{ "fetched_at": "2026-10-19T08:54:16Z", "source_url": "https://www.kaggle.com/competitions/esa-adb-challenge/data", "pages": [ { "name": "rules", "content": "The following Competition Rules derive from ESA's Advanced Concepts Team and their [Kelvins](https://kelvins.esa.int/about/) platform. In the event of any inconsistency or conflict, these Competition Rules shall take precedence over the General Competition Rules described in Sec. B below.\n\n### Code of Honor\n\nThe following general rules apply to all users of the website and participants in the competitions. Not following these rules can and will have consequences such as disqualification from competitions, banning, and deactivation of accounts.\n\n### Single Account\n\nOnly one single account per user is permitted. You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n### Cheating\n\nAny form of cheating competition rules is considered a threat and will be treated as such.\n\n### Etiquette\n\nAll users shall respect their fellow competitors and not engange in any activity leading to any form of harm to others.\n\n### Eligibility\n\n\"Spacecraft Anomaly Challenge on ESA dataset\" competition is open to everybody, including space experts, data-mining experts and citizen scientists. However, the following restrictions apply.\n\nSubmissions 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 and Canada, Latvia, Lithuania and Slovakia. Additional countries: Argentina, Australia, Bulgaria, Croatia, Cyprus, India, Japan, Malta, South Korea, United States of America.\n\n### Winner\n\nThe final ranking and the winner is determined after the deadline, based on the private leaderboard.\n\nThe final decision on the winner(s) is subject to whether the participants conformed to the rules as checked by the Competition Organisers and Sponsor.\n \nThis competition does not count towards Kaggle ranking points or medals.\n\n### License\n\nBy submitting, the authors grant to the organizers a license to use the submission files for the purpose of verifying and publishing the challenge results.\n\n### Submission\n\nBefore the competition deadline, solutions, notebooks, code snippets may only be shared publicly. Private sharing between teams is thus not allowed.\n\nThe submission limit is 2 submissions within 24 hours per team. The only exception is that the limit will be increased to 10 submissions for the duration of the hackathon on 13th March 2025.\n\n### Teams \n\nThe limit on the number of members in a team is 3.\n\nThe daily submission limit is based on teams, not on users. Thus, each team will have 2 submission per 24h interval.\n \n### Competition Timeline\n \nCompetition Timeline dates (including Entry Deadline, Final Submission Deadline, Start Date, and Team Merger Deadline, as applicable) are reflected on the competition’s [Overview > Timeline](https://www.kaggle.com/c/esa-adb-challenge/overview/timeline) page.\n \n### Competition-specific terms\n \n**Competition title**: Spacecraft Anomaly Challenge on ESA dataset\n \n**Competition sponsor**: European Space Agency\n \n**Competition website**: https://www.kaggle.com/c/esa-adb-challenge/\n\n**Data licence type**: Released under [CC BY 3.0 IGO ](https://creativecommons.org/licenses/by/3.0/igo/legalcode.en)\n\n**Entry in this competition constitutes your acceptance of these official competition rules.**\n \n\n### B. General Competition Rules\n#### **1. Binding agreement** \n \nTo enter the Competition, you must agree to these Official Competition Rules, which incorporate by reference the provisions and content of the Competition Website and any Specific Competition Rules above (collectively, the \"Rules\"). Please read these Rules carefully before entry to ensure you understand and agree. You further agree that submission of an entry in the Competition constitutes agreement to these Rules. You may not submit an entry to the Competition and are not eligible to receive the prizes associated with this Competition (“Prizes”) unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition.\n \n#### **2. Eligibility** \n \nA. To be eligible to enter the Competition, you must be a registered account holder at Kaggle.com.\n \nB. Unless otherwise stated in the Specific Competition Rules above or prohibited by internal policies of the Competition Entities, employees, interns, contractors, officers and directors of Competition Entities may enter and participate in the Competition, but are not eligible to win any Prizes. \"Competition Entities\" means the Competition Sponsor, Kaggle Inc., and their respective parent companies, subsidiaries and affiliates. If you are such a participant from a Competition Entity, you are subject to all applicable internal policies of your employer with respect to your participation.