Predicting CME arrival time through data integration and ensemble learning

The Sun constantly releases radiation and plasma into the heliosphere. Sporadically, launches solar eruptions such as flares coronal mass ejections (CMEs). CMEs carry away a huge amount of magnetic flux with them. An Earth-directed CME can cause serious consequences to human system. It destroy power grids/pipelines, satellites, communications. Therefore, accurately monitoring predicting is important minimize damages In this study we propose an ensemble learning approach, named CMETNet, for arrival time from Earth. We collect integrate eruptive events two cycles, #23 #24, 1996 2021 total 363 geoeffective CMEs. data used making predictions include features, wind parameters images obtained SOHO/LASCO C2 coronagraph. Our framework comprises regression algorithms numerical analysis convolutional neural network image processing. Experimental results show that CMETNet performs better than existing machine methods reported in literature, Pearson product-moment correlation coefficient 0.83 mean absolute error 9.75 h.