A Data-Driven Approach to Estimate LEO Orbit Capacity Models

2025-07-25

AI Summary

Accurately modeling and efficiently predicting the evolutionary dynamics of low Earth orbit (LEO) space objects—including operational satellites, defunct spacecraft, and debris—remains challenging due to high-dimensional nonlinearities and computational intractability. Method: This paper proposes a hybrid dynamic modeling framework integrating Sparse Identification of Nonlinear Dynamics (SINDy) with Long Short-Term Memory (LSTM) networks. Leveraging high-fidelity MOCAT-MC simulation data as ground truth, SINDy extracts interpretable, sparse differential equation structures, while LSTM captures complex nonlinear temporal dependencies across object populations. Contribution/Results: The resulting model achieves high predictive accuracy with significantly reduced computational complexity, enabling real-time LEO capacity assessment and long-term evolutionary trend analysis. It balances interpretability, efficiency, and scalability—offering a lightweight, deployable paradigm for operational space traffic management and sustainability analysis.

Technology Category

• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Estimating LEO orbit capacity using SINDy and LSTM models
• Predicting future satellite and debris propagation in LEO
• Creating a lightweight model from high-fidelity MOCAT-MC data

Innovation

• Uses SINDy algorithm for nonlinear dynamics
• Employs LSTM networks for accurate modeling
• Leverages MOCAT-MC data for fast forecasting