Orbit Propagation from Historical Data using Physics-informed Neural ODEs

With over 5000 satellites and 50000 debris currently in low-earth orbit, assessing collision risk between these entities is a problem of growing importance. With about 2 tracking points per day reported by Celestrak for each tracked entity, intermediate orbit states are “propagated” from these measurements using perturbation calculations of which SGP4 is the one in dominant use. Perturbation methods can accumulate errors of 10s of km over a week, and many attempts to use established machine learning techniques, time series analysis and deep neural networks (DNN) to predict based on past measurements have been made so far. We focus on the problem of predicting the orbit of an entity with higher accuracy over 7 days into the future in order to enable better collision risk assessment and ample time to make corrective maneuvers. Towards this, we show that training a physics informed Neural Ordinary Differential Equation (NeuraIODE) over a few measurements can help predict the near future with reduced propagation error compared to SGP4 in current use for this purpose, much further into the future than known ML based methods. We discuss training costs, and highlight challenges with scaling up this approach for the large number of debris and satellites in orbit today.