MEPS 139:289-299 (1996)  -  doi:10.3354/meps139289

Artificial neural networks as empirical models for estimating phytoplankton production

Scardi M

Many empirical models have been developed in order to obtain phytoplankton production estimates from other variables that are easier to measure. These empirical models are usually based on regression of phytoplankton production against biomass and other variables. They are particularly useful to fully exploit data sets acquired by both in situ instrumental measurements and remote sensing. Two conventional empirical models were compared with a new approach, based on artificial neural networks. Although very simple neural networks were used, they provided a much better fit to observed data than conventional models do and they seem a very promising tool for phytoplankton production modeling.


Empirical models · Neural networks · Phytoplankton · Production · Estuaries


Full text in pdf format