@InProceedings{GarciaSantCastMont:2014:ApArNe,
               author = "Garcia, Jos{\'e} Roberto M. and Santos, Rafael Duarte Coelho dos 
                         and Castro, Christopher Cunningham and Monteiro, Antonio Miguel 
                         Vieira",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)}",
                title = "Applying artificial neural networks to calibrate the precipitation 
                         forecast of the CPTEC’s ensemble prediction system",
            booktitle = "Resumos...",
                 year = "2014",
               editor = "Santiago J{\'u}nior, Valdivino Alexandre de and Ferreira, Karine 
                         Reis",
         organization = "Workshop dos Cursos de Computa{\c{c}}{\~a}o Aplicada do INPE, 
                         14. (WORCAP).",
            publisher = "Instituto Nacional de Pesquisas Espaciais (INPE)",
              address = "S{\~a}o Jos{\'e} dos Campos",
             keywords = "machine learning, artificial neural network, feed-forward neural 
                         network, back-propagation algorithm, numerical weather prediction 
                         system, ensemble prediction system.",
             abstract = "Ensemble prediction is currently the state of the art in weather 
                         prediction due to the fact that it provides means for computing 
                         probabilities of the occurrence of meteorological events in a 
                         quantitatively way. However it is not a fail-safe system and one 
                         major cause is due to the uncertainties of the Nature that are not 
                         modeled into the computational system, generating a deviation of 
                         the prediction from the actual state of the weather. To minimize 
                         this deviation (to calibrate) several post-processing techniques 
                         over the prediction data have been applied. This work is about 
                         applying of a feed-forward neural network to calibrate the 
                         precipitation forecast produced by the CPTECs Ensemble Prediction 
                         System. The dataset is composed by forecasts of the rainy season 
                         from 2009 to 2011 over the La Plata Basin. The ensemble mean 
                         precipitation forecast and the neural network forecast are 
                         compared to the correspondent precipitation observations via Mean 
                         Absolute Error.",
  conference-location = "S{\~a}o Jos{\'e} dos Campos",
      conference-year = "12-13 nov. 2014",
             language = "en",
         organisation = "Instituto Nacional de Pesquisas Espaciais (INPE)",
                  ibi = "8JMKD3MGP8W/3HBR2PP",
                  url = "http://urlib.net/ibi/8JMKD3MGP8W/3HBR2PP",
           targetfile = "worcap2014_submission_30.pdf",
        urlaccessdate = "06 maio 2024"
}