Evaluation of OLCI Neural Network Radiometric Water Products

Radiometric water products from the neural network (NNv2) in the alternative atmospheric correction (AAC) processing chain of Ocean and Land Colour Instrument (OLCI) data were assessed over different marine regions. These products, not included among the operational ones, were custom-produced from Copernicus Sentinel-3 OLCI Baseline Collection 3. The assessment benefitted of in situ reference data from the Ocean Color component of the Aerosol Robotic Network (AERONET-OC) from sites representative of different water types. These included clear waters in the Western Mediterranean Sea, optically complex waters characterized by varying concentrations of total suspended matter and chromophoric dissolved organic matter (CDOM) in the northern Adriatic Sea, and optically complex waters characterized by very high concentrations of CDOM in the Baltic Sea. The comparison of the water-leaving radiances $L_{\text {WN}}(\lambda)$ derived from OLCI data on board Sentinel-3A and Sentinel-3B with those from AERONET-OC confirmed consistency between the products from the two satellite sensors. However, the accuracy of satellite data products exhibited dependence on the water type. A general underestimate of ${L}_{\text {WN}}(\lambda)$ was observed for clear waters. Conversely, overestimates were observed for data products from optically complex waters with the worst results obtained for CDOM-dominated waters. These findings suggest caution in exploiting NNv2 radiometric products, especially for highly absorbing and clear waters.