Capabilities

dSGP4 is an open-source project that constitutes a differentiable version of SGP4. It also offers hybrid ML-dSGP4 models to improve the accuracy of SGP4, when simulated or observed precise data is available.

The core capabilities of dSGP4 can be summarized as follows:

• Differentiable version of SGP4 (implemented in PyTorch)

• Hybrid SGP4 and machine learning propagation: input/output/parameters corrections of SGP4 from accurate simulated or observed data are learned

• Parallel TLE propagation

• Use of differentiable SGP4 on several spaceflight mechanics problems (state transition matrix computation, covariance transformation, and propagation, orbit determination, ML hybrid orbit propagation, etc.)