A Data-Driven Approach to Estimate LEO Orbit Capacity Models

TL;DR

This paper presents a data-driven method combining SINDy and LSTM to accurately model and predict the population and propagation of space objects in Low Earth Orbit, using a computationally efficient approach.

Contribution

It introduces a novel hybrid modeling approach that leverages high-fidelity data to create a low-fidelity model for faster orbit capacity estimation.

Findings

Accurately predicts LEO object population dynamics.

Reduces computational time compared to high-fidelity models.

Demonstrates effective forecasting of satellite and debris propagation.

Abstract

Utilizing the Sparse Identification of Nonlinear Dynamics algorithm (SINDy) and Long Short-Term Memory Recurrent Neural Networks (LSTM), the population of resident space objects, divided into Active, Derelict, and Debris, in LEO can be accurately modeled to predict future satellite and debris propagation. This proposed approach makes use of a data set coming from a computational expensive high-fidelity model, the MOCAT-MC, to provide a light, low-fidelity counterpart that provides accurate forecasting in a shorter time frame.