J. Vasilescu, L. Marmureanu, E. Carstea, Analysis of seawater pollution using neural networks and channels relationship algorithms, Romanian Journal of Physics, 56/3-4 (2011) 530-539.

Title: Analysis of seawater pollution using neural networks and channels relationship algorithms

Abstract: The aim of this paper is to establish the most accurate and fastest method of Lidar signal analysis used for fluorescent water compounds identification. This study analyzes data acquired in 2007 late summer campaign on Romanian part of the Black Sea. Artificial Neural Network and channels relationship methods were evaluated in order to identify the best choice for fluorescence compounds detection and characterization. The Artificial Neural Network processing method proved to be useful for online recognition of oil spills, the sensitivity is dependent on training data set and training rule. It was found that is suitable to use channels relationship in order to reveal the distribution of fluorescence water components on a path and is suitable to use Artificial Neural Network to identify the type of fluorescence water components.

Key words: fluorescence Lidar signal, Artificial Neural Network, Channels Relationship