OIL SPILL DETECTION USING RBF NEURAL NETWORKS AND SAR DATA

Illegal oil spill discharges cause serious damage to marine ecosystems. Synthetic Aperture Radar (SAR) images are extensively used for the detection of oil spills in the marine environment, as they are not affected by local weather conditions and cloudiness. However, radar backscatter values for oil spills are very similar to backscatter values for very calm sea areas and other ocean phenomena because dampen capillary and short gravity waves is caused by the presence of an oil spill. Several studies aiming at oil spill detection have been conducted. Most of these studies rely on the detection of dark areas, which are objects with a high Bayesian probability of being oil-spills. The drawback of these methods is a complex process, because there are many non linearities involved. The use of Neural Networks (NNs) in remote sensing has increased significantly as NN can simultaneously handle non-linear data of a multidimensional input space. Furthermore, NN do not require an explicitly well-defined relationship between input and output as they determine their own relationships based on input/output values. In a previous study, the potential of the Multilayer Perceptron (MLP) neural network and different training algorithms for oil spill classification were investigated. In this paper another approach of NN use in oil spill detection is presented. The Radial Basis Function (RBF) neural network is investigated in order to be compared with the Multilayer Perceptron. For both networks, several topologies are examined and their performance is evaluated. MLPs appear to be superior than RBFs in detecting oil spills on SAR images. * Corresponding author.

[1]  W. Alpers,et al.  The Damping Of Ocean Surface Waves By Monomolecular Sea Slicks Measured By Airborne Multi-frequency Radars During The Saxon-fpn experiment , 1991, [Proceedings] IGARSS'91 Remote Sensing: Global Monitoring for Earth Management.

[2]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[3]  Victoriano Moreno,et al.  An oil spill monitoring system based on SAR images , 1996 .

[4]  Tom Ziemke,et al.  Radar image segmentation using recurrent artificial neural networks , 1996, Pattern Recognit. Lett..

[5]  Petros Pavlakis,et al.  On the optimization of spaceborne SAR capacity in oil spill detection and the related hydrodynamic phenomena , 1996 .

[6]  Rune Solberg,et al.  Automatic detection of oil spills in ERS SAR images , 1999, IEEE Trans. Geosci. Remote. Sens..

[7]  Soo Chin Liew,et al.  Ocean oil pollution mapping with ERS synthetic aperture radar imagery , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[8]  Andrea Garzelli,et al.  Oil-spills detection in SAR images by fractal dimension estimation , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[9]  M. Gade,et al.  On the detectability of marine oil pollution in European marginal waters by means of ERS SAR imagery , 2000, IGARSS 2000. IEEE 2000 International Geoscience and Remote Sensing Symposium. Taking the Pulse of the Planet: The Role of Remote Sensing in Managing the Environment. Proceedings (Cat. No.00CH37120).

[10]  Fabio Del Frate,et al.  Neural networks for oil spill detection using ERS-SAR data , 2000, IEEE Trans. Geosci. Remote. Sens..

[11]  Dario Tarchi,et al.  On the monitoring of illicit vessel discharges using spaceborne sar remote sensing - a reconnaissance study in the Mediterranean sea , 2001, Ann. des Télécommunications.

[12]  Kostas Topouzelis,et al.  Oil spill detection: SAR multiscale segmentation and object features evaluation , 2003, SPIE Remote Sensing.

[13]  Stan Matwin,et al.  Machine Learning for the Detection of Oil Spills in Satellite Radar Images , 1998, Machine Learning.