Forecasting Rainfall Time Series with stochastic output approximated by neural networks Bayesian approach

The annual estimate of the availability of the amount of water for the agricultural sector has become a lifetime in places where rainfall is scarce, as is the case of northwestern Argentina. This work proposes to model and simulate monthly rainfall time series from one geographical location of Catamarca, Valle El Viejo Portezuelo. In this sense, the time series prediction is mathematical and computational modelling series provided by monthly cumulative rainfall, which has stochastic output approximated by neural networks Bayesian approach. We propose to use an algorithm based on artificial neural networks (ANNs) using the Bayesian inference. The result of the prediction consists of 20% of the provided data consisting of 2000 to 2010. A new analysis for modelling, simulation and computational prediction of cumulative rainfall from one geographical location is well presented. They are used as data information, only the historical time series of daily flows measured in mmH2O. Preliminary results of the annual forecast in mmH2O with a prediction horizon of one year and a half are presented, 18 months, respectively. The methodology employs artificial neural network based tools, statistical analysis and computer to complete the missing information and knowledge of the qualitative and quantitative behavior. They also show some preliminary results with different prediction horizons of the proposed filter and its comparison with the performance Gaussian process filter used in the literature.

@article{Rivero2014,
  title     = {Forecasting Rainfall Time Series with stochastic output approximated by neural networks Bayesian approach},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {5},
  number    = {6},
  year      = {2014},
  publisher = {The Science and Information Organization},
  author    = {Cristian Rodriguez Rivero and Julian Antonio Pucheta},
  doi       = {10.14569/IJACSA.2014.050623},
  url       = {https://doi.org/10.14569/IJACSA.2014.050623}
}