@article{PAR00013605,
  title = {{S}oil moisture retrieval using neural networks : application to {SMOS}},
  author = {{R}odriguez-{F}ernandez, {N}. {J}. and {A}ires, {F}. and {R}ichaume, {P}. and {K}err, {Y}ann and {P}rigent, {C}. and {K}olassa, {J}. and {C}abot, {F}. and {J}imenez, {C}. and {M}ahmoodi, {A}. and {D}rusch, {M}.},
  editor = {},
  language = {{ENG}},
  abstract = {{A} methodology to retrieve soil moisture ({SM}) from {S}oil {M}oisture and {O}cean {S}alinity ({SMOS}) data is presented. {T}he method uses a neural network ({NN}) to find the statistical relationship linking the input data to a reference {SM} data set. {T}he input data are composed of passive microwaves ({L}-band {SMOS} brightness temperatures, {T}-b's) complemented with active microwaves ({C}-band {A}dvanced {S}catterometer ({ASCAT}) backscattering coefficients), and {M}oderate {R}esolution {I}maging {S}pectroradiometer ({MODIS}) {N}ormalized {D}ifference {V}egetation {I}ndex ({NDVI}). {T}he reference {SM} data used to train the {NN} are the {E}uropean {C}entre {F}or {M}edium-{R}ange {W}eather {F}orecasts model predictions. {T}he 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. {T}he 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} {T}b's (or {ASCAT} backscattering coefficients) and the associated {SM} values. {T}he {NN}-inverted {SM} is able to capture the temporal and spatial variability of the {SM} reference data set. {T}he temporal variability is better captured when either adding active microwaves or using a local normalization of {SMOS} {T}-b's. {T}he {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. {T}he {NN} used in this paper allows to retrieve {SM} globally on a daily basis. {T}hese results open interesting perspectives such as a near-real-time processor and data assimilation in weather prediction models.},
  keywords = {{A}rtificial neural networks ({NN}s) ; {A}dvanced {S}catterometer ({ASCAT}) ; {E}uropean {C}entre for {M}edium-{R}ange {W}eather {F}orecasts ({ECMWF}) ; {M}oderate ; {R}esolution {I}maging {S}pectroradiometer ({MODIS}) ; soil moisture ({SM}) ; {S}oil ; {M}oisture and {O}cean {S}alinity ({SMOS})},
  booktitle = {},
  journal = {{I}eee {T}ransactions on {G}eoscience and {R}emote {S}ensing},
  volume = {53},
  numero = {11},
  pages = {5991--6007},
  ISSN = {0196-2892},
  year = {2015},
  DOI = {10.1109/tgrs.2015.2430845},
  URL = {https://www.documentation.ird.fr/hor/{PAR}00013605},
}