\n \n#### **3. Sponsor and hosting platform** \n \nThe Competition is sponsored by Competition Sponsor named above. The Competition is hosted on behalf of Competition Sponsor by Kaggle Inc. (\"Kaggle\"). Kaggle is an independent contractor of Competition Sponsor, and is not a party to this or any agreement between you and Competition Sponsor. You understand that Kaggle has no responsibility with respect to selecting the potential Competition winner(s) or awarding any Prizes. Kaggle will perform certain administrative functions relating to hosting the Competition, and you agree to abide by the provisions relating to Kaggle under these Rules. As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at [www.kaggle.com/terms][2] in addition to these Rules.\n \n#### **4. Competition period** \n \nFor the purposes of Prizes, the Competition will run from the Start Date and time to the End Date and time (such duration the “Competition Period”). The Competition Timeline is subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. *YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.* \n \n#### **5. Competition entry** \n \nNO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website prior to the Entry Deadline, and follow the instructions for developing and entering your Submission through the Competition Website. Your Submissions must be made in the manner and format, and in compliance with all other requirements, stated on the Competition Website (the \"Requirements\"). Submissions must be received before any Submission deadlines stated on the Competition Website. Submissions not received by the stated deadlines will not be eligible to receive a Prize.\n \nSubmissions may not use or incorporate information from hand labeling or human prediction of the validation dataset or test data records.\n \nSubmissions are void if they are in whole or part illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. Competition Sponsor reserves the right to disqualify any entrant who does not follow these Rules, including making a Submission that does not meet the Requirements. \n \n#### **6. Individuals and teams** \n \nA. *Individual Account*. You may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website. \n \nB. *Teams*. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a team (a \"Team\"); however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size stated on the Competition Website.\n \nC. *Team Merger*. Teams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules. \n \n#### **7. Competition data** \n \n\"Competition Data\" means the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to participants. \n \nA. *Data Access and Use*.\n*Competition Use and Commercial*: You may access and use the Competition Data for any purpose, whether commercial or non-commercial, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.\n \nB. *Data Security*. You agree to use reasonable and suitable measures to prevent persons who have not formally agreed to these Rules from gaining access to the Competition Data. You agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Competition Data to any party not participating in the Competition. You agree to notify Kaggle immediately upon learning of any possible unauthorized transmission of or unauthorized access to the Competition Data and agree to work with Kaggle to rectify any unauthorized transmission or access.\n \nC. *External Data*. You may use data other than the Competition Data (“External Data”) to develop and test your Submissions. However, you will ensure the External Data is publicly available to use by all participants of the Competition for purposes of the competition at no cost to the other participants. The ability to use External Data under this Section 7.C (External Data) does not limit your other obligations under these Competition Rules, including but not limited to Section 11 (Winners Obligations). \n \n#### **8. Submission code requirements**\n \nA. *Private Code Sharing*. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition Period, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data or other source or executable code relevant to the Competition (“Competition Code”). This prohibition includes sharing Competition Code between separate Teams, unless a Team merger occurs. Any such sharing of Competition Code is a breach of these Competition Rules and may result in disqualification.