Geodesic
A comparison of Multiple Non-linear regression and neural network techniques for sea surface salinity estimation in the tropical Atlantic ocean based on satellite data
H. Moussa1, 2 ; M. A. Benallal1, 2 ; C. Goyet1, 2 ; N. Lefevre3, 4 ; M. C. EL Jai1, 2 ; V. Guglielmi1, 2 ; F. Touratier1, 2
1IMAGESESPACE-DEV, Université de Perpignan Via Domitia, 52 Avenue Paul Alduy, 66860 Perpignan Cedex 9, France.
2ESPACE-DEV, UG UA UR UM IRD, Maison de la télédétection, 500 Rue Jean-Franois Breton, 34093 Montpellier Cedex 5, France.
3IRD LOCEAN, Université Pierre et Marie Curie, UMR 7159, Paris, France.
4Lab. Oceanografia Física Estuarina e Costeira , Universidade Federal de Pernambuco, Av. Arquitetura, Brasil.
ESAIM. Proceedings, Tome 49 (2015), pp. 65-77
Cet article a éte moissonné depuis la source EDP Sciences

Voir la notice de l'article

Using measurements of Sea Surface Salinity and Sea Surface Temperature in the Western Tropical Atlantic Ocean, from 2003 to 2007 and 2009, we compare two approaches for estimating Sea Surface Salinity : Multiple Non-linear Regression and Multi Layer Perceptron. In the first experiment, we use 18,300 in situ data points to establish the two models, and 503 points for testing their extrapolation. In the second experiment, we use 15,668 in situ measurements for establishing the models, and 3,232 data points to test their interpolation. The results show that the Multiple Non-linear Regression is an admissible solution whether it be interpolation or extrapolation. Yet, the Multi Layer Perceptron can be used only for interpolation.
DOI : 10.1051/proc/201549006

H. Moussa  1 , 2   ; M. A. Benallal  1 , 2   ; C. Goyet  1 , 2   ; N. Lefevre  3 , 4   ; M. C. EL Jai  1 , 2   ; V. Guglielmi  1 , 2   ; F. Touratier  1 , 2

1 IMAGESESPACE-DEV, Université de Perpignan Via Domitia, 52 Avenue Paul Alduy, 66860 Perpignan Cedex 9, France.
2 ESPACE-DEV, UG UA UR UM IRD, Maison de la télédétection, 500 Rue Jean-Franois Breton, 34093 Montpellier Cedex 5, France.
3 IRD LOCEAN, Université Pierre et Marie Curie, UMR 7159, Paris, France.
4 Lab. Oceanografia Física Estuarina e Costeira , Universidade Federal de Pernambuco, Av. Arquitetura, Brasil. 
@article{EP_2015_49_a7,
     author = {H. Moussa and M. A. Benallal and C. Goyet and N. Lefevre and M. C. EL Jai and V. Guglielmi and F. Touratier},
     title = {A comparison of {Multiple} {Non-linear} regression and neural network techniques for sea surface salinity estimation in the tropical {Atlantic} ocean based on satellite data},
     journal = {ESAIM. Proceedings},
     pages = {65--77},
     year = {2015},
     volume = {49},
     doi = {10.1051/proc/201549006},
     language = {en},
     url = {http://geodesic.mathdoc.fr/articles/10.1051/proc/201549006/}
}
TY  - JOUR
AU  - H. Moussa
AU  - M. A. Benallal
AU  - C. Goyet
AU  - N. Lefevre
AU  - M. C. EL Jai
AU  - V. Guglielmi
AU  - F. Touratier
TI  - A comparison of Multiple Non-linear regression and neural network techniques for sea surface salinity estimation in the tropical Atlantic ocean based on satellite data
JO  - ESAIM. Proceedings
PY  - 2015
SP  - 65
EP  - 77
VL  - 49
UR  - http://geodesic.mathdoc.fr/articles/10.1051/proc/201549006/
DO  - 10.1051/proc/201549006
LA  - en
ID  - EP_2015_49_a7
ER  - 
%0 Journal Article
%A H. Moussa
%A M. A. Benallal
%A C. Goyet
%A N. Lefevre
%A M. C. EL Jai
%A V. Guglielmi
%A F. Touratier
%T A comparison of Multiple Non-linear regression and neural network techniques for sea surface salinity estimation in the tropical Atlantic ocean based on satellite data
%J ESAIM. Proceedings
%D 2015
%P 65-77
%V 49
%U http://geodesic.mathdoc.fr/articles/10.1051/proc/201549006/
%R 10.1051/proc/201549006
%G en
%F EP_2015_49_a7
H. Moussa; M. A. Benallal; C. Goyet; N. Lefevre; M. C. EL Jai; V. Guglielmi; F. Touratier. A comparison of Multiple Non-linear regression and neural network techniques for sea surface salinity estimation in the tropical Atlantic ocean based on satellite data. ESAIM. Proceedings, Tome 49 (2015), pp. 65-77. doi: 10.1051/proc/201549006

Cité par Sources :