Spacecraft Collision Risk Assessment with Probabilistic Programming

Abstract

Over 34,000 objects bigger than 10 cm in length are known to orbit Earth. Amongthem, only a small percentage are active satellites, while the rest of the populationis made of dead satellites, rocket bodies, and debris that pose a collision threatto operational spacecraft. Furthermore, the predicted growth of the space sectorand the planned launch of megaconstellations will add even more complexity,therefore causing the collision risk and the burden on space operators to increase.Managing this complex framework with internationally agreed methods is pivotaland urgent. In this context, we build a novel physics-based probabilistic generativemodel for synthetically generating conjunction data messages, calibrated usingreal data. By conditioning on observations, we use the model to obtain posteriordistributions via Bayesian inference. We show that the probabilistic programmingapproach to conjunction assessment can help in making predictions and in findingthe parameters that explain the observed data in conjunction data messages, thusshedding more light on key variables and orbital characteristics that more likelylead to conjunction events. Moreover, our technique enables the generation ofphysically accurate synthetic datasets of collisions, answering a fundamental needof the space and machine learning communities working in this area.