\n \nB. *Public Code Sharing*. You are permitted to publicly share Competition Code, provided that such public sharing does not violate the intellectual property rights of any third party. If you do choose to share Competition Code or other such code, you are required to share it on Kaggle.com on the discussion forum or kernels associated specifically with the Competition for the benefit of all competitors. By so sharing, you are deemed to have licensed the shared code under an Open Source Initiative-approved license (see [www.opensource.org][2]) that in no event limits commercial use of such Competition Code or model containing or depending on such Competition Code.\n \nC. *Use of Open Source*. Unless otherwise stated in the Specific Competition Rules above, if open source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see [www.opensource.org][2]) that in no event limits commercial use of such code or model containing or depending on such code.\n \n#### **9. Determining leaderboard** \n \nEach Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's public leaderboard. The public leaderboard will be based on the public test set and the private leaderboard will be based on the private test set.\n \nIn the event of a tie, the Submission that was entered first to the Competition will be ranked higher.\n \n#### **10. Disqualification**\n \nCompetition Sponsor reserves the right to disqualify any participant from the Competition if the Competition Sponsor reasonably believes that the participant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other participants, Competition Sponsor or Kaggle.\n \nA disqualified participant may be removed from the Competition leaderboard, at Kaggle's sole discretion.\n \nThe final leaderboard list will be publicly displayed at Kaggle.com. Determinations of Competition Sponsor are final and binding.\n \n#### **11. General Conditions** \n \nAll federal, state, provincial and local laws and regulations apply. \n \n#### **12. Privacy**\n \nYou acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to, name, mailing address, phone number, and email address (“Personal Information”). Kaggle acts as an independent controller with regard to its collection, storage, sharing, and other use of this Personal Information, and will use this Personal Information in accordance with its Privacy Policy <[www.kaggle.com/privacy][3]>, including for administering the Competition. As a Kaggle.com account holder, you have the right to request access to, review, rectification, portability or deletion of any personal data held by Kaggle about you by logging into your account and/or contacting Kaggle Support at <[www.kaggle.com/contact][4]>.\n \nAs part of Competition Sponsor performing this contract between you and the Competition Sponsor, Kaggle will transfer your Personal Information to Competition Sponsor, which acts as an independent controller with regard to this Personal Information. As a controller of such Personal Information, Competition Sponsor agrees to comply with all U.S. and foreign data protection obligations with regard to your Personal Information. Kaggle will transfer your Personal Information to Competition Sponsor in the country specified in the Competition Sponsor Address listed above, which may be a country outside the country of your residence. Such country may not have privacy laws and regulations similar to those of the country of your residence.\n \n#### **13. Warranty, Indemnity, and Release** \n \nYou warrant that your Submission is your own original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses. You agree not to make any Submission that: (i) infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; or (ii) otherwise violates any applicable U.S. or foreign state or federal law.\n \nTo the maximum extent permitted by law, you indemnify and agree to keep indemnified Competition Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any of your acts, defaults or omissions and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the Competition Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules or any applicable U.S. or foreign state or federal law; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the Competition; and (e) your acceptance, possession, misuse or use of any Prize, or your participation in the Competition and any Competition-related activity.\n \nYou hereby release Competition Entities from any liability associated with: (a) any malfunction or other problem with the Competition Website; (b) any error in the collection, processing, or retention of any Submission; or (c) any typographical or other error in the printing, offering or announcement of any Prize or winners.