Space Debris Tracker with Real-Time Orbit Data

Abstract

The rapid growth of satellites and fragmentation debris in Earth’s orbit has significantly increased the risk of collisions that threaten operational spacecraft and long-term orbital sustainability. Traditional Space Situational Awareness (SSA) systems rely mainly on static orbital catalogs and periodic updates, which limits their ability to provide real-time monitoring and predictive risk analysis. This paper proposes a Space Debris Tracker with Real-Time Orbit Data that integrates public space-track datasets, SGP4 orbit propagation, and machine learning models to enhance orbital monitoring and collision prediction. The proposed system processes updated satellite telemetry and debris data, predicts orbital trajectories, and evaluates potential conjunction risks using intelligent classification models. A web-based interactive dashboard visualizes orbital movements in both 2D and 3D environments, allowing users to filter objects by altitude, velocity, and risk level. The system also provides automated alerts for potential collision scenarios, enabling researchers and satellite operators to make timely decisions. By combining predictive analytics, real-time visualization, and scalable architecture, the proposed platform improves situational awareness and supports safer satellite operations. The developed framework demonstrates how machine learning and modern visualization technologies can contribute to sustainable space traffic management and future autonomous collision avoidance systems.