Abstract
The focus of this study is to evaluate the efficacy of Machine Learning (ML) algorithms in the long-lead prediction of El Niño (La Niña) Modoki (ENSO Modoki) index (EMI). We evaluated two widely used non-linear ML algorithms namely Support Vector Regression (SVR) and Random Forest (RF) to forecast the EMI at various lead times, viz. 6, 12, 18 and 24 months. The predictors for the EMI are identified using Kendall’s tau correlation coefficient between the monthly EMI index and the monthly anomalies of the slowly varying climate variables such as sea surface temperature (SST), sea surface height (SSH) and soil moisture content (SMC). The importance of each of the predictors is evaluated using the Supervised Principal Component Analysis (SPCA). The results indicate both SVR and RF to be capable of forecasting the phase of the EMI realistically at both 6-months and 12-months lead times though the amplitude of the EMI is underestimated for the strong events. The analysis also indicates the SVR to perform better than the RF method in forecasting the EMI.
Highlights
The El Niño (La Niña) Modoki (ENSO Modoki, hereafter EM)[1] is a newly acknowledged phenomenon characterized by warm central Pacific sea surface temperature (SST) flanked by cool eastern and western Pacific SSTs
The optimal number of principal components to be considered is determined by examining the variation of the prediction performance with number of principal components considered before feeding to the Machine Learning (ML) tools
Long-lead (6 to 12 months) prediction of El Niño Southern Oscillation (ENSO) Modoki index (EMI) with reasonable accuracy is achieved in this study using two ML algorithms namely Support Vector Regression (SVR) and Random Forest (RF)
Summary
The El Niño (La Niña) Modoki (ENSO Modoki, hereafter EM)[1] is a newly acknowledged phenomenon characterized by warm (cool) central Pacific sea surface temperature (SST) flanked by cool (warm) eastern and western Pacific SSTs. Impacts of EM events have been well established, the EM is apparently not so well predicted at long lead times by current operational climate forecast models[2,9,10,11,12,13,14]. APEC Climate Center (APCC) Multi-Model Ensemble (MME) seasonal forecast system shows the ability to predict the patterns of tropical Pacific SST anomaly (SSTA) of the Modoki events four months ahead with a high correlation coefficient i.e. 0.817. The limited skill in predicting the ENSO Modoki index (EMI) in terms of long lead times by the current seasonal forecasting systems, on the face of huge benefit in predicting it, motivated us to look for alternative methods to forecast the EMI. The following sections provide a detailed description of the results obtained, data used and mathematical description of the models in the methodology
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