\n \n#### **14. Internet** \n \nCompetition Entities are not responsible for any malfunction of the Competition Website or any late, lost, damaged, misdirected, incomplete, illegible, undeliverable, or destroyed Submissions or entry materials due to system errors, failed, incomplete or garbled computer or other telecommunication transmission malfunctions, hardware or software failures of any kind, lost or unavailable network connections, typographical or system/human errors and failures, technical malfunction(s) of any telephone network or lines, cable connections, satellite transmissions, servers or providers, or computer equipment, traffic congestion on the Internet or at the Competition Website, or any combination thereof, which may limit a participant’s ability to participate.\n \n#### **15. Right to cancel, modify, or disqualify**\n \nIf for any reason the Competition is not capable of running as planned, including infection by computer virus, bugs, tampering, unauthorized intervention, fraud, technical failures, or any other causes which corrupt or affect the administration, security, fairness, integrity, or proper conduct of the Competition, Competition Sponsor reserves the right to cancel, terminate, modify or suspend the Competition. Competition Sponsor further reserves the right to disqualify any participant who tampers with the submission process or any other part of the Competition or Competition Website. Any attempt by a participant to deliberately damage any website, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws. Should such an attempt be made, Competition Sponsor and Kaggle each reserves the right to seek damages from any such participant to the fullest extent of the applicable law.\n \n#### **16. Not an offer or contract of employment**\n \nUnder no circumstances will the entry of a Submission, the awarding of a Prize, or anything in these Rules be construed as an offer or contract of employment with Competition Sponsor or any of the Competition Entities. You acknowledge that you have submitted your Submission voluntarily and not in confidence or in trust. You acknowledge that no confidential, fiduciary, agency, employment or other similar relationship is created between you and Competition Sponsor or any of the Competition Entities by your acceptance of these Rules or your entry of your Submission.\n \n [1]: http://www.kaggle.com/terms\n [2]: http://www.opensource.org\n [3]: http://www.kaggle.com/privacy\n [4]: http://www.kaggle.com/contact\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Summary", "content": "Your objective is to design an algorithm to detect anomalies in a multivariate time series setting. The data used in the Challenge is real spacecraft data coming from one of the [European Space Agency's missions](https://www.esa.int/). \n\nYou have access to a large set of historical data, baseline algorithms, and detailed descriptions.\n\nThe Spacecraft Anomaly Challenge on ESA dataset starts now! 🚀 ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "*Please note that submissions are only considered from nationals of one of the following States:\nAustria, 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. \nAdditional countries: Argentina, Australia, Bulgaria, Croatia, Cyprus, India, Japan, Malta, South Korea, United States of America.*\n\nThe 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. \n\nIn 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.\n\nOver 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. \n\nIn 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.\n\n\n\n### Data\nMore details in the [Data tab](https://www.kaggle.com/competitions/esa-adb-challenge/data)\n\n\n### Code\nThe 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.\n\nAll materials are released under a permissive [CC BY 3.0 IGO](https://creativecommons.org/licenses/by/3.0/igo/legalcode.en) license.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Awards 🏆", "content": "\n\n\n\nThis Challenge is a qualifier to the final validation phase where algorithms will be tested on a hidden test set. Best teams will be invited to this 2nd phase that will determine the overall winner(s) eligible for prizes. The full list of prizes currently includes:\n- **1-month remote access to the Leopard processing unit by KP Labs** via the brand-new [Smart Mission Lab platform](https://sml.kplabs.space/) to benchmark your models on flight-proven hardware with KP Labs’ expert support (+ an option to widely promote the results through KP Labs’ social media) - estimated value €5,000.