A class of Bayesian machine learning model for forecasting Dst during intense geomagnetic storms

Abstract

In this paper we apply a class of Bayesian machine learning model, Gaussian Process Regression, to the prediction of Dst index by using 80 intense geomagnetic storms data (Dst⩽-100nT) from 1995 to 2014. The purpose of this paper is to compare the performance of Gaussian process regression model with Support Vector Machine model combined together with Distance Correlation (DC-SVM) and Neural Network model combined together with Distance Correlation (DC-NN) (Lu et al., 2016). For comparison, we estimate the correlation coefficients (CC), the RMS errors, the absolute value of difference in minimum Dst (ΔDstmin) and the absolute value of difference in minimum time (ΔtDst) between observed Dst and predicted one.In order to compare the prediction effects and the generalizability of the three models to magnetic storm events, we combined 70 intense magnetic storm events and 10 super large magnetic storm events into one group. It is shown that DC-GPR model exhibits the better forecasting performance than by DC-SVM model and DC-NN model in magnetic storm. The CC, the RMS errors, the ΔDstmin , and the ΔtDst of GPR are 0.65, 35.45 nT, 16.12 nT and 1.16 h, respectively.