Stochastic Model for Rainfall Occurrence Using Markov chain Model

Abstract

This dissertation will attempt to demonstrate the potential benefits of using Stochastic Processes for modeling and interpreting historical rainfall records by the examination of weekly rainfall occurrence by using Markov Chains as the driving mechanism. The weekly occurrence of rainfall was modeled by two-state first and second order Markov chain while the amount of rainfall on a rainy week was approximated by taking the maximum likelihood estimation method to estimate transition probability Matrices of rainfall sequences during rainy season. Daily rainfall data were collected from two meteorological stations located in Kurdufan State based on the (21) years of past data. The result indicated that the season starts effectively from 8 th SMW (17 – 22th June) at ElObied station and 7 th SMW (11 – 17th June) at Kadugli station. The transition probability matrix of Markov chain model is homogeneous and remains constant over the years of period considered. Accordingly the testing of ID degree that one in Elobied higher than that of Kadugli Station the hypothesis is accepted at 5% level of significant with P-value (0.151). The researcher recommended that the weekly rainfall should be generated with the first-order Markov chain model to preserve the statistical and seasonal characteristics that exist in the historical record exact on short season.