A Data-Driven Approach to Estimate LEO Orbit Capacity Models
This provides a faster forecasting tool for space traffic management, but it is incremental as it builds on existing methods applied to new data.
The paper tackled the problem of predicting future satellite and debris propagation in Low Earth Orbit by developing a low-fidelity model using SINDy and LSTM, achieving accurate forecasting with reduced computational time compared to a high-fidelity model.
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.