\n- Gifts from ESA and KP Labs\n\nThe award ceremony and best teams presentations will take place during the [**ESA AI STAR 2025**](https://atpi.eventsair.com/ai-star-2025). Winner(s) will be invited as co-authors of a joint paper summarizing the Challenge. \n\nAll participants are invited to submit regular or short papers describing their algorithms to the dedicated session at the [ML4ITS workshop](https://ml4its.github.io/ml4its2025) of the [**ECML PKDD 2025 conference**](https://ecmlpkdd.org/2025/submissions-workshop-track/). The foreseen deadline for submissions is **~~14 June 2025~~** **21 June 2025** - nine days after competition ends, so participants are expected to work on the paper already before the Challenge finishes. The final Challenge results should be included in the paper. **Submitting at least a short paper or a presentation to the workshop is necessary to be eligible for the II phase and the final prize! The novelty is not essential and you do not need to present or participate at the conference to win the competition (however, in this case, your paper will not be included in the official conference proceedings).**\n\nIntermediate results will be presented at [**SpaceOps 2025 conference**](https://www.spaceops2025.org/) 26-30 May 2025. \n\n## Hackathon (closed)\nThe Challenge started with a hackathon on 13 March 2025 during the [AI Symposium on Ground Segment Engineering, Operations, and Space Safety](https://commercialisation.esa.int/event/ai-symposium-on-ground-segment-engineering-operations-and-space-safety/) at ESA's European Space Operations Centre. The winner was **Simon Schaefer** (SHS Telespazio team, user: [shsshs](https://www.kaggle.com/shsshs))", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "## TLDR\n\nThe dataset represents several years of real sensor measurements collected from a large spacecraft operated by the European Space Agency. It is a single long continuous multivariate time series data of 87 mission-critical parameters. The dataset was carefully annotated for anomalies and rare events based on the original flight control reports and several iterations of manual and algorithm-driven refinement of labels [1]. \n\nYour task is to find all anomalous time points in the test set (binary decision, 0 - normal point, 1 - anomalous point, see the `sample_submission.parquet` file) while minimizing the number of false alarms.\n\n## List of files\n\n* **train.parquet** - the training set; 14 years of ESA-Mission1 data from the [ESA-AD dataset](https://zenodo.org/records/12528696) with annotated anomalous time points (`is_anomaly` column)\n* **test.parquet** - the test set; a never before published 6-months long fragment of ESA-Mission1 data\n* **target_channels.csv** - a list of names of 58 channels monitored for anomalies (other 29 channels are just external auxiliary variables)\n* **sample_submission.parquet** - a sample submission file in the correct format\n\n## More details\n\n\n### Preprocessing\n\nThe dataset is a simplified and preprocessed version of the raw ESA-Mission1 data from the ESA-AD dataset publicly available on [Zenodo](https://zenodo.org/records/12528696). The preprocessing is described together with all other dataset details in the ESA-ADB paper [2] and the preprocessing script is available on the official ESA-ADB GitHub repository [here](https://github.com/kplabs-pl/ESA-ADB/blob/main/notebooks/data-prep/Mission1_semisupervised_prep_from_raw.py). For simplicity, timestamps have been replaced with integer index and annotations have been aggregated across all channels into the single `is_anomaly` column, such that `1` is marked for a time point if at least one channel is affected by an anomaly or a rare event. **Participants are welcome to propose their own preprocessing and annotations aggregation methods**, however, the test set is already preprocessed and aggregated using our described methods.\n\n### Channels \n\nThe dataset contains 87 channels, among which 58 are target channels (monitored for anomalies) listed in the `target_channels.csv` file, 18 channels are auxiliary environmental variables (not monitored for anomalies), and 11 are telecommands (binary control commands sent by operators; marked with the `telecommand_` prefix). The subset of 6 channels 41-46 is recommended as a good starting point for developing and testing algorithms before applying them to the full set. \n\nThese 87 channels are just a small subset of real spacecraft telemetry with thousands of channels. However, this subset was designed by spacecraft operators to be a self-contained representation of the most important mission-critical and auxiliary variables necessary to identify anomalies.\n\n### Events to detect\n\nESA-ADB dataset contains three categories of events: anomalies, nominal rare events, and communication gaps. The test set does not contain communication gaps. Your task is to detect both anomalies and rare nominal events.\n\n### References\n\n[1] K. Kotowski, C. Haskamp, B. Ruszczak, J. Andrzejewski, and J. Nalepa, “Annotating Large Satellite Telemetry Dataset For ESA International AI Anomaly Detection Benchmark,” in Proceedings of the 2023 conference on Big Data from Space, Vienna: Publications Office of the European Union, Nov. 2023, pp. 341–344. doi: [10.2760/46796](https://dx.doi.org/10.2760/46796).