{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:55:49Z","timestamp":1775814949970,"version":"3.50.1"},"reference-count":59,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>The growing number of on-orbit spacecraft and the increasing volume of telemetry data have made intelligent anomaly detection in multi-channel telemetry essential for mission operations. Current spacecraft anomaly detection methods primarily rely on statistical models or time-series deep learning approaches, which often fail to explicitly model spatiotemporal dependencies across multiple telemetry channels. This shortcoming limits their ability to capture the dynamically evolving and intricately coupled relationships between variables. To overcome this limitation, a Progressive Spatiotemporal Graph (PSTG) model is proposed for anomaly detection in multi-channel spacecraft telemetry. PSTG employs a multi-scale patch embedding module to extract hierarchical semantic features from multi-channel time series, effectively reducing the dimensionality of the spatiotemporal graph. It constructs a sparse adjacency matrix using a multi-head attention mechanism that integrates intra-channel temporal dynamics, inter-channel spatial correlations, and cross-channel spatiotemporal interactions. An improved multi-head graph attention network then captures pairwise dependencies among nodes within the adjacency matrix. As a result, PSTG encodes rich spatiotemporal representations derived from intricate variable interactions, enabling accurate, real-time prediction of multi-channel telemetry. Furthermore, a dynamic thresholding mechanism is incorporated into PSTG to perform online anomaly detection based on prediction residuals. Extensive experiments on real-world spacecraft telemetry data collected over 84 months show that PSTG outperforms eleven state-of-the-art benchmark methods in almost all cases across multiple evaluation metrics. Finally, visualizations of the learned adjacency and attention matrices are presented to interpret the spatiotemporal modeling process, providing operators with actionable insights into the detected anomalies and facilitating root cause analysis.<\/jats:p>","DOI":"10.3390\/e28040426","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:08:12Z","timestamp":1775812092000},"page":"426","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Spatiotemporal Graph Modeling for Spacecraft Anomaly Detection"],"prefix":"10.3390","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1522-8193","authenticated-orcid":false,"given":"Zihan","family":"Chen","sequence":"first","affiliation":[{"name":"School of Advanced Manufacturing and Robotics, Peking University, Beijing 100871, China"},{"name":"Institute of Remote Sensing Satellite, China Academy of Space Technology, Beijing 100094, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zewen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Advanced Manufacturing and Robotics, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuge","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Advanced Manufacturing and Robotics, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Remote Sensing Satellite, China Academy of Space Technology, Beijing 100094, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hsi","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Advanced Manufacturing and Robotics, Peking University, Beijing 100871, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"108083","DOI":"10.1016\/j.engappai.2024.108083","article-title":"Explainable anomaly detection in spacecraft telemetry","volume":"133","author":"Santos","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.actaastro.2020.12.012","article-title":"Imbalanced satellite telemetry data anomaly detection model based on Bayesian LSTM","volume":"180","author":"Chen","year":"2021","journal-title":"Acta Astronaut."},{"key":"ref_3","unstructured":"Patgiri, R., Bandyopadhyay, S., Borah, M., and Thounaojam, D. (2019). NISAR Real Time Data Processing\u2014A Simple and Futuristic View. Big Data, Machine Learning, and Applications, Springer International Publishing."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1016\/j.actaastro.2023.09.032","article-title":"An encoder-decoder generative adversarial network-based anomaly detection approach for satellite telemetry data","volume":"213","author":"Xu","year":"2023","journal-title":"Acta Astronaut."},{"key":"ref_5","unstructured":"Boniol, P., Paparizzos, J., and Palpanas, T. (2023, January 28\u201331). New Trends in Time Series Anomaly Detection. Proceedings of the 26th International Conference on Extending Database Technology (EDBT 2023), Ioannina, Greece."