Advances in satellite ocean color technologies and methodologies are expected to lead to the generation of coastal water bio-optical products with accuracies close to those targeted in oceanic regions. In view of contributing to such a progress, Multi Layer Perceptron (MLP) neural networks complying with standard MERIS pigment indices were developed relying on regional highly accurate in-situ data. This work illustrates and discusses the application to sample MERIS imagery of those neural networks trained to produce pigments indices in seas characterized by increased levels of bio-optical complexity: the Baltic, the northern Adriatic and the Western Black Seas.
KAJIYAMA Tamito;
D'ALIMONTE Davide;
ZIBORDI Giuseppe;
2012-12-04
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
JRC68314
1545-598X,
http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6236000,
https://publications.jrc.ec.europa.eu/repository/handle/JRC68314,
10.1109/LGRS.2012.2202370,
This document is only visible at the Commission level.
You are not authorized to publish or distribute it outside the European Commission.
This is a public document. You can share this publication.
Additional supporting files
| File name | Description | File type | |
|---|
