Prediction of rainfall in Saudi Arabia

Cardinal Scholar

Show simple item record

dc.contributor.advisor Rahamataullaha Imana, E. Eica. Ema.
dc.contributor.author Alshammari, Hadi O..
dc.date.accessioned 2015-05-14T12:31:52Z
dc.date.available 2015-05-14T12:31:52Z
dc.date.issued 2015-05-02
dc.identifier.uri http://cardinalscholar.bsu.edu/handle/123456789/199546
dc.description.abstract Climate change has been one of the major concerns of the world. Saudi Arabia is not free from this concern. Saudi Arabia does not have enough rain and for this reason most of its area is desert. But some cities of Saudi Arabia are now experiencing frequent rainfall. But infrastructures of these areas are not designed for rainfall. So rainfall often causes lots of damage and casualties in Saudi Arabia. For this reason it is very important us to forecast future rainfall in Saudi Arabia. In our study we analyzed a group of climate data from 1986 to 2014. We had one year’s information missing, so we estimated that missing value first. At first we try to fit and predict rainfall using regression. But we did not get very good fits. The main reason is that our response variable, the total amount of yearly rainfall, was not correct. We observe from the rainfall data many years with total zero mm rainfall, but the data reports contradictory picture as the total number of rainy days in such years were quite high. So we tried to fit and predict rainfall using a mediation technique. In our study we consider the number of rainy days as the mediator variable for rainfall. Since rainfall data is a time series data we employ ARIMA models to fit the data. We did a cross validation study to evaluate forecasts and it came out that the mediation method predicts the rainfall data in the best way. Finally we present the future trend of rainfall for the major cities of Saudi Arabia. en_US
dc.description.sponsorship Department of Mathematical Sciences
dc.description.tableofcontents Estimation of missing values in Saudi Arabia climate data -- Modeling and fitting of data using regression and mediation methods -- Forecasting with ARIMA models -- Evaluations of forecasts by regression, mediation and ARIMA models.
dc.subject.lcsh Rainfall probabilities -- Saudi Arabia -- Mathematical models.
dc.subject.lcsh Missing observations (Statistics)
dc.title Prediction of rainfall in Saudi Arabia en_US
dc.description.degree Thesis (M.S.) en_US
dc.identifier.cardcat-url http://liblink.bsu.edu/catkey/1784571


Files in this item

This item appears in the following Collection(s)

  • Master's Theses [5318]
    Master's theses submitted to the Graduate School by Ball State University master's degree candidates in partial fulfillment of degree requirements.

Show simple item record

Search Cardinal Scholar


Browse

My Account