Affiliations: GPAR-Group of Robotic and Automation, Federal University of Ceara, Fortaleze, Brazil | Meteorology Department, Foundation for Meteorology and Hydric Resourses of Ceara, Ceara, Brazil
Note: [] Corresponding author. Thiago N. de Castro, GPAR-Group of Robotic and Automation, Federal University of Ceara, Fortaleze, Brazil. Tel.: +55 85 3366 9578; Fax: +55 85 3366 9574; E-mails; tnc@dee.ufc.br (Thiago N. de Castro); ricthe@dee.ufc.br (Ricardo S.T. Pontes); laurinda@dee.ufc.br (Laurinda L.N. dos Reis); sdaher@dee.ufc.br. (Sérgio Daher); brabo@funceme.br (José M.B. Alves)
Abstract: The knowledge about the seasonal rainfall in some Brazilian regions is essential for agriculture and the adequate management of water resources. For this purpose, linear and nonlinear models are commonly used for seasonal rainfall prediction, while some of them are based on Artificial Neural Networks, demonstrating great potential as shown in literature. According to this tendency, this work presents a rainfall seasonal forecast model based on a neuro-fuzzy technique called Neo-Fuzzy Neuron Model. Improved performance by using this approach has been obtained in terms of reduced root mean square error (RMSE) and increased correlation between predicted and real output when compared with dynamic downscaling model using the Regional Spectral Model. Experimental results show the effectiveness of the proposed method in predictions regarding the first four trimesters from year 2002 up to the current one.
Keywords: Seasonal rainfall prediction, ANN, neo-fuzzy neuron, dynamic model