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hundman, K., Constantinou, V., Laporte, C., Colwell, I., and Soderstrom, T. (2018, January 19\u201323). Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK.","DOI":"10.1145\/3219819.3219845"},{"key":"ref_7","unstructured":"Iverson, D.L. (2004, January 21\u201324). Inductive system health monitoring. Proceedings of the International Conference on Artificial Intelligence, Las Vegas, NV, USA."},{"key":"ref_8","first-page":"6","article-title":"Analysis of Space Shuttle main engine data using beacon-based exception analysis for multi-missions","volume":"Volume 6","author":"Park","year":"2002","journal-title":"Proceedings of the IEEE Aerospace Conference"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"464","DOI":"10.2514\/1.42783","article-title":"Unsupervised anomaly detection for liquid-fueled rocket propulsion health monitoring","volume":"6","author":"Schwabacher","year":"2009","journal-title":"J. Aerosp. Comput. Inf. Commun."},{"key":"ref_10","unstructured":"Martin, R.A. (2010). Evaluation of Anomaly Detection Capability for Ground-Based Pre-Launch Shuttle Operations. Aerospace Technologies Advancements, IntechOpen."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"117831","DOI":"10.1016\/j.eswa.2022.117831","article-title":"Exploiting Wavelet Recurrent Neural Networks for satellite telemetry data modeling, prediction and control","volume":"206","author":"Napoli","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3507221","DOI":"10.1109\/TIM.2022.3151930","article-title":"Satellite Telemetry Data Anomaly Detection Using Causal Network and Feature-Attention-Based LSTM","volume":"71","author":"Zeng","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3515209","DOI":"10.1109\/TIM.2021.3073442","article-title":"Telemetry Data-Based Spacecraft Anomaly Detection With Spatial\u2013Temporal Generative Adversarial Networks","volume":"70","author":"Yu","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"110791","DOI":"10.1016\/j.measurement.2022.110791","article-title":"Variational transformer-based anomaly detection approach for multivariate time series","volume":"191","author":"Wang","year":"2022","journal-title":"Measurement"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/j.inffus.2022.08.011","article-title":"MST-GAT: A multimodal spatial\u2013temporal graph attention network for time series anomaly detection","volume":"89","author":"Ding","year":"2023","journal-title":"Inf. Fusion"},{"key":"ref_16","unstructured":"Corradini, F., Gori, M., Lucheroni, C., Piangerelli, M., and Zannotti, M. (2024). A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"111928","DOI":"10.1016\/j.knosys.2024.111928","article-title":"SiET: Spatial information enhanced transformer for multivariate time series anomaly detection","volume":"296","author":"Xiong","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"9753","DOI":"10.1007\/s00521-023-08213-9","article-title":"Spacecraft anomaly detection with attention temporal convolution networks","volume":"35","author":"Liu","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4400","DOI":"10.1038\/s41598-023-31193-8","article-title":"Anomaly detection using spatial and temporal information in multivariate time series","volume":"13","author":"Tian","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"102357","DOI":"10.1016\/j.aei.2024.102357","article-title":"From anomaly detection to classification with graph attention and transformer for multivariate time series","volume":"60","author":"Wang","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez, M., Yue, Y., and Weber, R. (2017, January 5\u20138). Telemetry Anomaly Detection System Using Machine Learning to Streamline Mission Operations. Proceedings of the 2017 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Banff, AB, Canada.","DOI":"10.1109\/SMC-IT.2017.19"},{"key":"ref_22","unstructured":"Rolincik, M., Lauriente, M., Koons, H., and Gorney, D. (1991, January 24\u201327). An expert system for diagnosing environmentally induced spacecraft anomalies. Proceedings of the AIAA-91-1377, Huntsville, AL, USA."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Kolcio, K., and Fesq, L. (2016, January 5\u201312). Model-based off-nominal state isolation and detection system for autonomous fault management. Proceedings of the 2016 IEEE Aerospace Conference, Big Sky, MT, USA.","DOI":"10.1109\/AERO.2016.7500793"},{"key":"ref_24","unstructured":"Bernal-Mencia, P., Doerksen, K., and Yap, C. (2021, January 7\u201312). Machine Learning for Early Satellite Anomaly Detection. Proceedings of the Small Satellite Conference, Logan, UT, USA."