Rodriguez-Fernandez, Nemesio J.; Aires, Filipe; Richaume, Philippe; Kerr, Yann H.; Prigent, Catherine; Kolassa, Jana; Cabot, Francois; Jimenez, Carlos; Mahmoodi, Ali; Drusch, Matthias (2015). Soil Moisture Retrieval Using Neural Networks: Application to SMOS. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 53(11), 5991-6007.

Abstract
A methodology to retrieve soil moisture (SM) from Soil Moisture and Ocean Salinity (SMOS) data is presented. The method uses a neural network (NN) to find the statistical relationship linking the input data to a reference SM data set. The input data are composed of passive microwaves (L-band SMOS brightness temperatures, T-b's) complemented with active microwaves (C-band Advanced Scatterometer (ASCAT) backscattering coefficients), and Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI). The reference SM data used to train the NN are the European Centre For Medium-Range Weather Forecasts model predictions. The best configuration of SMOS data to retrieve SM using an NN is using T-b's measured with both H and V polarizations for incidence angles from 25 degrees to 60 degrees. The inversion of SM can be improved by similar to 10% by adding MODIS NDVI and ASCAT backscattering data and by an additional similar to 5% by using local information on the maximum and minimum records of SMOS Tb's (or ASCAT backscattering coefficients) and the associated SM values. The NN-inverted SM is able to capture the temporal and spatial variability of the SM reference data set. The temporal variability is better captured when either adding active microwaves or using a local normalization of SMOS T-b's. The NN SM products have been evaluated against in situ measurements, giving results of comparable or better (for some NN configurations) quality to other SM products. The NN used in this paper allows to retrieve SM globally on a daily basis. These results open interesting perspectives such as a near-real-time processor and data assimilation in weather prediction models.

DOI:
10.1109/TGRS.2015.2430845

ISSN:
0196-2892