Premium
Monitoring aerosol optical properties over the Mediterranean from SeaWiFS images using a neural network inversion
Author(s) -
Jamet C.,
Moulin C.,
Thiria S.
Publication year - 2004
Publication title -
geophysical research letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.007
H-Index - 273
eISSN - 1944-8007
pISSN - 0094-8276
DOI - 10.1029/2004gl019951
Subject(s) - seawifs , aeronet , angstrom exponent , aerosol , remote sensing , environmental science , radiative transfer , mediterranean sea , inversion (geology) , artificial neural network , mediterranean climate , meteorology , computer science , geology , geography , optics , physics , artificial intelligence , chemistry , paleontology , organic chemistry , phytoplankton , archaeology , structural basin , nutrient
The SeaWiFS archive provides a unique opportunity to study aerosol optical properties over oceans since October 1997. Standard SeaWiFS aerosol products are however not suitable because optical thicknesses are limited to 0.35 and Angström exponents to 1.5. We developed an inversion based on neural networks to retrieve both optical thickness and Angström exponent from SeaWiFS red and near infrared channels. Neural networks are capable of approximating non‐linear inverse functions and of processing efficiently large amounts of data. Neural networks were trained with radiative transfer computations for wide ranges of optical thickness and Angström exponent. All SeaWiFS images of the Mediterranean for year 2000 were processed and monthly mean maps of aerosol optical thickness and Angström exponent were derived. A comparison with ground‐based measurements at three AERONET stations in the Mediterranean shows the good accuracy of the method, as well as the improvement compared to operational SeaWiFS aerosol products.