Machine Learning Augmented Prediction of Saturn’s Right Ascension and Declination

Astronomy has evolved from qualitative observations to a precise science, founded on the basic laws of gravitation. Isaac Newton’s law of universal gravitation and Kepler’s laws of planetary motion remain vital for predicting celestial movements. Given these principles along with methods from spherical geometry, objects can be analytically tracked as perceived from Earth. This mathematical method, however, makes certain simplifications that can affect the accuracy of its predictions. To resolve this potential inaccuracy, a machine-learning-based random forest model is proposed to predict the path of Saturn. This model is trained on generated data and its results are compared to collected telescopic data. To further the study, a one-class Support Vector Machine (SVM) model was created for the detection of anomalies in Saturn’s orbit, in the hopes of being used to improve telescopic data collection methods.