been developed based on SAR [27][28][29][30][31][32], there are few semi-/automatic oil spill detection algorithms working for optical imagery. Currently, oil spill extent detection in optical remote sensing images largely relies on visual interpretation and manual delineation [33][34][35], which require extensive experience and expertise; and the derived oil spill map is also subject to interpretation. Other than visual interpretation, methods including pixel-based indices and deep learning have been developed to identify and classify oil slicks based on optical imagery [36][37][38][39][40][41][42][43][44].…”

Farmland Segmentation in Landsat 8 Satellite Images Using Deep Learning and Conditional Generative Adversarial Networks

“…Nearly 800 million people in the world are in shortage of food supplies, and in a couple of decades, the food demand is expected to increase by 60% [1]. Remote sensing has helped in monitoring different land cover changes, including agricultural areas [2][3][4].…”

“…We compare the effects of different band combinations on segmentation results, such as RGB, the normalised vegetation index (NDVI), and the combination of the NDVI and other visible bands. 4.…”