We present GalaxAI - a versatile machine learning toolbox for efficient and interpretable end-to-end analysis of spacecraft telemetry data. GalaxAI employs various machine learning algorithms for multivariate time series analyses, classification, regression and structured output prediction, capable of handling high-throughput heterogeneous data. These methods allow for the construction of robust and accurate predictive models, that are in turn applied to different tasks of spacecraft monitoring and operations planning. More importantly, besides the accurate building of models, GalaxAI implements a visualisation layer, providing mission specialists and operators with a full, detailed and interpretable view of the data analysis process. We show the utility and versatility of GalaxAI on two use-cases concerning two different spacecraft: i) analysis and planning of Mars Express thermal power consumption and ii) predicting of INTEGRAL's crossings through Van Allen belts.
@article{arxiv.2108.01407,
title = {GalaxAI: Machine learning toolbox for interpretable analysis of spacecraft telemetry data},
author = {Ana Kostovska and Matej Petković and Tomaž Stepišnik and Luke Lucas and Timothy Finn and José Martínez-Heras and Panče Panov and Sašo Džeroski and Alessandro Donati and Nikola Simidjievski and Dragi Kocev},
journal= {arXiv preprint arXiv:2108.01407},
year = {2021}
}