We present a new approach in astrodynamics and celestial mechanics fields, calledhybrid perturbation theory. A hybrid perturbation theory combines anintegrating technique, general perturbation theory or special perturbation theory or semianalytical method, with aforecasting technique, statistical time series model or computational intelligence method. This combination permits an increase in the accuracy of the integrating technique, through the modeling of higher-order terms and other external forces not considered in the integrating technique. In this paper, neural networks have been used as time series forecasters in order to help two economic general perturbation theories describe the motion of an orbiter only perturbed by the Earth’s oblateness.
Deprit’s method has been revisited in order to take advantage of certain arbitrariness arising when the inverse of the Lie operator is applied to obtain the generating function of the Lie transform. This arbitrariness is intrinsic to all perturbation techniques and can be used to demonstrate the equivalence among different perturbation methods, to remove terms from the generating function of the Lie transform, or to eliminate several angles simultaneously in the case of having a degenerate Hamiltonian.
An up-to-date catalog of residents space objects orbiting Earth requires a critical balance between computational efficiency and orbital prediction precision. This work presents HSGP4, a hybrid orbit propagator specifically tailored for Galileo-type orbits that enhances the classical SGP4 analytical model using Artificial Neural Networks. The methodology centers on a non-invasive hybridization process that utilizes high-fidelity pseudo-observations to forecast SGP4 error residuals. A core contribution is the introduction of the Hybrid Two-Line Element format, which encapsulates neural model parameters alongside traditional orbital elements, ensuring seamless integration with existing catalog infrastructure. The development process involved comprehensive Exploratory Data Analysis and sensitivity analysis, which identified the argument of latitude as the most influential variable for correcting SGP4 errors in the MEO region. To ensure statistical robustness, a hierarchical selection strategy was implemented. This reduced an exhaustive search space of 32,256 candidate architectures to a final subset of optimized configurations. Validated against a decade of TLE data, the results confirm that HSGP4 effectively captures missing dynamic patterns and significantly improves ephemeris accuracy. By forecasting SGP4 error residuals, this hybrid approach provides a high-fidelity correction layer. It compensates for the limitations of analytical theories without requiring complex numerical integration.
Two-Line Elements (TLEs) continue to be the sole public source of orbiter observations. The accuracy of TLE propagations through the Simplified General Perturbations-4 (SGP4) software decreases dramatically as the propagation horizon increases, and thus the period of validity of TLEs is very limited. As a result, TLEs are gradually becoming insufficient for the growing demands of Space Situational Awareness (SSA). We propose a technique, based on the hybrid propagation methodology, aimed at extending TLE validity with minimal changes to the current TLE-SGP4 system in a non-intrusive way. It requires that the institution in possession of the osculating elements distributes hybrid TLEs, HTLEs, which encapsulate the standard TLE and the model of its propagation error. The validity extension can be accomplished when the end user processes HTLEs through the hybrid SGP4 propagator, HSGP4, which comprises the standard SGP4 and an error corrector.