*Please note that submissions are only considered from nationals of one of the following States: Austria, Belgium, Czechia, Denmark, Estonia, Finland, France, Germany, Greece, Hungary, Ireland, Italy, Luxembourg, the Netherlands, Norway, Poland, Portugal, Romania, Slovenia, Spain, Sweden, Switzerland, the United Kingdom, Canada, Latvia, Lithuania and Slovakia. Additional countries: Argentina, Australia, Bulgaria, Croatia, Cyprus, India, Japan, Malta, South Korea, United States of America.* The competition is based on the **European Space Agency Anomaly Detection Benchmark** (ESA-ADB) dataset, released in 2024 [1] and publicly available on Zenodo https://zenodo.org/records/12528696. In 2021, ESA's European Space Operations Centre initiated a project to outline a clear direction for AI implementation in mission operations. This initiative led to the creation of the [Artificial Intelligence for Automation (A2I) Roadmap](https://esoc.esa.int/a2i-roadmap-0) [2], developed by a team of over 70 specialists at ESOC, with support from an industry consortium. The roadmap underwent further validation and refinement in collaboration with the European space and IT sectors. Over the years, the A2I Roadmap evolved into the [AI and Data Foundation Project](https://esoc.esa.int/a2i-roadmap-0) that focuses on five key capabilities, one of which is ''Automated system health monitoring and control''. Anomaly detection plays a critical role in this capability, as early detection of anomalies can prevent potential dangers to the spacecraft. In this Challenge, your objective is to identify the anomalies experienced by one of ESA's missions using Artificial Intelligence. We hope that this unique Challenge that uses real world data will allow researchers and scientists from academia, research institutes, national and international space agencies, and industry to develop and benchmark novel approaches for anomaly detection for spacecraft telemetry data. ### Data More details in the [Data tab](https://www.kaggle.com/competitions/esa-adb-challenge/data) ### Code The baseline algorithms were trained and run using the dedicated ESA-ADB framework **https://github.com/kplabs-pl/ESA-ADB** which is a recommended environment to work on new models for the task. Besides, the competition offers [notebooks](https://www.kaggle.com/competitions/esa-adb-challenge/code) and [model files](https://www.kaggle.com/competitions/esa-adb-challenge/models) to reproduce results of baseline algorithms directly at Kaggle. All materials are released under a permissive [CC BY 3.0 IGO](https://creativecommons.org/licenses/by/3.0/igo/legalcode.en) license.