{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/machine-learning-for-predicting-thermal-power","title":"Machine learning for predicting thermal power consumption of the Mars Express Spacecraft","arxiv_id":"1809.00542","date":"2018-09-03","proceeding":null,"authors":["Matej Petković","Redouane Boumghar","Martin Breskvar","Sašo Džeroski","Dragi Kocev","Jurica Levatić","Luke Lucas","Aljaž Osojnik","Bernard Ženko","Nikola Simidjievski"],"abstract":"The thermal subsystem of the Mars Express (MEX) spacecraft keeps the on-board\nequipment within its pre-defined operating temperatures range. To plan and\noptimize the scientific operations of MEX, its operators need to estimate in\nadvance, as accurately as possible, the power consumption of the thermal\nsubsystem. The remaining power can then be allocated for scientific purposes.\nWe present a machine learning pipeline for efficiently constructing accurate\npredictive models for predicting the power of the thermal subsystem on board\nMEX. In particular, we employ state-of-the-art feature engineering approaches\nfor transforming raw telemetry data, in turn used for constructing accurate\nmodels with different state-of-the-art machine learning methods. We show that\nthe proposed pipeline considerably improve our previous (competition-winning)\nwork in terms of time efficiency and predictive performance. Moreover, while\nachieving superior predictive performance, the constructed models also provide\nimportant insight into the spacecraft's behavior, allowing for further analyses\nand optimal planning of MEX's operation.","url_abs":"http://arxiv.org/abs/1809.00542v2","url_pdf":"http://arxiv.org/pdf/1809.00542v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"machine-learning-for-predicting-thermal-power","repo_url":"https://github.com/shinjjo/MarsExpress","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}