Prediction of theDstindex using multiresolution wavelet models
Hua‐Liang Wei, Steve A. Billings, Michael A. Balikhin · Journal of Geophysical Research Atmospheres · 2004
A new identification approach is introduced for predicting theDstindex using multiresolution B‐spline wavelet models based on an observational data set consisting ofVBs, the solar wind parameter, as the input and theDstindex as the output. The relationship between the inputVBsand outputDstis initially described using a B‐spline wavelet model. This model is then simplified using an orthogonal least squares and error reduction ratio (OLS‐ERR) algorithm by selecting the significant model terms to produce a parsimonious wavelet model. Forecasts of theDstindex are then computed based on this model.