\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation metric ✅", "content": "Submissions are evaluated using the **corrected event-wise F0.5 score for anomaly detection in time series** introduced by Sehili & Zhang [3] and adopted as a primary metric in the ESA-ADB benchmark [1]. The metric is a harmonic mean of corrected event-wise precision and event-wise recall, with precision having 2 times higher importance than recall:\n\n$$F_{0.5}=\\frac{(1 + 0.5^2) * Precision_{e_{corr}} * Recall_e}{0.5^2 * Precision_{e_{corr}} + Recall_e}$$\n\nEvent-wise precision and recall treat each continuous anomalous segment as a single event, regardless of its size. A segment is considered an event-wise true positive *`TPe`* if at least one of its samples is detected; otherwise, it is an event-wise false negative *`FNe`*. Any continuous detection that does not overlap with an anomalous segment is counted as an event-wise false positive *`FPe`*. Additionally, due to the correction applied to the event-wise precision, each falsely detected sample *`FPt`* decreases the value of the corrected event-wise precision relatively to the number of nominal sample *`Nt`*. \n\n$$Precision_{e_{corr}} = \\frac{TP_e}{TP_e + FP_e} * (1 - \\frac{FP_t}{N_t})$$\n\n$$Recall_e = \\frac{TP_e}{TP_e + FN_e}$$\n\nIn summary, **the proposed solutions should focus on**:\n1. minimizing the number of event-wise and sample-wise false positives\n1. producing short and compact detections (not necessarily covering the whole anomalous segment, it is enough to detect at least one sample)\n\nThe metric does **NOT** care about:\n1. the level of overlap between correct detections and anomalous segments\n1. detection timing\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Submission file 📁", "content": "For each index representing a consecutive time point in the test set, the solution file should contain a binary information if this time point contains an anomaly (1) or not (0). The file should contain a header and have the following format:\n\n| id | is_anomaly |\n| --- | --- |\n|14728321|0|\n|14728322|0|\n|14728323|1|\n|14728324|0|\n| ... | ... |\n|15249600|0|\n\nThe file can be in CSV, but we highly recommend using the [Apache Parquet format](https://parquet.apache.org/) to significantly decrease the file size", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline ⌛", "content": "* **Start Date** - 13 March 2025\n* **Entry deadline** - Same as the Final Submission Deadline\n* **Team Merger deadline** - Same as the Final Submission Deadline\n* **Final submission deadline** - 11 June 2025\n* **Private leaderboard release** - 12 June 2025\n\nAll deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The competition organizers reserve the right to update the contest timeline if deemed necessary.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Acknowledgement 🎉", "content": "The dataset results from the work of an 18-month project carried by an industry Consortium composed of **Airbus Defence and Space**, **KP Labs**, and the **European Space Agency’s European Space Operations Centre** (ESA ESOC). The project, funded by ESA under the contract number 4000137682/22/D/SR, is a part of The Artificial Intelligence for Automation (A²I) Roadmap [3], a large endeavour started in 2021 to automate space operations by leveraging artificial intelligence.\n\nThe competition is organized on behalf of ESA (Gabriele De Canio) by [KP Labs company](https://www.kplabs.space/) (Krzysztof Kotowski and Bogdan Ruszczak) and [University of Pisa](https://www.unipi.it/index.php/english) (Vincenzo Lomonaco and Luigi Quarantiello). ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "References 📖", "content": "[1] K. Kotowski K, C. Haskamp, J. Andrzejewski, B. Ruszczak, J. Nalepa, D. Lakey, P. Collins, A. Kolmas, M. Bartesaghi, J. Martinez-Heras, G. De Canio, “European Space Agency Benchmark for Anomaly Detection in Satellite Telemetry,” 2024, [arXiv:2406.17826](http://arxiv.org/abs/2406.17826).\n\n[2] G. De Canio, J. Eggleston, J. Fauste, A. M. Palowski, and M. Spada, “Development of an actionable AI roadmap for automating mission operations,” in 2023 SpaceOps Conference, Dubai, United Arab Emirates, [link](https://star.spaceops.org/user_manudownload.php?doc=303__bm05ydei.pdf)\n\n[3] M. El Amine Sehili and Z. Zhang, “Multivariate Time Series Anomaly Detection: Fancy Algorithms and Flawed Evaluation Methodology,” in Performance Evaluation and Benchmarking, R. Nambiar and M. Poess, Eds., Cham: Springer Nature Switzerland, 2024, pp. 1–17. doi: 10.1007/978-3-031-68031-1_1.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }