FN Archimer Export Format
PT J
TI Exploring Machine Learning to Correct Satellite-Derived Sea Surface Temperatures
BT 
AF PICART, Stephane Saux
   TANDEO, Pierre
   AUTRET, Emmanuelle
   GAUSSET, Blandine
AS 1:1;2:2;3:3;4:1;
FF 1:;2:;3:PDG-ODE-LOPS-SIAM;4:;
C1 Meteo France Ctr Meteorol Spatiale, Ave Lorraine,BP 50747, F-22307 Lannion, France.
   IMT Atlantique, Lab STICC, UBL, F-29238 Brest, France.
   IFREMER, Lab Oceanog Phys & Spatiale, ZI Pointe Diable CS 10070, F-29280 Plouzane, France.
C2 CNRM (METEO FRANCE), FRANCE
   IMT ATLANTIQUE, FRANCE
   IFREMER, FRANCE
SI BREST
SE PDG-ODE-LOPS-SIAM
UM LOPS
IN WOS Ifremer jusqu'en 2018
   DOAJ
   copubli-france
IF 4.118
TC 8
UR https://archimer.ifremer.fr/doc/00426/53797/54721.pdf
LA English
DT Article
DE ;machine learning;systematic error;sea surface temperature;random forest
AB Machine learning techniques are attractive tools to establish statistical models with a high degree of non linearity. They require a large amount of data to be trained and are therefore particularly suited to analysing remote sensing data. This work is an attempt at using advanced statistical methods of machine learning to predict the bias between Sea Surface Temperature (SST) derived from infrared remote sensing and ground “truth” from drifting buoy measurements. A large dataset of collocation between satellite SST and in situ SST is explored. Four regression models are used: Simple multi-linear regression, Least Square Shrinkage and Selection Operator (LASSO), Generalised Additive Model (GAM) and random forest. In the case of geostationary satellites for which a large number of collocations is available, results show that the random forest model is the best model to predict the systematic errors and it is computationally fast, making it a good candidate for operational processing. It is able to explain nearly 31% of the total variance of the bias (in comparison to about 24% for the multi-linear regression model). 
PY 2018
PD FEB
SO Remote Sensing
SN 2072-4292
PU Mdpi
VL 10
IS 2
UT 000427542100070
DI 10.3390/rs10020224
ID 53797
ER

EF