Affiliation:
1. State Oil Company of the Azerbaijan Republic
2. Siberian State University of Geosystems and Technologies
Abstract
This article substantiates the relevance of the study, the characteristics of the joint use of optical multispectral survey, radar interferometry and partial polarimetry, identifies the scope of interpretation of the radar-optical composite built by optical and radar data, and provides a mathematical model for image processing of the water surface area. The quantitative assessment of these automated or semi-automated methods is not inferior to the accuracy of traditional methods for assessing the state of the offshore marine environment. It was shown that the most efficient approach is the direct use of the ResNet-10 deep learning algorithm on scenes when combined with complex (amplitude and phase) centimeter-range radar images and multispectral optical images of Sentinel platforms. This approach made it possible to detect 86.72% of all spots in the scenes and had an average accuracy of 75.35%. The approach has also showed a significantly reduced ability to detect patches when the local wind speed was below 2 m/s or above 12 m/s.
Publisher
Siberian State University of Geosystems and Technologies
Subject
Industrial and Manufacturing Engineering
Reference9 articles.
1. Fingas, M., & Brown, C. Review of oil spill remote sensing. Marine Pollution Bulletin, 83, pp.9-23, 2014 doi:10.1016/j. marpolbul.2014.03.059 https://downloads.spj.sciencemag.org
2. Ivanov, A. Y., Dostovalov, M. Y., & Sineva, A. A. Characterization of oil pollution around the oil rocks production site in the Caspian Sea using spaceborne polarimetric SAR imagery. Izvestiya, Atmospheric and Oceanic Physics, 2012, 48(9), 1014-1026.
3. Bayramov, E. R., Buchroithner, M. F., & Bayramov, R. V. Multi-temporal assessment of ground cover restoration and soil erosion risks along petroleum and gas pipelines in Azerbaijan using GIS and remote sensing. Environmental earth sciences, 2016 ,75(3), 256.
4. Fingas, M.; Brown, C. Review of oil spill remote sensing. Mar. Pollut. Bull. 2014, 83, 9-23. [CrossRef]
5. Lu, Y.C.; Hu, C.M.; Sun, S.J.; Zhang, M.W.; Zhou, Y.; Shi, J.; Wen, Y.S. Overview of optical remote sensing of marine oil spills and hydrocarbon seepage. J. Remote Sens. 2016, 20, 1259-1269.