Predictive Modeling of Gamma Radiation Levels During Solar Eclipses: A Machine Learning Approach

Predicting gamma radiation levels during solar eclipses can enhance our understanding of eclipse-related phenomena and improve monitoring capabilities. This study focuses on the development and evaluation of machine learning models to predict gamma radiation levels during solar eclipses. The dataset includes various parameters related to solar eclipses such as eclipse type, eclipse size, study area, and temporal information. We examine the relationship between these parameters and gamma radiation levels to identify significant factors influencing the predictions. Regression tree and random forest regression models are trained and evaluated for their accuracy in predicting gamma radiation levels during eclipses. Additionally, visual techniques, including paired plots and correlation matrices, are employed to elucidate the relationships between different features and gamma radiation levels. This analysis provides valuable insights into the factors affecting gamma radiation and underscores the potential of machine learning in the prediction and monitoring of solar eclipse phenomena.