Evolution of the C2RCC Neural Network for Sentinel 2 and 3 for the Retrieval of Ocean Colour Products in Normal and Extreme Optically Complex Waters
Abstract
Retrieval of water constituents, or its optical properties, requires inversion of the water leaving reflectance spectrum, measured at top of atmosphere by ocean colour satellites. The Case 2 Regional processor, originally developed by Doerffer and Schiller [6], uses a large database of radiative transfer simulations inverted by neural networks as basic technology. Through the CoastColour project major improvements were introduced. It has been amended by a set of additional neural networks performing specific tasks and special neural networks have been trained to cover extreme ranges of scattering and absorption. The processor has been renamed into C2RCC (Case 2 Regional CoastColour) and is applicable to all past and current ocean colour sensors as well as Sentinel 2. It has been validated in various studies and is available through ESA's Sentinel toolbox SNAP. It is also used in the Sentinel 3 OLCI ground segment processor of ESA for the generation of the Case 2 water products, as well as in the processor for the upcoming MERIS 4th reprocessing.
- Publication:
-
Living Planet Symposium
- Pub Date:
- August 2016
- Bibcode:
- 2016ESASP.740E..54B