A Study Of Remote Sensing For Monitoring Marine Pollution Waters

The concentrations of chlorophyll in surface waters is one of the important parameters used for monitoring coastal water quality. Ocean color remote sensing provides a convenient method of detecting these concentration from upwelling radiance. In the open ocean, it is not difficult to derive empirical algorithms of chlorophyll. In turbid coastal \vaters, however, this is much more difficult due to the presence of high concentrations of suspended sediments and dissolved organic material, which overwhelm the spectral signal of chlorophyll. Neural networks have been proved successful in modeling a variety of geophysical transfer functions. Here, a neural network is employed to model the transfer function between the chlorophyll and the satellite-received radiance in the Dalian Bay. It was found that a neural network with two hidden nodes, using the two visible Landsat Thematic Mapper bands as inputs, was able to model the transfer function to a much higher accuracy than multiple regression analysis.It is the purpose of this article to demonstrate a new method of algorithm development for the estimation of surface chlorophyll in estuarine waters such as Dalian Bay. A neural network is used to model the transfer function between the concentrations of chlorophyll in Dalian Bay and the radiance received at the Thematic Mapper sensor. This study used the Landsat Thematic Mapper, but the method is transferable to any ocean color-sensing satellite sensor, such as the recently launched Sea-viewing Wide Field-of- view Sensor (SeaWiFS).