Developing an empirical model of phytoplankton primary production: a neural network case study

We describe the development of a neural network model for estimating primar y production of phytoplankton. Data from an enriched estuary in the eastern United States, Chesapeake Bay, were used to train, validate and test the m odel. Two error backpropagation multilayer perceptrons were trained: a simp ler one (3-5-1) and a more complex one (12-5-1). Both neural networks outpe rformed conventional empirical models, even though only the latter, which e xploits a larger suite of predictive variables, provided truly accurate out puts. The application of this neural network model is thoroughly discussed and the results of a sensitivity analysis are also presented. (C) 1999 Else vier Science B.V. All rights reserved.