Machine Learning Approach to Improve Satellite Orbit Prediction Accuracy Using Publicly Available Data

Efficient and high precision orbit prediction is increasingly crucial for improved Space Situational Awareness. Due to the lack of the required information such as space environment conditions and characteristics of Resident Space Objects (RSOs), satellite collisions have happened, partially because that the solely physics-based approaches can fail to achieve the required accuracy for collision avoidance. With the hypothesis that a Machine Learning (ML) approach can learn the underlying pattern of the orbit prediction errors from historical data, in this paper, the Support Vector Machine (SVM) is explored for improving the orbit prediction accuracy. Two publicly available Two-Line Element (TLE) catalog and International Laser Ranging Service (ILRS) catalog are used to validate the proposed ML approach. The position and velocity components of 11 total RSOs maintained at both catalogs are studied. Results of the study demonstrate that the designed dataset structure and SVM model can improve the orbit prediction accuracy with good performance on most cases. The performance on RSOs belonging to different orbit types is analyzed using different sizes of training and testing data. Results of the paper demonstrate the potential of using the proposed ML approach to improve the accuracy of TLE catalog.