Neural networks are increasingly used in the field of hydrology due to their properties of parsimony and universal approximation with regard to nonlinear systems. Nevertheless, as a result of the non stationarity of natural variables (rainfalls and consequently discharges) it appeared as difficult to capture both dynamics (roughly slow and fast) in a same neural network while their respective behaviors cannot be fully dissociated. For this reason the identification of the behavior of a complex aquifer, such as the aquifer of the Lez spring addressed in this study, is not yet fully achieved. Taking profit of such an analysis this paper presents an original way to decompose the behavior of the aquifer in several independent components using the powerful tool of multiresolution analysis. The method allows thus to perform discharge prediction without rainfalls prediction up to three days ahead increasing considerably the performance of the predictive methods.