Ferramentas para avaliação da rede de monitoramento de qualidade de água da bacia do rio Piabanha – RJ com base em redes neurais e modelagem hidrológica

Abstract

Water quality monitoring is a complex issue that requires support tools in order to provide information for water resource management. Budget constraints as well as an inadequate water quality network design call for the development of evaluation tools to provide efficient water quality monitoring. For this purpose, a nonlinear principal component analysis (NLPCA) based on an autoassociative neural network was performed to assess the redundancy of the parameters and monitoring locations of the water quality network in the Piabanha River watershed. Principal Component Analysis (PCA) is widely used for this purpose. However, conventional PCA is not able to capture the nonlinearities of water quality data, while neural networks can represent those nonlinear relationships. From the results of NLPCA, the most relevant water quality parameter is Fecal Coliforms and the least relevant is Chemical Oxygen Demand. Regarding the monitoring locations, the most relevant is Rocio e the least relevant is Esperança. The second methodology aims to evaluate the RMQAP stations in view of observed data impact on the SWAT model calibration. To measure this impact, IRMQAP index was developed based on the adjustment of the hydrological model and neural networks for the simulation of the nitrate parameter as a function of the flow rate. The results showed that the most impressive station is Pedro do Rio and the less impressive is Poço Tarzan.