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Baireddy, S., Desai, S., Foster, R., Chan, M., Comer, M., and Delp, E. (2023, January 4\u201311). Spacecraft Time-Series Online Anomaly Detection Using Deep Learning. Proceedings of the 2023 IEEE Aerospace Conference, Big Sky, MT, USA.","DOI":"10.1109\/AERO55745.2023.10115783"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1016\/j.actaastro.2022.06.026","article-title":"Evaluating algorithms for anomaly detection in satellite telemetry data","volume":"198","author":"Nalepa","year":"2022","journal-title":"Acta Astronaut."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, T., Comer, M., Delp, E., Desai, S., Foster, R., and Chan, M. (2022, January 5\u201312). A Matching-Based Method for Anomaly Verification in Spacecraft Telemetry. Proceedings of the 2022 IEEE Aerospace Conference, Big Sky, MT, USA.","DOI":"10.1109\/AERO53065.2022.9843771"},{"key":"ref_28","first-page":"2044","article-title":"An Anomaly Detection Method for Satellites Using Monte Carlo Dropout","volume":"59","author":"Zhu","year":"2023","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Caruso, A., Quarta, A.A., Mengali, G., and Bassetto, M. (2022). Optimal On-Orbit Inspection of Satellite Formation. Remote Sens., 14.","DOI":"10.3390\/rs14205192"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Gao, Y., Chen, G., Fu, W., Chen, X., Ma, L., Luo, T., and Xue, D. (2023). A Real-Time Linear Prediction Algorithm for Detecting Abnormal BDS-2\/BDS-3 Satellite Clock Offsets. Remote Sens., 15.","DOI":"10.3390\/rs15071831"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Pang, J., Liu, D., Peng, Y., and Peng, X. (2019). Collective Anomalies Detection for Sensing Series of Spacecraft Telemetry with the Fusion of Probability Prediction and Markov Chain Model. Sensors, 19.","DOI":"10.3390\/s19030722"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.jsse.2019.10.005","article-title":"Anomaly detection of satellite telemetry based on optimized extreme learning machine","volume":"6","author":"Abdelghafar","year":"2019","journal-title":"J. Space Saf. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Sakurada, M., and Yairi, T. (2014, January 2). Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction. Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, Gold Coast, QLD, Australia.","DOI":"10.1145\/2689746.2689747"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1109\/TSMC.2014.2323212","article-title":"Dynamic Bayesian Networks for Fault Detection, Identification, and Recovery in Autonomous Spacecraft","volume":"45","author":"Portinale","year":"2015","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wu, Y., Yang, Q., and Zhang, J. (2021, January 17\u201320). Anomaly Detection of Spacecraft Telemetry Data Using Temporal Convolution Network. Proceedings of the 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), Glasgow, UK.","DOI":"10.1109\/I2MTC50364.2021.9459840"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., and Pei, D. (2019, January 4\u20138). Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330672"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Tariq, S., Lee, S., Shin, Y., Lee, M., Jung, O., Chung, D., and Woo, S. (2019, January 4\u20138). Detecting Anomalies in Space using Multivariate Convolutional LSTM with Mixtures of Probabilistic PCA. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330776"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Lakey, D., and Schlippe, T. (2024, January 2\u20139). A Comparison of Deep Learning Architectures for Spacecraft Anomaly Detection. Proceedings of the 2024 IEEE Aerospace Conference, Big Sky, MT, USA.","DOI":"10.1109\/AERO58975.2024.10521015"},{"key":"ref_39","unstructured":"Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., and Long, M. (2024, January 7\u201311). iTransformer: Inverted Transformers Are Effective for Time Series Forecasting. Proceedings of the International Conference on Learning Representations (ICLR), Vienna, Austria."},{"key":"ref_40","unstructured":"Nie, Y., Nguyen, N.H., Sinthong, P., and Kalagnanam, J. (2023, January 1\u20135). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. Proceedings of the The Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_41","unstructured":"Chen, S.A., Li, C.L., Yoder, N., Arik, S.O., and Pfister, T. (2023). TSMixer: An All-MLP Architecture for Time Series Forecasting. Trans. Mach. Learn. Res."