Forecasting Rainfall Time Series with stochastic output approximated by neural networks Bayesian approach
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2014, Vol 5, Issue 6
Abstract
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.
Authors and Affiliations
Cristian Rivero, Julian Pucheta
Keywords
Related Articles
- EP ID EP136920
- DOI 10.14569/IJACSA.2014.050623
- Views 123
- Downloads 0
Recurrence Relation for Projectile Simulation Project and Game based Learning
Huge Gap has been observed on study of projectile simulation models relating it to speed of camera or frame per seconds. The objective of this paper is to explore and investigate time driven simulation models to mimic pr...
Formalization of UML Composite Structure using Colored Petri Nets
Design specification and requirement analysis, during development process involved in transformation of real world problems to software system are subjected to severe issues owing to involvement of semantics. Though, for...
Iterative Threshold Decoding Of High Rates Quasi-Cyclic OSMLD Codes
Majority logic decoding (MLD) codes are very powerful thanks to the simplicity of the decoder. Nevertheless, to find constructive families of these codes has been recognized to be a hard job. Also, the majority of known...
A Type-2 Fuzzy in Image Extraction for DICOM Image
Eradication of a desired portion of an image is a very important role in image processing and is also called feature extraction. This is mainly concern about reducing the number of possessions required to portray a large...
Modeling and Control by Multi-Model Approach of the Greenhouse Dynamical System with Multiple Time-delays
This paper presents the Internal Multi-Model Control IMMC for a multivariable discrete-time system with variable multiple delays. This work focus on the Greenhouse climate model as a multivariable time-delay system. In f...