Influences of Solar Wind Parameters on Energetic Electron Fluxes at Geosynchronous Orbit Revealed by the Deep SHAP Method

• Published in: Space weather Vol. 22; no. 6
• Main Authors: Wang, Jianhang, Xiang, Zheng, Ni, Binbin, Guo, Deyu, Liu, Yangxizi, Dong, Junhu, Hu, Jingle, Guo, Haozhi
• Format: Journal Article
• Language: English
• Published: 01.06.2024
• Subjects: electron flux; geosynchronous orbit; machine learning
• ISSN: 1542-7390; 1542-7390
• DOI: 10.1029/2024SW003880

Solar wind is an intermediary in energy transfer from the Sun into the Earth's magnetosphere, and is considered as a decisive driver of energetic electron dynamics at the geosynchronous orbit (GEO). Based on machine learning technology, several models driven by solar wind parameters have been established to predict GEO electron fluxes. However, the relative contributions of different solar wind parameters on GEO electron fluxes are still unclear. Recently, a feature attribution method, Deep SHapley Additive exPlanations (Deep SHAP) is proposed to open black boxes of machine learning models. In this study, we use the Deep SHAP method to quantify contributions of different solar wind parameters with an artificial neural network (ANN) model. Backpropagating the prediction results of this ANN model from 2011 to 2020, SHAP values for four solar wind parameters (interplanetary magnetic field (IMF) BZ, solar wind speed, solar wind dynamic pressure, and proton density) are calculated and comprehensively analyzed. The results suggest that solar wind speed with a lag of 1 day is the most important driver. We further investigate relative roles of different parameters in three specific electron fluxes variation events (corresponding to electron fluxes reaching a local maximum, a local minimum, and unchanged, respectively). The results suggest that high solar wind speed and southward IMF BZ (high dynamic pressures) facilitate increases (decreases) of electron fluxes. These findings help reveal the underlying physical mechanisms of GEO electron dynamics and help develop more accurate prediction models for GEO electron fluxes. Plain Language Summary Solar wind, which transfers energy from the Sun to the Earth's magnetosphere, plays a crucial role in the dynamics of energetic electrons at geosynchronous orbit (GEO). The process is such complex that hundreds of studies have tried to clarify the correlation between solar wind and the dynamics of the GEO electron fluxes but haven't gained a clear conclusion yet. In this study, we reveal the influences of solar wind parameters on electron fluxes by opening the black box of a machine learning model based on a feature attribution method. We analyze the importance of different solar wind parameters statistically. The results show that the solar wind speed on previous day is the most important parameter for variations of GEO electron fluxes. We also investigate the influence of different solar wind parameters on electron fluxes during three specific moments. Our results indicate that high solar wind speed and southward IMF BZ (high dynamic pressures) are favorable for the increases (decreases) of electron fluxes. These findings can help us understand the key factors that affect energetic electron behaviors and contribute to the development of more accurate and reliable prediction models in the future. Key Points The Deep SHapley Additive exPlanations method is used to quantify contributions of different solar wind parameters on dynamics of energetic electrons at geosynchronous orbit (GEO) Solar wind speed with a lag of 1 day is the most important factor for >800 keV electron flux variations at GEO High solar wind speed and southward interplanetary magnetic field BZ favor increases of energetic electron fluxes while high dynamic pressure inhibits the fluxes