Técnicas de inteligência computacional aplicadas à modelagem chuva vazão

Abstract

Rainfall-runoff modeling is fundamental for water resource management; however, its inherently non-linear nature and the influence of large-scale climatic phenomena represent a significant methodological challenge for traditional hydrological models. This work aimed to develop and evaluate a monthly flow forecasting model for the DO 3 Hydrographic District, outlet at Naque Velho, using computational intelligence techniques. The methodology adopted explored the potential of Artificial Neural Networks (ANNs) coupled with a Genetic Algorithm (GA). This was used for the global search of an optimal set of synaptic weights, aiming to overcome the vulnerability of the backpropagation algorithm to local minima and ensuring greater robustness and accuracy in network training. The results demonstrated that the model achieved median performance, converging in less than 20 generations, with a final fitness of 0.79. Flood events were fully captured within the upper predicted range, confirming that the model adequately incorporated the effect of antecedent precipitation and surface runoff memory; however, it showed superior performance during the dry season. The complete coverage of extremes (COV_ext=1) demonstrates the system's ability to handle hydrologically critical episodes without inflating average predictions. The model consolidates a hybrid approach capable of representing the uncertainty and seasonal variability of the basin. Its structure allows for a more faithful modeling of hydrological behavior, maintaining statistical robustness and operational simplicity