Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms
Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms
复制标题
DOI：
10.1038/s41598-019-57183-3
复制
发表时间：
2020-01
影响因子：
4.6
通讯作者：
Manali Pal;R. Maity;J. V. Ratnam;M. Nonaka;S. Behera
中科院分区：
文献类型：
--
作者：
Manali Pal;R. Maity;J. V. Ratnam;M. Nonaka;S. Behera
本研究的重点是评估机器学习（ML）算法在厄尔尼诺（La Niña）Modoki（ENSO Modoki）指数（EMI）长期预测中的有效性。我们评估了两种广泛使用的非线性ML算法，即支持向量回归（SVR）和随机森林（RF），以预测不同提前期（即6，12，18和24个月）的EMI。EMI的预测因子的确定使用肯德尔的tau之间的相关系数的每月EMI指数和每月异常的缓慢变化的气候变量，如海表温度（SST），海表高度（SSH）和土壤水分含量（SMC）。每个预测因子的重要性使用监督主成分分析（SPCA）进行评估。结果表明，SVR和RF都能够在6个月和12个月的提前期实际预测EMI的相位，尽管EMI的振幅被低估了。分析还表明，支持向量回归机在预测电磁干扰方面优于射频方法。
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.