@Article{WeigangSaNordBevi:1996:PrSeSu,
               author = "Weigang, Li and Sa, Leonardo Deane de Abreu and Nordemann, Daniel 
                         Jean Roger and Bevilaqua, Rute Maria",
          affiliation = "{CPTEC-INPE-Cachoeira Paulista-12630-000-SP-Brasil}",
                title = "Predictions of Sea Surface Temperature in Tropical Ocean Using 
                         Neural Networks",
              journal = "Bulletin of the American Meteorological Society",
                 year = "1996",
               volume = "68",
               number = "1",
                pages = "23--33",
             keywords = "neural networks, prediction, sea surface temperature, time 
                         series.",
             abstract = "A review of researches on the relationship between the tropical 
                         ocean sea surface temperatures (SST) and rainfalI anomalies in 
                         Northeast Brazil was introduced. In this work, two neural network 
                         models are implemented to reconstruct and predict the time series 
                         of the SST in two regions: the tropical Atlantic ocean (Wrigbt 
                         index, from 1854 to 1985) and the tropical Pacific ocean (regions 
                         Ninol-2: 0ºN-10ºS, 270ºE- 280ºE and Nino 4: 5°N-5°S, 160ºE-150ºE, 
                         from 1950 to 1995). The selected neural networks include 
                         Backpropagation Neural Network (BNN) and Time Delay Neural Network 
                         (mNN). Both were imple- mented in the neural network stimulator 
                         SNNS. For the Wright index, the trained Backpropagation Neural 
                         Network successfully predicted the index of the following four 
                         months with the relative errors from 1.40 to 3.34%. For SST in 
                         Nino 1-2 and Nino4 regions, the Time Delay Neural Network was used 
                         for reconstruction and prediction. Comparing with the next six 
                         month observations and predictions, alI of them are 10- cated 
                         within the predicted error bars. These results show that neural 
                         network methods may be used, within certain limits, for prediction 
                         and evaluation of predictability of time series measured from 
                         phenomena influenced by complex climatic and geophysical 
                         processes, like SST.",
           copyholder = "SID/SCD",
                 issn = "0003-0007",
             language = "en",
           targetfile = "11058.pdf",
        urlaccessdate = "05 maio 2024"
}