Research/ SPACE AI & AUTONOMY

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

Ana Kostovska, Matej Petković, Tomaž Stepišnik, Luke Lucas, Timothy Finn, José Martínez-Heras, Panče Panov, Sašo Džeroski, Alessandro Donati, Nikola Simidjievski, Dragi Kocev

SMC-IT/SCC 2021/Aug 3, 2021/ 9 citations

Space × AI

Technique

Learning-based MethodsarXiv: cs.LG · Guidance, Dynamics & ControlOpenAlex topic: Fault Detection and Control Systems

Indexed as

arXivcs.LGOpenAlexSpacecraft Design and Technology · Space Technology and Applications · Fault Detection and Control Systems

ar5iv HTML PDF arXiv:2108.01407 DOI Semantic Scholar OpenAlex

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.

Journal ref: 8th IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT 2021)

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

Ana Kostovska, Matej Petković, Tomaž Stepišnik, Luke Lucas, Timothy Finn, José Martínez-Heras, Panče Panov, Sašo Džeroski, Alessandro Donati, Nikola Simidjievski, Dragi Kocev

SMC-IT/SCC 2021/Aug 3, 2021/ 9 citations

Space × AI

Technique

Learning-based MethodsarXiv: cs.LG · Guidance, Dynamics & ControlOpenAlex topic: Fault Detection and Control Systems

Indexed as

arXivcs.LGOpenAlexSpacecraft Design and Technology · Space Technology and Applications · Fault Detection and Control Systems

ar5iv HTML PDF arXiv:2108.01407 DOI Semantic Scholar OpenAlex

Journal ref: 8th IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT 2021)

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

Related papers

Using Machine Learning to Automatically Detect Anomalous Spacecraft Behavior from Telemetry Data

Anomaly Detection in Spacecraft Telemetry: Forecasting vs. Classification

Explainable Deep Learning for Satellite Telemetry Anomaly Detection: A Systematic Literature Review

Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices

Machine Learning for Spacecraft Operations Support - The Mars Express Power Challenge

Towards autonomous spacecraft operations using machine learning

Telemetry Anomaly Detection System Using Machine Learning to Streamline Mission Operations

Machine learning-driven Anomaly Detection and Forecasting for Euclid Space Telescope Operations

SADDLE: Spacecraft Anomaly Detection using Deep Learning

Smart Fault Detection in Satellites: Review of Lightweight ML Models for Real-Time Anomaly Detection

More from SMC-IT/SCC

A Methodology for Evaluating and Analyzing FPGA-Accelerated, Deep-Learning Applications for Onboard Space Processing

Improving Dependability of Onboard Deep Learning with Resilient TensorFlow

Onboard Multi-Scale Tile Classification for Satellites and Other Spacecraft

R-Hope: Development Approach to Extreme Non-Volatile Memory Reuse Onboard the Curiosity Rover

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

Related papers

Using Machine Learning to Automatically Detect Anomalous Spacecraft Behavior from Telemetry Data

Anomaly Detection in Spacecraft Telemetry: Forecasting vs. Classification

Explainable Deep Learning for Satellite Telemetry Anomaly Detection: A Systematic Literature Review

Deep Learning-Based Anomaly Detection in Spacecraft Telemetry on Edge Devices

Machine Learning for Spacecraft Operations Support - The Mars Express Power Challenge

Towards autonomous spacecraft operations using machine learning

Telemetry Anomaly Detection System Using Machine Learning to Streamline Mission Operations

Machine learning-driven Anomaly Detection and Forecasting for Euclid Space Telescope Operations

SADDLE: Spacecraft Anomaly Detection using Deep Learning

Smart Fault Detection in Satellites: Review of Lightweight ML Models for Real-Time Anomaly Detection

More from SMC-IT/SCC

A Methodology for Evaluating and Analyzing FPGA-Accelerated, Deep-Learning Applications for Onboard Space Processing

Improving Dependability of Onboard Deep Learning with Resilient TensorFlow

Onboard Multi-Scale Tile Classification for Satellites and Other Spacecraft

R-Hope: Development Approach to Extreme Non-Volatile Memory Reuse Onboard the Curiosity Rover