Click for new scientific resources and news about Corona[COVID-19]

Paper Information

Journal:   IRANIAN JOURNAL OF IRRIGATION AND DRAINAGE   2008 , Volume 2 , Number 2; Page(s) 123 To 132.
 
Paper: 

PREDICTION OF ANNUAL PRECIPITATION USING ARTIFICIAL NEURAL NETWORKS IN KERMAN PROVINCE

 
 
Author(s):  KARIMI GOOGHARI SH., ESLAMI A.
 
* 
 
Abstract: 

Prediction of annual precipitation usually guarantees success in dry-farming, design and operation of water resources, better regional economic programs and pasture management. Kerman province is located in the south east of Iran where more is covered by high mountains and pastures. Agricultural production and farmer economic statues in. these regions are highly associated with annual precipitation. Therefore, a method for predicting annual precipitation in the beginning of water-year could be useful.
The studies have been resulted good relationships between annual precipitation and the duration which is needed to occur a definite amount of precipitation since the onset of autumn (beginning of water-year; October to September) in some part of Iran. Karimi and Sepaskhah (2006) have reported significance linear relationship between annual rainfall and the duration of 47.5 mm of precipitation since the onset of autumn in Kerman province. They developed a linear model to predict the annual rainfall too. Similar results have been reported by Sepaskhah and Taghvaee (2006) for west of Iran.
Different procedures have been used to predict rainfall. Rainfall forecasting is an extremely complex and difficult problem involving many variables which are interconnected in a very complicated way. Most of the relationships describing the dynamical and spatial relations are nonlinear. This complexity and non-linearity makes it attractive to try the artificial neural network (ANN) approach which is inherently suited to problems that are mathematically difficult to describe.
Neural networks were originally developed as a model of information storage and computing by neuronal processes found in nature. Details of emergent computational properties of such artificial neural networks are discussed in many texts. The use of neural networks in the hydrology is dramatically increasing, and includes applications to problems such as rainfall-runoff modeling (Shamsedin, 1997) and reservoir inflow forecasting (Coulibari et al., 2000). The ANN methodology has been applied also to forecast rainfall; for example, French et al. (1992) used synthetically generated rainfall storms to calibrate an ANN model and then generated plausible rainfall sequences that could occur over a catchment using a physically based rainfall to validate the ANN. Based on author knowledge there is no published report about the ability of ANNs to predict the rainfall south east of Iran.
The present study was conducted to develop linear and ANN models to predict the annual precipitation in Kerman province based on prior knowledge of relatively good relationship between the numbers of rainy days from the beginning of fall for total precipitation of 47.5 mm with annual precipitation.

 
Keyword(s): ANNUAL PRECIPITATION, ARTIFICIAL NEUVAL NETWORKS, TIME OF PRECIPITETION OCCURANCE
 
 
References: 
  • Not Registered.
  •  
  •  
 
Citations: 
  • Not Registered.
 
+ Click to Cite.
APA: Copy

KARIMI GOOGHARI, S., & ESLAMI, A. (2008). PREDICTION OF ANNUAL PRECIPITATION USING ARTIFICIAL NEURAL NETWORKS IN KERMAN PROVINCE. IRANIAN JOURNAL OF IRRIGATION AND DRAINAGE, 2(2), 123-132. https://www.sid.ir/en/journal/ViewPaper.aspx?id=211016



Vancouver: Copy

KARIMI GOOGHARI SH., ESLAMI A.. PREDICTION OF ANNUAL PRECIPITATION USING ARTIFICIAL NEURAL NETWORKS IN KERMAN PROVINCE. IRANIAN JOURNAL OF IRRIGATION AND DRAINAGE. 2008 [cited 2021November30];2(2):123-132. Available from: https://www.sid.ir/en/journal/ViewPaper.aspx?id=211016



IEEE: Copy

KARIMI GOOGHARI, S., ESLAMI, A., 2008. PREDICTION OF ANNUAL PRECIPITATION USING ARTIFICIAL NEURAL NETWORKS IN KERMAN PROVINCE. IRANIAN JOURNAL OF IRRIGATION AND DRAINAGE, [online] 2(2), pp.123-132. Available: https://www.sid.ir/en/journal/ViewPaper.aspx?id=211016.



 
 
Persian Abstract Yearly Visit 61
 
 
Latest on Blog
Enter SID Blog