TY - JOUR
T1 - El Niño southern-oscillation prediction using southern oscillation index and Niño3 as onset indicators
T2 - Application of artificial neural networks
AU - Baawain, Mahad S.
AU - Nour, Mohamed H.
AU - El-Din, Ahmed G.
AU - El-Din, Mohamed Gamal
PY - 2005/3
Y1 - 2005/3
N2 - El Niño southern-oscillation (ENSO) is known to be the strongest climatic variation on seasonal to inter-annual time scales. It causes severe droughts, floods, fires, and hurricanes leading to economical disasters. This study explores the use of relatively simple inputs in developing artificial neural network (ANN) models for predicting the onset of ENSO by forecasting some of its indicators. Two indicators, southern oscillation index (SOI) and Niño3, were used one at a time to model the ENSO occurrence using monthly averaged data. Both models performed well in forecasting and predicting ENSO occurrence up to 12 months in advance. Correlation coefficient values of more than 0.8 and 0.9 (one month lead time), and above 0.7 and 0.8 (12 month lead time) were obtained for SOI and Niño3, respectively. Both models apply the feed forward multilayer perceptron network trained with error back-propagation algorithm. The final models were compared with each other and found to be highly consistent with 75% agreement in their forecasting ability.
AB - El Niño southern-oscillation (ENSO) is known to be the strongest climatic variation on seasonal to inter-annual time scales. It causes severe droughts, floods, fires, and hurricanes leading to economical disasters. This study explores the use of relatively simple inputs in developing artificial neural network (ANN) models for predicting the onset of ENSO by forecasting some of its indicators. Two indicators, southern oscillation index (SOI) and Niño3, were used one at a time to model the ENSO occurrence using monthly averaged data. Both models performed well in forecasting and predicting ENSO occurrence up to 12 months in advance. Correlation coefficient values of more than 0.8 and 0.9 (one month lead time), and above 0.7 and 0.8 (12 month lead time) were obtained for SOI and Niño3, respectively. Both models apply the feed forward multilayer perceptron network trained with error back-propagation algorithm. The final models were compared with each other and found to be highly consistent with 75% agreement in their forecasting ability.
KW - Artificial neural networks
KW - Cllimate anomalies
KW - ENSO
KW - El Niño
KW - La Niña
KW - Niño3
KW - Southern oscillation index (SOI)
KW - Teleconnections
UR - http://www.scopus.com/inward/record.url?scp=20544448454&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=20544448454&partnerID=8YFLogxK
U2 - 10.1139/s04-047
DO - 10.1139/s04-047
M3 - Article
AN - SCOPUS:20544448454
SN - 1496-2551
VL - 4
SP - 113
EP - 121
JO - Journal of Environmental Engineering and Science
JF - Journal of Environmental Engineering and Science
IS - 2
ER -