Neural network approach to case 2 water analysis from Ocean Colour and Temperature Scanner

For the purpose of remote sensing, ocean water conditions are divided into two categories, case 1 and case 2. Case 1 waters are fully dominated by phytoplankton and their by-products. Case 2 waters additionally contain suspended sediments, dissolved organic matter, and terrigenous particles. Coastal zones are mostly classified to the case 2 category. The analysis of case 2 waters creates a difficulty due to complexity of substance mixtures, unstable atmospheric residue and noise. Water-leaving radiances used for the extraction of upper ocean constituents represent no more than 10% of the total radiance captured by satellite optical sensors. The readings are dominated by the atmosphere. An atmospheric correction may be performed to remove the contribution of the atmosphere in satellite measurements. In case 2 waters, there is a significant water leaving radiance in both the visible and near-infrared. Regular atmospheric corrections fail in case 2 waters because the extrapolation of aerosol path radiance into visible bands results in distorted or negative reflectances at visible wavelengths. Current operational ocean colour algorithms are not suited to analyse case 2 waters. Some algorithms additionally apply a turbid water test on 555 nm channel normalized water leaving radiances after the full atmospheric correction. Then, they just label isolated case 2 waters because chlorophyll estimates in case 2 zones are unreliable. The current research addresses the need for a consistent and accurate method of case 1 and case 2 water separation and a detailed analysis of case 2 water types. The task is to locate case 2 waters in Ocean Colour and Temperature Scanner (OCTS) imagery and differentiate coastal water types. There have been attempts to extract chlorophyll and gelbstoff levels based on radiative transfer models. The present study contributes with a novel artificial intelligence approach to the precise case 2 water examination.