Satellite Orbit Prediction Through Observation Data and the Artificial Neural Networks

In this study, a different approach to the prediction of satellite position is introduced. All methods are based on the Kepler’s laws of planetary motion and the orbital perturbations such as the Earth’s oblateness, atmospheric drag, third-body perturbation and the solar-radiation pressure. All these perturbations are modeled and are included separately in the equation. However, this paper offers a new view of the prediction which suggests the use of artificial neural networks and observation data. The advantage of this method is based on the usage of observation data, so that all disturbances are taken into account and there is no need to use perturbation models. For this reason, the use of the TLE as the most reachable actual data is considered. Comparison of the output of this method with actual data shows the accuracy of the proposed method which is very high.