1. Multiple linear regression (MLR), generalised additive models (GAM) and
artificial neural networks (ANN), were used to define young of the year (0) roach (Rutilus rutilus) microhabitat and to predict its abundance.
2. 0+ Roach and nine environmental variables were sampled using point abund
ance sampling by electrofishing in the littoral area of Lake Pareloup (Fran
ce) during summer 1997. Eight of these variables were used to set up the mo
dels after log(10) (x + 1) transformation of the dependent variable (0+ roa
ch density). Model training and testing were performed on independent subse
ts of the whole data matrix containing 306 records.
3. The predictive quality of the models was estimated using the determinati
on coefficient between observed and estimated values of roach densities. Th
e best models were provided by ANN, with a correlation coefficient (r) of 0
.83 in the training procedure and 0.62 in the testing procedure. GAM and ML
R gave lower prediction in the training set (r = 0.53 for GAM and r = 0.32
for MLR) and in the testing set (r = 0.48 for GAM and r = 0.43 for MLR). In
the same way, samples without fish were reliably predicted by ANN whereas
GAM and MLR predicted absence unreliably.
4. ANN sensitivity analysis of the eight environmental variables in the mod
els revealed that 0+ roach distribution was mainly influenced by five varia
bles: depth, distance from the bank, local slope of the bottom and percenta
ge of mud and flooded vegetation cover. The nonlinear influence of these va
riables on 0+ roach distribution was clearly shown using nonparametric lowe
ss smoothing procedures.
5. Non-linear modelling methods, such as GAM and ANN, were able to define 0
+ fish microhabitat precisely and to provide insight into 0+ roach distribu
tion and abundance in the littoral zone of a large reservoir. The results s
howed Bat in lakes, 0+ roach microhabitat is influenced by a complex combin
ation of several environmental variables acting mainly in a nonlinear way.