esa/dSGP4

dSGP4: differentiable SGP4. Supports differentiability, ML integration & embarassingly parallel computations

55
/ 100
Established

This tool helps satellite operators, space traffic managers, and astrodynamicists predict the future position and velocity of satellites and other orbital objects using Two-Line Element (TLE) data. You input a TLE for an object and a specific time, and it outputs the object's predicted position and velocity. This is especially useful for tasks like calculating state transition matrices, transforming covariance, or estimating orbits with advanced machine learning techniques.

No commits in the last 6 months. Available on PyPI.

Use this if you need to propagate satellite orbits and require the ability to calculate derivatives (gradients) of these propagations for advanced analysis, optimization, or machine learning applications.

Not ideal if you simply need to propagate an orbit without any need for gradient calculations or integration with machine learning frameworks, as simpler SGP4 implementations might suffice.

satellite-operations orbit-prediction space-situational-awareness astrodynamics machine-learning-for-space
Stale 6m
Maintenance 2 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

82

Forks

17

Language

Python

License

GPL-3.0

Last pushed

Apr 16, 2025

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/esa/dSGP4"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.