Back to first pageBack to first page Centre for Artificial Intelligence of UNL
Browse our site
You are here:

Publication details

Go back
Publication details
Main information
Seawater-type Based Neural Networks for Ocean Color Data Inversion
October 2013
ACRS-2013
The retrieval of Ocean Color (OC) data products is here investigated by using Multi Layer Perceptron (MLP) neural nets. Synthetic data have been generated for this scope with a forward OC model. These samples have then been used to train and assess the MLP performance considering different seawater types (WTs) with optical properties driven by: chlorophyll (Chl-a), colored dissolved organic matter (CDOM), and non-pigmented particulate matter (NPPM), as well as a mixture of Chl-a, CDOM and NPPM (denoted MIXI). Acknowledging that MLP classification results represent WT posterior probabilities, an integrated machine learning approach is set up by joining MLPs for data regression and classification in a composite scheme. Results indicate that this approach is valuable to support the use of regional ocean color inversion schemes by decomposing the overall challenge in sub-components, optimally addressing each of them, and combining the individual solutions in a principled framework.
In proceedings
Ari Saptawijaya, Davide D'Alimonte, Tamito Kajiyama
Proceedings 34th Asian Conference on Remote Sensing (ACRS 2013)
-
Asian Association on Remote Sensing
http://www.acrs2013.com/proceedings.html
-
235-242
978-602-9439-33-5
-
-
http://www.acrs2013.com/sites/media/uploads/2013/11/SC3bag2.pdf
Export formats
Ari Saptawijaya and Davide D'Alimonte and Tamito Kajiyama, Seawater-type Based Neural Networks for Ocean Color Data Inversion, , Proceedings 34th Asian Conference on Remote Sensing (ACRS 2013), Asian Association on Remote Sensing, http://www.acrs2013.com/proceedings.html, ISBN 978-602-9439-33-5, Pag. 235-242, (http://www.acrs2013.com/sites/media/uploads/2013/11/SC3bag2.pdf), October 2013.
<a href="/people/members/view.php?code=3296a2fcb759ac3f30bc313a41f955bc" class="author">Ari Saptawijaya</a>, Davide D'Alimonte and Tamito Kajiyama, <b>Seawater-type Based Neural Networks for Ocean Color Data Inversion</b>, <u>Proceedings 34th Asian Conference on Remote Sensing (ACRS 2013)</u>, Asian Association on Remote Sensing, http://www.acrs2013.com/proceedings.html, ISBN 978-602-9439-33-5, Pag. 235-242, (<a href="http://www.acrs2013.com/sites/media/uploads/2013/11/SC3bag2.pdf" target="_blank">url</a>), October 2013.
@inproceedings {ACRS-2013, author = {Ari Saptawijaya and Davide D'Alimonte and Tamito Kajiyama}, title = {Seawater-type Based Neural Networks for Ocean Color Data Inversion}, booktitle = {Proceedings 34th Asian Conference on Remote Sensing (ACRS 2013)}, publisher = {Asian Association on Remote Sensing}, address = {http://www.acrs2013.com/proceedings.html}, pages = {235-242}, isbn = {978-602-9439-33-5}, url = {http://www.acrs2013.com/sites/media/uploads/2013/11/SC3bag2.pdf}, abstract = {The retrieval of Ocean Color (OC) data products is here investigated by using Multi Layer Perceptron (MLP) neural nets. Synthetic data have been generated for this scope with a forward OC model. These samples have then been used to train and assess the MLP performance considering different seawater types (WTs) with optical properties driven by: chlorophyll (Chl-a), colored dissolved organic matter (CDOM), and non-pigmented particulate matter (NPPM), as well as a mixture of Chl-a, CDOM and NPPM (denoted MIXI). Acknowledging that MLP classification results represent WT posterior probabilities, an integrated machine learning approach is set up by joining MLPs for data regression and classification in a composite scheme. Results indicate that this approach is valuable to support the use of regional ocean color inversion schemes by decomposing the overall challenge in sub-components, optimally addressing each of them, and combining the individual solutions in a principled framework.}, keywords = {neural network, regional algorithms, ocean color, remote sensing}, month = {October}, year = {2013}, }
Publication's urls
/publications/view.php?code=b458443bd75877d56331e154b01d0c6f
/publications/view.php?code=ACRS-2013
Go back
Centre for Artificial Intelligence of UNL
Departamento de Informática, FCT/UNL
Quinta da Torre 2829-516 CAPARICA - Portugal
Tel. (+351) 21 294 8536 FAX (+351) 21 294 8541

Fundacao_FCT