Confidence Levels in the Detection of Oil Spills from Satellite Imagery: From Research to Operational Use

Detected oil spills are usually classified according to confidence levels. Such levels are supposed to describe the probability that an observed dark feature in the satellite image is related to the actual presence of an oil spill. The Synthetic Aperture Radar (SAR) derived oil spill detection probability estimation has been explored as an intrinsic aspect of oil spill classification, which fundamentally computes the likelihood that the detected dark area and its extracted features are related to oil spill. However, the SAR based probability estimation should be integrated with additional criteria in order to become a more effective tool for the End User. As example, the key information for the final users is not the confidence level of the detection “per se” but the alert (i.e. the impact) that such a detection could generate. This topic was deeply discussed in the framework of the R&D European Group of Experts on remote sensing Monitoring of marine Pollution (EGEMP) and a paper was published in 2010. Following this paper, the newly established EMSA CleanSeaNet service (2nd generation) provides the alert level connected to the detection of an potential oil spill in a satellite image in a different way.

FERRARO DI SILVI E CASTIGLIONE Guido;  TRIESCHMANN Olaf;  PERKOVIC Marko;  TARCHI Dario; 

2013-08-12

S P I E - INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING

JRC70586

0277-786X,   

http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1402400,    https://publications.jrc.ec.europa.eu/repository/handle/JRC70586,