GalaxAI: Machine learning toolbox for interpretable analysis of spacecraft telemetry data

TL;DR

GalaxAI is a machine learning toolbox designed for interpretable, end-to-end analysis of spacecraft telemetry data, aiding in spacecraft monitoring and operations with visualizations.

Contribution

It introduces a versatile, interpretable machine learning framework for analyzing heterogeneous spacecraft telemetry data, including visualization tools for mission specialists.

Findings

Effective analysis of Mars Express thermal power consumption

Successful prediction of INTEGRAL's Van Allen belt crossings

Demonstrated versatility across different spacecraft data

Abstract

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.