Neural Networks in Detection and Identification of Littoral Oil Pollution by Remote Sensing

In order to differentiate classes of oil-spills on water surface, a neural network (NN) approach is applied for spectral data analysis and identification of airborne laser fluorosensor in this paper. The target to be detected may be one of the following: seawater, lube, diesel, etc. The primary requirement for airborne sensors is to identify the substances targeted by the laser beam. Pearson Correlation Coefficient (PCC) method is one of the most current approaches. This paper outlines the NN model for the identification of the spilled oils, and makes a comparison with PCC in an effort to increase the level of confidence in the identification results. The results of ground tests using known targets show an increased confidence in the results when using the NN Model compared to that of PCC. It is believed that the NN model would play a significant role in the ocean oil-spill identification in the future.