Using network theory and machine learning to predict El Niño
Peter D. Nooteboom1,3,Qing Yi Feng1,3,Cristóbal López2,Emilio Hernández-García2,and Henk A. Dijkstra1,3Peter D. Nooteboom et al.Peter D. Nooteboom1,3,Qing Yi Feng1,3,Cristóbal López2,Emilio Hernández-García2,and Henk A. Dijkstra1,3
Received: 07 Mar 2018 – Discussion started: 13 Mar 2018 – Revised: 22 Jun 2018 – Accepted: 26 Jun 2018 – Published: 23 Jul 2018
Abstract. The skill of current predictions of the warm phase of the El Niño Southern Oscillation (ENSO) reduces significantly beyond a lag time of 6 months. In this paper, we aim to increase this prediction skill at lag times of up to 1 year. The new method combines a classical autoregressive integrated moving average technique with a modern machine learning approach (through an artificial neural network). The attributes in such a neural network are derived from knowledge of physical processes and topological properties of climate networks, and they are tested using a Zebiak–Cane-type model and observations. For predictions up to 6 months ahead, the results of the hybrid model give a slightly better skill than the CFSv2 ensemble prediction by the National Centers for Environmental Prediction (NCEP). Interestingly, results for a 12-month lead time prediction have a similar skill as the shorter lead time predictions.
The prediction of the El Niño phenomenon, an increased sea surface temperature in the eastern Pacific, fascinates people for a long time. El Niño is associated with natural disasters, such as droughts and floods. Current methods can make a reliable prediction of this phenomenon up to 6 months ahead. However, this article presents a method which combines network theory and machine learning which predicts El Niño up to 1 year ahead.
The prediction of the El Niño phenomenon, an increased sea surface temperature in the eastern...