Artificial neural networks for modeling the transfer function between marine reflectance and phytoplankton pigment concentration

A neural network methodology is developed to estimate the near-surface phyt oplankton pigment concentration of case I waters from spectral marine refle ctance measurements (ocean color) at the Sea-viewing Wide Field-of-view Sen sor (SeaWiFS) visible wavelengths, The advantages of neural network approxi mation, i.e., association of nonlinear complexity, smoothness, and reduced sensitivity to noise, are demonstrated. When applied to in situ California Cooperative Oceanic Fisheries Investigations data, the neural network algor ithm performs better than the reflectance ratio algorithms. Relative rms er rors on pigment concentration are reduced from 61 and 62 to 38%, and absolu te rms errors are reduced from 4.43 and 3.52 to 0.83 mg m(-3). When applied to SeaWiFS-derived imagery, there is statistical evidence that the neural network algorithm filters residual atmospheric correction errors more effic iently than the standard SeaWiFS bio-optical algorithm.