Conjunction Data Messages behave as a Poisson Process
Published in Workshop on AI for Spacecraft Longevity, 2021
Recommended citation: Francisco Caldas, Claudia Soares, Cláudia Nunes, Marta Guimarães, Mariana Filipe, Rodrigo Ventura, "Conjunction Data Messages behave as a Poisson Process." Workshop on AI for Spacecraft Longevity, 2021. https://ai4spacecraft.github.io/papers/AI4Spacecraft_paper_2.pdf
Abstract
Space debris is a major problem in space exploration. International bodies continuously monitor a large database of orbiting objects and emit warnings in the form of conjunction data messages. An important question for satellite operators is to estimate when fresh information will arrive so that they can react timely but sparingly with satellite maneuvers. We propose a statistical learning model of the message arrival process, allowing us to answer two important questions: (1) Will there be any new message in the next specified time interval? (2) When exactly and with what uncertainty will the next message arrive? The average prediction error for question (2) of our Bayesian Poisson process model is smaller than the baseline in more than 3 hours in a test set of 50k close encounter events.
BibTeX
@inproceedings{Poisson2021,
author = "Caldas, Francisco and Soares, Claudia and Nunes, Cl{\'a}udia and Guimar{\\textasciitilde a}es, Marta and Filipe, Mariana and Ventura, Rodrigo",
year = "2021",
maintitle = "International Joint Conference on Artificial Intelligence 2021",
booktitle = "Workshop on AI for Spacecraft Longevity",
title = "Conjunction Data Messages behave as a Poisson Process",
abstract = "Space debris is a major problem in space exploration. International bodies continuously monitor a large database of orbiting objects and emit warnings in the form of conjunction data messages. An important question for satellite operators is to estimate when fresh information will arrive so that they can react timely but sparingly with satellite maneuvers. We propose a statistical learning model of the message arrival process, allowing us to answer two important questions: (1) Will there be any new message in the next specified time interval? (2) When exactly and with what uncertainty will the next message arrive? The average prediction error for question (2) of our Bayesian Poisson process model is smaller than the baseline in more than 3 hours in a test set of 50k close encounter events.",
abstractsource = "https://ai4spacecraft.github.io/papers/AI4Spacecraft\_paper\_2.pdf",
abstractsourcelabel = "Published abstract source",
url = "https://ai4spacecraft.github.io/papers/AI4Spacecraft\_paper\_2.pdf"
}