US 12,380,670 B2
Identifying and remediating oil spills
Khaled M. Asfahani, Dhahran (SA); Ali M. Qasem, Dhahran (SA); Alaa A. Elyas, Dhahran (SA); Ibrahim Hoteit, Thuwal (SA); and Sabique Langodan, Dhahran (SA)
Assigned to Saudi Arabian Oil Company, Dhahran (SA); and King Abdullah University of Science and Technology, Thuwal (SA)
Filed by Saudi Arabian Oil Company, Dhahran (SA); and King Abdullah University of Science and Technology, Thuwal (SA)
Filed on Aug. 16, 2022, as Appl. No. 17/820,191.
Prior Publication US 2024/0062512 A1, Feb. 22, 2024
Int. Cl. G06V 10/62 (2022.01); G01S 13/90 (2006.01); G06T 7/62 (2017.01); G06T 7/73 (2017.01); G06V 10/774 (2022.01); G06V 20/10 (2022.01); G06V 20/13 (2022.01)
CPC G06V 10/62 (2022.01) [G01S 13/9021 (2019.05); G06T 7/62 (2017.01); G06T 7/73 (2017.01); G06V 10/774 (2022.01); G06V 20/13 (2022.01); G06V 20/194 (2022.01); G06T 2207/10036 (2013.01); G06T 2207/30181 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for identifying an oil spill in a body of water, the method comprising:
(a) obtaining an image of the body of water from a satellite for a first time period and a second time period, wherein obtaining the image of the body of water from the satellite comprises obtaining a synthetic aperture radar image and a multispectral image;
(b) determining one or more features to extract from the image, the features representing a physical feature of a surface of the body of water for each of the first time period and the second time period;
(c) extracting the one or more features from the image to form a first feature vector for the first time period and a second feature vector for the second time period;
(d) processing the first feature vector and the second feature vector using a machine learning model, the machine learning model being trained with labeled image data representing instances of oil on the surface of the body of water, the labeled image data associating oil appearances code with portions of the surface of the water body based on the respective instances of the oil spill in the first and second vectors;
(e) determining, based on the processing, areas of the body of water associated with each oil appearance code;
(f) determining, based on the areas of the body of water associated with each oil appearance code, locations and volumes of oil in the body of water, wherein the locations and volumes of oil are determined based on comparing a first output of the machine learning model based on features from the synthetic aperture radar image to a second output of the machine learning model based on features from the multispectral image; and
(h) storing, in a data store based on the comparing, data representing the locations and volumes of oil in the body of water in association with the image.