What question did this study set out to answer?

This research aims to enhance orbital propagation accuracy using polynomial feature expansion.

May 10, 20260 citationsOpen Access

LSP-Orbital v4.1: Lo-Shu Geometric Orbit Propagation with Polynomial Feature Expansion

Key Points

This research aims to enhance orbital propagation accuracy using polynomial feature expansion.
Extended LSP-Orbital v1.0 with 21-dimensional polynomial feature expansion.
Large-scale training involved 410 satellites and 3,280 samples.
Utilized the Theorem LSP-O to predict tangential orbital residuals.
Achieved 49.6% mean error reduction over pure Keplerian propagation with an 80% win rate.
Reduced Iridium LEO error from 12.60km to 6.80km (-46%).
Demonstrated R^2=0.333 for LEO residuals and R^2=0.641 for MEO residuals.

Abstract

LSP-Orbital v4. 1 extends v1. 0 with polynomial feature expansion (21-dim) and large-scale training (410 satellites, 3, 280 samples, 7. 8x v1. 0). Key results: 49. 6% mean error reduction over pure Keplerian propagation (dt 30-120min), win rate 80%. Iridium LEO error: 12. 60km to 6. 80km (-46%). Theorem LSP-O: Lo-Shu row-imbalance predicts tangential orbital residuals with R²=0. 333 (LEO, N=2000, robust), R²=0. 641 (MEO, N=680). Full training dataset included (3280x21 features, 3280x3 targets, all orbit-type coefficients). Supersedes: 10. 5281/zenodo. 20082651.

AIに質問

Bookmark

View Full Paper