Abstract The continuing Machine Learning (ML) revolution indubitably has had a significant positive impact on the analysis of downlinked satellite data. Other aspects of the Earth Observation industry, despite being less susceptible to widespread application of Machine Learning, are also following this trend. These applications, actual use cases, possible prospects and difficulties, as well as anticipated research gaps, are the focus of this review of Machine Learning applied to Earth Observation Operations. A wide range of topics are covered, including mission planning, fault diagnosis, fault prognosis and fault repair, optimization of telecommunications, enhanced GNC, on-board image processing, and the use of Machine Learning models on platforms with constrained compute and power capabilities, as well as recommendations in the respective areas of research. The review tackles all on-board and off-board applications of machine learning to Earth Observation with one notable exception: it omits all post-processing of payload data on the ground, a topic that has been studied extensively by past authors. In addition, this review article discusses the standardization of Machine Learning (i.e., Guidelines and Roadmaps), as well as the challenges and recommendations in Earth Observation operations for the purpose of building better space missions.
A critical review on the state-of-the-art and future prospects of machine learning for Earth observation operations
Advances in Space Research ; 71 , 12 ; 4959-4986
2023-02-13
28 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Artificial Intelligence , Astrionics , Earth Observation , Edge Computing , Machine Learning , Neural Network , Remote Sensing , State-of-the-art , <bold>AI</bold> , ML , DL , Deep Learning , FDIR , Fault Detection Isolation and Recovery , <bold>GNC</bold> , Guidance Navigation and Control , NN , CNN , Convolutional Neural Network , DNN , Deep Neural Network , ANN , Artificial Neural Network , BNN , Binarized Neural Network , BN , Bayesian Network , DBN , Dynamic Bayesian Network , NASA , National Aeronautics and Space Administration , ESA , European Space Agency , OBC , On-Board Computer , EO , RDF , Random Decision Forest , BT , Bayesian Thresholding , SVM , Support Vector Machine , COTS , Commercial off-the-shelf , SwaP , Size Weight and Power , LIDAR , Light Detection and Ranging , SoC , System on a Chip , FP , False Positives , CCSDS , Consultative Committee for Space Data Systems , GNSS , Global Navigation Satellite System , GPS , Global Positioning System , PI , Proportional - Integral , PID , Proportional - Integral - Derivative , AODS , Attitude Orbital Determination System , RL , Reinforcement Learning , EKF , Extended Kalman Filter , RF , Random Forest , AOCS , Attitude and Orbit Control System , K-NN , k-Nearest Neighbour , SOM , Self-Organizing Map , OOS , On Orbit Servicing , ARPHA , Anomaly Resolution and Prognostic Health Management for Autonomy , DBSCAN , Density-Based Spatial Clustering of Applications with Noise , EPS , Electrical Power System , SSHM , Software and Sensor Health Management , RDA , Regularized Discriminant Analysis , AROW , Adaptive Regularization of Weight Vector , SCW , Soft Confidence-Weighted , CNES , Centre national d'études spatiales (The National Centre for Space Studies) , ESOC , European Space Operations Centre , RBF , Radial Basis Function , DLR , Deutsches Zentrum für Luft- und Raumfahrt (German Aerospace Center) , OC-SVM , One-Class Support Vector Machine , NHERD , Normal Gaussian Herding , THEMIS , Thermal EMission Imaging System , IPEX , Intelligent Payload EXperiment , <bold>HyspIRI</bold> , Hyperspectral Infrared Imager , <bold>MODIS</bold> , Moderate-Resolution Imaging Spectroradiometer , <bold>PSNR</bold> , Peak Signal to Noise Ratio , <bold>SSIM</bold> , Structural Similarity Index , FPGA , Field Programmable Gate Array , CALIC , Context-Based, Adaptive, Lossless Image Codec , IWT , Integral Wavelet Transform , PH , Peano-Hilbert , LVQ , Learning Vector Quantization , TF , TensorFlow , SAR , Synthetic Aperture Radar , ROEWA , Ratio of Exponential Weighted Average , JPEG , Joint Photographic Experts Group , <bold>STP-H5-CSP</bold> , Space Test Program-Houston-5-Cubesat Service protocol , NAS , Neural Architecture Structure , CPU , Central Processing Unit , GPU , Graphics Processing Unit , VPU , Visual Processing Unit , TPU , Time Processing Unit , TTQ , Trained Ternary Quantization , RT , Radiation Tolerant , MNAS , Mobile Neural Architecture Search , KT , Knowledge Transfer , K<inf>D</inf> , Knowledge Distillation , CSP , Cubesat Service Protocol , SBC , SpaceBorne Computer , MNIST , Modified National Institute of Standards and Technology database , NISSTC , National Information Security Standardization Technical Committee , DIN , Deutsches Institut für Normung (German Institute of Standardization) , DKE , Deutschen Kommission Elektrotechnik Elektronik Informationstechnik (German Commission for Electrical, Electronic and Information Technologies) , EU , European Union , EC , European Commission , SMEs , Small and Medium Enterprises , DEEL , DEpendable and Expandable Learning , EOSDIS , Earth Observation Systems’ Data Information Systems , SGACm , Space Generation Advisory Council , SSPG , Small Satellite Project Group , DRL , Deep Reinforcement Learning , GIS , Geographic Information Systems , XAI , Explainable AI
MACHINE LEARNING IN EARTH OBSERVATION OPERATIONS: A REVIEW
TIBKAT | 2022
|The operations security concept for future ESA earth observation missions
Tema Archiv | 2008
|The Operations Security Concept for Future ESA Earth Observation Missions
British Library Conference Proceedings | 2008
|