IMPROVED ESTIMATION, USING NEURAL NETWORKS, OF THE FOOD-CONSUMPTION OF FISH POPULATIONS

The aim of the present work is to improve the relevance of methods to predict the Q/B ratio (annual consumption of food Q relative to the bi omass B of fish species), which is essential for any multispecies stoc k model based on trophic relationships. Two methods were considered: m ultiple linear regression (MLR), improved by the log transformation of some variables, and artificial neural networks (NNs), which have the advantage of accepting nonlinearity in the relations between Q/B and d ifferent independent variables. Although MLR is acceptable for predict ing small values of Q/B (mainly carnivorous fish), it does not display good performances for high values (herbivorous and detritivorous fish ). In contrast, by using the gradient back-propagation algorithm, the NNs are suitable for a valid estimation of the whole range of known va lues of Q/B. Both types of model were tested with test sets of data (d rawn at random from the full set of data) that had not been used for m odel construction. The proposed methods are thus predictive. As they r equire only a few easily accessible parameters, they can avoid tedious studies of fish feeding over a daily and an annual cycle. The NN prog ram used, operating on a personal computer, is available on request.