Abstract
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.
Original language | English |
---|---|
Pages (from-to) | 113-121 |
Number of pages | 9 |
Journal | Journal of Environmental Engineering and Science |
Volume | 4 |
Issue number | 2 |
DOIs | |
Publication status | Published - Mar 2005 |
Externally published | Yes |
Keywords
- Artificial neural networks
- Cllimate anomalies
- ENSO
- El Niño
- La Niña
- Niño3
- Southern oscillation index (SOI)
- Teleconnections
ASJC Scopus subject areas
- General Environmental Science