Monthly Rainfall Forecasting Using Bayesian Belief Networks
Journal Title: International Research Journal of Applied and Basic Sciences - Year 2012, Vol 3, Issue 11
Abstract
Bayesian Belief Networks (BBNs) provide an effective graphical model for factoring joint probability distributions under uncertainty. In this paper we introduce application of BBNs in weather forecasting. We work with a database of observations (monthly rainfall) in a network of 20 stations in Khorasan provinces (Iran), measured for the years 1985-2011 on a grid of approximately 600km resolution. Firstly, we analyze the efficiency of Tabu search algorithm to structural learning of BBN. In this step, a directed acyclic graph shows dependencies among stations in the area of study; we also use Netica software for parametric learning of BBNs. The comparisons show usefulness of proposed method as a probabilistic rainfall forecasting model.
Authors and Affiliations
Alireza Sadeghi Hesar| Department of Computer Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran,Alireza.sadeghi89@yahoo.com, Hamid Tabatabaee| Department of Computer Engineering, Quchan Branch, Islamic Azad University, Quchan, Iran, Mehrdad Jalali| Department of Computer Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran
Keywords
Related Articles
- EP ID EP5170
- DOI -
- Views 370
- Downloads 17
The formation of G-super soluble Groups
A class of finite groups is called saturated formation ? when if ( ) G G ?? ? , then G ?? in which ? is called a class of groups. The purpose of this paper is to show that the finite super soluble groups form a saturated...
Efficiency of potato production in the city of Tabriz – Basmenj
In this study, the available data on potato production in the city of Tabriz city Basmnj, the first was to determine the appropriate production function. After determining the appropriate form of test functions, the resu...
Vermicompost as a soil supplement to improve growth of tomato (Lycopersicum esculentum)
The effects of vermicompost on the growth of tomatoes (Lycopersicum esculentum) (c.v. Polard) was investigated in a greenhouse experiment. Five levels vermicompost treatments including: 0, 10, 20, 30 and 40 % (w/v) were...
Method Of Complex Chemical Reactions
In the first part of the study, several mathematical methods for solving differential equations systems describing a process which are most commonly used in engineering theory and practice, were analyzed, for a character...
Design of a Low - Power Switched - Capacitor Bandpass Filter in 0.18?m CMOS Technology with Quality Factor Tunability
In this paper, the design of low - power second - order switched – capacitor bandpass filter is presented in 0.18?m CMOS technology. Instead of two operational amplifiers in conventional structures only...