Please use this identifier to cite or link to this item:
Type: Conference paper
Title: Medium term forecasting of rainfall using artificial neural networks
Author: Iseri, Y.
Dandy, G.
Maier, H.
Kawamura, A.
Jinno, K.
Citation: MODSIM 2005 International Congress on Modelling and Simulation: Modelling and Simulation Society of Australia and New Zealand, December 2005 / Andre Zerger and Robert M. Argent (eds.): pp.1834-1840
Publisher: mssanz
Publisher Place:
Issue Date: 2005
ISBN: 0975840002
Conference Name: International Congress on Modelling and Simulation (16th : 2005 : Melbourne, Victoria)
Statement of
Iseri, Y., G. C. Dandy, H. R. Maier, A. Kawamura and K. Jinno
Abstract: The state of the atmosphere and ocean can be characterized by climate indices. One of the well known indices is the Southern Oscillation Index (SOI). SOI measures the sea level pressure difference between Tahiti and Darwin, indicating the occurrence of the El Nià ±o phenomenon in the Central Pacific region. The Pacific Decadal Oscillation Index (PDOI) represents decadal scale atmosphere-ocean oscillation in the Pacific Ocean while the North Pacific Index (NPI) measures the intensity of the Aleutian low pressure cell ( Kawamura et al. 2003). A number of researchers have studied the possibility of forecasting rainfall several months in advance using climate indices such as SOI, PDOI and NPI (e.g. Silverman and Dracup, 2000). Furthermore, the existence of substantial databases of sea surface temperature anomalies (SST) opens the possibility of using these data to forecast rainfall several months in advance. Most of the research carried out in this area has used traditional statistical methods such as linear correlation or time series methods to identify the significant variables. These methods test for a linear relationship between the independent variables and rainfall, whereas the relationships are more likely to be non-linear as the underlying processes are themselves non-linear. This paper describes the use of partial mutual information (PMI) to identify the significant inputs for medium term rainfall forecasting in Japan. In particular, a study is made of monthly rainfall in the City of Fukuoka. Fukuoka, which is located in the northern part of Kyushu Island, is vulnerable to drought. In fact, the city was affected by devastating droughts in 1978 and 1996 (Kawamura and Jinno, 1996). Therefore a more successful rainfall prediction model would be of great benefit to the city. The possible inputs considered include the SOI, NPI and PDOI as well as SST in selected locations from a 5à °x 5à ° grid in the Pacific Ocean. The selected inputs are used to develop artificial neural network models (ANNs) to forecast rainfall in Fukuoka several months in advance. Six distinctive scenarios are considered in this study. Three of the scenarios use input data with lags between 1 month and 12 months and the other three scenarios use data with lags between 3 months and 12 months in order to investigate the possibility of forecasting more than 3 months in advance. The three scenarios considered for the two different ranges of lags are as follows: (1) use only SST as candidate predictors (2) use only climate indices as candidate predictors (3) use both SST and climate indices as candidate predictors One of the objectives of this study is the identification of a possible relationship between rainfall in Fukuoka and hydro-climatic variables such as SST and climate indices, using partial mutual information. The other objective is to verify the forecasts produced using the predictors identified with partial mutual information and investigate whether the inclusion of SST in addition to climate indices improves the prediction accuracy. It is found that the North Pacific Index (NPI) lagged by 6 months has a strong relationship with August rainfall in Fukuoka. Some improvement in forecasts can be achieved by including sea surface temperature anomalies as additional inputs. 1834
Description: © 2005 Modelling & Simulation Society of Australia & New Zealand
RMID: 0020052445
Description (link):
Published version:
Appears in Collections:Civil and Environmental Engineering publications
Environment Institute publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.