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

被引:3
|
作者
Kostovska, Ana [1 ,2 ]
Petkovic, Matej [1 ,2 ]
Stepisnik, Tomaz [1 ,2 ]
Lucas, Luke [3 ]
Finn, Timothy [4 ]
Martinez-Heras, Jose [5 ]
Panov, Pance [1 ,2 ]
Dzeroski, Saso [2 ]
Donati, Alessandro [5 ]
Simidjievski, Nikola [1 ,2 ,6 ]
Kocev, Dragi [1 ,2 ]
机构
[1] Bias Variance Labs, Ljubljana, Slovenia
[2] Jozef Stefan Inst, Ljubljana, Slovenia
[3] LSE Space GmbH, Gilching, Germany
[4] European Space Agcy, ESOC, Darmstadt, Germany
[5] Solenix Engn, Darmstadt, Germany
[6] Univ Cambridge, Cambridge, England
来源
8TH IEEE INTERNATIONAL CONFERENCE ON SPACE MISSION CHALLENGES FOR INFORMATION TECHNOLOGY (SMC-IT 2021) | 2021年
关键词
machine learning; interpretable data analysis; Mars Express; INTEGRAL;
D O I
10.1109/SMC-IT51442.2021.00013
中图分类号
V [航空、航天];
学科分类号
08 ; 0825 ;
摘要
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.
引用
收藏
页码:44 / 52
页数:9
相关论文
共 50 条
  • [1] Machine Learning Methods for Spacecraft Telemetry Mining
    Ibrahim, Sara K.
    Ahmed, Ayman
    Zeidan, M. Amal Eldin
    Ziedan, Ibrahim E.
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2019, 55 (04) : 1816 - 1827
  • [2] Using Machine Learning to Automatically Detect Anomalous Spacecraft Behavior from Telemetry Data
    Naik, Kedar
    Holmgren, Andrew
    Kenworthy, John
    2020 IEEE AEROSPACE CONFERENCE (AEROCONF 2020), 2020,
  • [3] Correlation analysis on telemetry data of manned spacecraft
    Li Zhe
    An Meizhen
    Bai Linhou
    Zhu Enyong
    PROCEEDINGS OF THE 30TH CHINESE CONTROL AND DECISION CONFERENCE (2018 CCDC), 2018, : 377 - 380
  • [4] Hessian-based toolbox for reliable and interpretable machine learning in physics
    Dawid, Anna
    Huembeli, Patrick
    Tomza, Michal
    Lewenstein, Maciej
    Dauphin, Alexandre
    MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2022, 3 (01):
  • [5] Explainable artificial intelligence and interpretable machine learning for agricultural data analysis
    Ryo, Masahiro
    ARTIFICIAL INTELLIGENCE IN AGRICULTURE, 2022, 6 : 257 - 265
  • [6] Synthetic satellite telemetry data for machine learning
    Schefels, Clemens
    Schlag, Leonard
    Helmsauer, Kathrin
    CEAS SPACE JOURNAL, 2025,
  • [7] Explainable and interpretable machine learning and data mining
    Atzmueller, Martin
    Fuernkranz, Johannes
    Kliegr, Tomas
    Schmid, Ute
    DATA MINING AND KNOWLEDGE DISCOVERY, 2024, 38 (05) : 2571 - 2595
  • [8] Interpretable Machine Learning of Voluminous Scattering data
    Kim, E.
    ACTA CRYSTALLOGRAPHICA A-FOUNDATION AND ADVANCES, 2021, 77 : A146 - A146
  • [9] Modern Machine Learning Methods for Telemetry-Based Spacecraft Health Monitoring
    Mukhachev, P. A.
    Sadretdinov, T. R.
    Pritykin, D. A.
    Ivanov, A. B.
    Solov'ev, S., V
    AUTOMATION AND REMOTE CONTROL, 2021, 82 (08) : 1293 - 1320
  • [10] Modern Machine Learning Methods for Telemetry-Based Spacecraft Health Monitoring
    P. A. Mukhachev
    T. R. Sadretdinov
    D. A. Pritykin
    A. B. Ivanov
    S. V. Solov’ev
    Automation and Remote Control, 2021, 82 : 1293 - 1320