A Data-Driven Approach to Estimate LEO Orbit Capacity Models

2025/07/25 by B. Stock, Stock, Braden, Maddox McVarthy +3
Engineering · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Satellite Communication Systems #Space Satellite Systems and Control #Spacecraft Dynamics and Control

paper · pdf · doi:10.48550/arxiv.2507.19365

openalex publication_date 2025/07/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Parameters Evolution in Source-Sink Space Population Evolutionary Models
• A New Monte-Carlo Model for the Space Environment
• Threat Level Estimation From Possible Break-Up Events In LEO
• A review on the long short-term memory model
• Sparse Identification of Nonlinear Dynamics with Control (SINDYc)

Related

• Towards a Machine Learning-Based Approach to Predict Space Object Density Distributions
• The Capacity of Low Earth Orbit Computed using Source-sink Modeling
• Predicting RSO Populations Using a Neighbouring Orbits Technique
• Taxonomy for Resident Space Objects in LEO: A Deep Learning Approach
• Two-Line Element Estimation Using Machine Learning