Building a Learning Database for the Neural Network Retrieval of Sea Surface Salinity from SMOS Brightness Temperatures

This article deals with an important aspect of the neural network retrieval of sea surface salinity (SSS) from SMOS brightness temperatures (TBs). The neural network retrieval method is an empirical approach that offers the possibility of being independent from any theoretical emissivity model, during the in-flight phase. A Previous study [1] has proven that this approach is applicable to all pixels on ocean, by designing a set of neural networks with different inputs. The present study focuses on the choice of the learning database and demonstrates that a judicious distribution of the geophysical parameters allows to markedly reduce the systematic regional biases of the retrieved SSS, which are due to the high noise on the TBs. An equalization of the distribution of the geophysical parameters, followed by a new technique for boosting the learning process, makes the regional biases almost disappear for latitudes between 40{\deg}S and 40{\deg}N, while the global standard deviation remains between 0.6 psu (at the center of the of the swath) and 1 psu (at the edges).

[1]  Jacqueline Boutin,et al.  Overview of the SMOS Sea Surface Salinity Prototype Processor , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Serni Ribó i Vedrilla Calibration Validation and Polarimetry in 2D Aperture Synthesis. Application to MIRAS , 2005 .

[3]  Yann Kerr,et al.  SMOS: The Mission and the System , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[5]  Jacqueline Boutin,et al.  Influence of sea surface emissivity model parameters at L-band for the estimation of salinity , 2002 .

[6]  C. Swift,et al.  An improved model for the dielectric constant of sea water at microwave frequencies , 1977, IEEE Journal of Oceanic Engineering.

[7]  Jianqing Fan,et al.  Local polynomial modelling and its applications , 1994 .

[8]  Sylvie Thiria,et al.  Sea Surface Salinity Retrieval for the SMOS Mission Using Neural Networks , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Stephen C. Riser,et al.  Salinity in Argo: A Modern View of a Changing Ocean , 2008 .

[10]  Min Zhang,et al.  Theoretical study of the small slope approximation for ocean polarimetric thermal emission , 1999, IEEE Trans. Geosci. Remote. Sens..

[11]  Philippe Waldteufel,et al.  About off-axis radiometric polarimetric measurements , 2002, IEEE Trans. Geosci. Remote. Sens..

[12]  Adriano Camps,et al.  The determination of surface salinity with the European SMOS space mission , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Adriano Camps,et al.  Radiometric sensitivity computation in aperture synthesis interferometric radiometry , 1998, IEEE Trans. Geosci. Remote. Sens..

[14]  N. Skou Faraday rotation and L band oceanographic measurements , 2003 .