A Way To Predict The Solar Wind Velocity Base On SVR Method

摘要

We apply a new neural network technique, support vector regression (SVR), to forecast the solar wind (SW) velocity. In our work, we choose the SW data during the nine years from 1998 to 2006, which includes the periods of the SW speed variation associated with high speed streams from coronal hole and coronal mass ejections (CMEs). We fred that the new approach is accurate and reliable in forecasting SW velocity. Based on the error difference, it can be concluded that the SVR technique can lend it itself to future space weather forecasting models.