investigation of the magnetosphere-solar wind interaction using an artificial neural network

The significant variations in the solar and magnetic parameters during the peak solar activity periods necessitate a detailed analysis to understand the interactions between the solar wind and the magnetosphere. this research investigates the impact of various solar wind parameters on the polar cap (pc) magnetic activity index. the primary objective of this research is to identify and analyze the relationships between the solar wind speed (vsw), the solar wind dynamic pressure (psw), and the interplanetary electric activity index (ae) with the pc index. a multilayer perceptron (mlp) artificial neural network model was used to explore these relationships. identifying and predicting complex nonlinear relationships between the input variables and the pc index is the distinctive feature of the model. the dataset used in this research was obtained from the defense meteorological satellite program (dmsp) satellites and includes vsw, psw, and ae parameters during periods of peak solar activity in 2002 and 2014. these data were used to analyze the temporal and seasonal variations of the pc index.the results indicate that artificial neural network models can effectively predict the pc index, and a strong correlation between the pc index and the input parameters, particularly in the first half of the years under research, has been observed. the results show the high potential of machine learning models to analyze and predict geomagnetic phenomena, which can improve the forecasting and management of geomagnetic disturbances, and serve as a suitable alternative to classical models.

investigation of the magnetosphere-solar wind interaction using an artificial neural network

the significant variations in the solar and magnetic parameters during the peak solar activity periods necessitate a detailed analysis to understand the interactions between the solar wind and the magnetosphere. this research investigates the impact of various solar wind parameters on the polar cap (pc) magnetic activity index. the primary objective of this research is to identify and analyze the relationships between the solar wind speed (vsw), the solar wind dynamic pressure (psw), and the interplanetary electric activity index (ae) with the pc index. a multilayer perceptron (mlp) artificial neural network model was used to explore these relationships. identifying and predicting complex nonlinear relationships between the input variables and the pc index is the distinctive feature of the model. the dataset used in this research was obtained from the defense meteorological satellite program (dmsp) satellites and includes vsw, psw, and ae parameters during periods of peak solar activity in 2002 and 2014. these data were used to analyze the temporal and seasonal variations of the pc index.the results indicate that artificial neural network models can effectively predict the pc index, and a strong correlation between the pc index and the input parameters, particularly in the first half of the years under research, has been observed. the results show the high potential of machine learning models to analyze and predict geomagnetic phenomena, which can improve the forecasting and management of geomagnetic disturbances, and serve as a suitable alternative to classical models.