Machine learning methods for radiation belts profile predictions

Timothy Finn, Antigoni Georgiadou, Redouane Boumghar, Jose Antonio Martinez Heras

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

This paper presents the results of the potential application of machine learning techniques, specifically the Random Forest method, to spacecraft operations optimization. The test subject is ESAs INTEGRAL gamma ray observatory with the goal of demonstrating that AI techniques can reliably model the radiation environment of the satellite as it orbits the Earth and passes through the Earths trapped radiation zones in the Van Allen belts. The results clearly demonstrate that machine learning can approximate predictions of complex and dynamic radiation environment within +/-10% provided that an extensive data set is available and is adequately engineered. The consequences of such accurate data-driven predictions are that comprehensive physical models may be, under certain circumstances, an unnecessarily complicated solution to the optimization of scientific operations of Earth orbiting satellites.

Original languageEnglish
Title of host publication15th International Conference on Space Operations, 2018
PublisherAmerican Institute of Aeronautics and Astronautics Inc, AIAA
ISBN (Print)9781624105623
DOIs
StatePublished - 2018
Externally publishedYes
Event15th International Conference on Space Operations, SpaceOps 2018 - Marseille, France
Duration: May 28 2018Jun 1 2018

Publication series

Name15th International Conference on Space Operations, 2018

Conference

Conference15th International Conference on Space Operations, SpaceOps 2018
Country/TerritoryFrance
CityMarseille
Period05/28/1806/1/18

Funding

The authors would like to acknowledge the funding from the ESOC Intern Programme & DAAD grant with technical support from the Integral FCT (OPS-OAI) and Data Analytics Team for Operations (OPS-OSA)

Fingerprint

Dive into the research topics of 'Machine learning methods for radiation belts profile predictions'. Together they form a unique fingerprint.

Cite this