Prediction of Solar Wind Speed at 1 AU Using an Artificial Neural Network

Yi Yang  Fang Shen  Zicai Yang  Xueshang Feng
First published: 18 August 2018

A hybrid intelligent source surface model applying the artificial neural network tactic for solar wind speed prediction is presented in this paper. The model is a hybrid system merging various observational and theoretical information as input. Different inputs are tested including individual parameters and their combinations in order to select an optimum. Then, the optimal model is implemented for prediction. The prediction is validated by both error analysis and event‐based analysis from 2007 to 2016. The overall correlation coefficient is 0.74, and the root‐mean‐square error is 68 km/s. The probability for detecting a high‐speed‐event is 0.68, the positive predicted value is 0.73, and the threat score is 0.55.