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Murad, M.M.N., Aktukmak, M., and Yilmaz, Y. (2025, January 25\u201327). WPMixer: Efficient Multi-Resolution Mixing for Long-Term Time Series Forecasting. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v39i18.34156"},{"key":"ref_43","unstructured":"Zhang, Y., and Yan, J. (2023, January 1\u20135). Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting. Proceedings of the International Conference on Learning Representations (ICLR), Kigali, Rwanda."},{"key":"ref_44","unstructured":"Yi, K., Zhang, Q., Fan, W., Wang, S., Wang, P., He, H., Lian, D., An, N., Cao, L., and Niu, Z. (2023, January 10\u201316). Frequency-domain MLPs are More Effective Learners in Time Series Forecasting. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA."},{"key":"ref_45","unstructured":"Wu, X., Qiu, X., Cheng, H., Li, Z., Hu, J., Guo, C., and Yang, B. (2025, January 9\u201315). Enhancing Time Series Forecasting through Selective Representation Spaces: A Patch Perspective. Proceedings of the NeurIPS, Vancouver, BC, Canada."},{"key":"ref_46","unstructured":"Zeng, A., Chen, M., Zhang, L., and Xu, Q. (2023, January 7\u201314). Are Transformers Effective for Time Series Forecasting?. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"102460","DOI":"10.1016\/j.aei.2024.102460","article-title":"Fault diagnosis of gearbox driven by vibration response mechanism and enhanced unsupervised domain adaptation","volume":"61","author":"Jiang","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"ref_48","first-page":"76","article-title":"Partial domain adaptation fault diagnosis method based on deep residual shrinkage network","volume":"12","author":"Liu","year":"2025","journal-title":"J. Comput. Des. Eng."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Bennetot","year":"2020","journal-title":"Inf. Fusion"},{"key":"ref_50","unstructured":"Das, A., and Rad, P. (2020). Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey. arXiv."},{"key":"ref_51","first-page":"3523913","article-title":"A Multivariate Anomaly Detector for Satellite Telemetry Data Using Temporal Attention-Based LSTM Autoencoder","volume":"72","author":"Xu","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"3891","DOI":"10.1109\/TII.2023.3314852","article-title":"MAG: A Novel Approach for Effective Anomaly Detection in Spacecraft Telemetry Data","volume":"20","author":"Yu","year":"2024","journal-title":"IEEE Trans. Ind. Informatics"},{"key":"ref_53","unstructured":"Hu, Y., Zhang, G., Liu, P., Lan, D., Li, N., Cheng, D., Dai, T., Xia, S.T., and Pan, S. (2025). TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting. arXiv."},{"key":"ref_54","unstructured":"Loshchilov, I., and Hutter, F. (2019, January 6\u20139). Decoupled Weight Decay Regularization. Proceedings of the International Conference on Learning Representations (ICLR), New Orleans, LA, USA."},{"key":"ref_55","unstructured":"Loshchilov, I., and Hutter, F. (2017, January 24\u201326). SGDR: Stochastic Gradient Descent with Warm Restarts. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"3678","DOI":"10.14778\/3554821.3554873","article-title":"TimeEval: A benchmarking toolkit for time series anomaly detection algorithms","volume":"15","author":"Wenig","year":"2022","journal-title":"Proc. VLDB Endow."},{"key":"ref_57","unstructured":"Kotowski, K., Haskamp, C., Andrzejewski, J., Ruszczak, B., Nalepa, J., Lakey, D., Collins, P., Kolmas, A., Bartesaghi, M., and Martinez-Heras, J. (2024). European Space Agency Benchmark for Anomaly Detection in Satellite Telemetry. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"124922","DOI":"10.1016\/j.eswa.2024.124922","article-title":"Unsupervised anomaly detection in time-series: An extensive evaluation and analysis of state-of-the-art methods","volume":"256","author":"Mejri","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Xu, H., Chen, W., Zhao, N., Li, Z., Bu, J., Li, Z., Liu, Y., Zhao, Y., Pei, D., and Feng, Y. (2018). Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications. Proceedings of the 2018 World Wide Web Conference, International World Wide Web Conferences Steering Committee.","DOI":"10.1145\/3178876.3185996"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/4\/426\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T09:11:20Z","timestamp":1775812280000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/4\/426"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,10]]},"references-count":59,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,4]]}},"alternative-id":["e28040426"],"URL":"https:\/\/doi.org\/10.3390\/e28040426","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,10]]}}}