[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128149-en":3,"doc-seo-128149-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128149,549768072016,"River Wang","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Training a Machine Learning Model to Detect Holding Patterns in Aircraft Trajectories","This paper develops a machine learning model for detecting holding pattern events in aircraft trajectories. Holding patterns are racetrack-shaped routes used to delay approach or maintain flight without progressing to destination, often driven by airport congestion, adverse weather, or other operational constraints. While rule-based detection is challenging, the study labels a dataset of 130,000+ landing trajectories from five major European airports, then trains a model to identify holding accurately for performance evaluation in Terminal Manoeuvring Areas.","Journal of Open Aviation Science (2024), Vol.2 doi:10.59490/joas.2024.7943  \nPROCEEDINGS | The 12th OpenSky Symposium  \nTraining a Machine Learning Model to Detect Holding Patterns in Aircraft Trajectories  \nXavier Olive ,*,1 Luis Basora ,1 Junzi Sun ,2 and Enrico Spinielli 3  \n1 ONERA DTIS, Université de Toulouse, France  \n2Faculty of Aerospace Engineering, Delft University of Technology, The Netherlands  \n3EUROCONTROL, Performance Review Unit, Brussels, Belgium  \n*Corresponding author: [xavier.olive@onera.fr](xavier.olive@onera.fr)  \n(Received: 6 Dec 2024; Revised: 18 Mar 2025; Accepted: 17 Feb 2025; Published: 19 Mar 2025)  \n(Editor: Martin Strohmeier; Reviewers: Max Li and Christian Verdonk Gallego)  \nAbstract  \nThis paper presents a Machine Learning (ML) model developed to detect holding pattern events in aircraft trajectories. Holding patterns are racetrack-shaped flight paths that an aircraft follows while awaiting further instructions or clearance from air traffic control (ATC) . They are typically used to delay an aircraft’s approach or to maintain flight without progressing towards its destination, often due to airport congestion, adverse weather conditions, or other operational factors. Accurate detection of these patterns in aircraft trajectories is crucial for performance evaluation studies within Terminal Manoeuvring Areas. Although holding patterns are relatively straightforward to define, efficiently detecting them using rulebased methods is challenging. This study details the process of labelling a dataset comprising over 130,000 aircraft trajectories landing at five major European airports and training a model to accurately identify these patterns.  \nKeywords: air traffic management, ADS-B, trajectory analysis, data preprocessing, machine learning  \n1. Introduction  \nAs air traffic control (ATC) is responsible for ensuring safe and efficient operations, this task becomes particularly complex within Terminal Manoeuvring Areas (TMAs), where numerous aircraft converge towards one or more runways. In these areas, aircraft must reduce speed and altitude, align for landing, and maintain safe separation distances, including wake turbulence separations. The challenge intensifies under adverse conditions, such as fog or thunderstorms, which necessitate greater separation distances, further complicating the management of air traffic flow.  \nControl strategies within Terminal Manoeuvring Areas (TMAs) include level-offs, path stretching, point-merge techniques, and holding patterns [1]. Previous research [2] has demonstrated that holding patterns have the most significant adverse environmental impact among these strategies, regardless of the underlying cause. Another study [3] investigated the factors contributing to holding patterns at major European airports. These analyses were all based on the original detection method implemented in the traffic library [4], a method which, until now, has not been formally published in an academic context.  \nIn this paper, we present the method used to label an original dataset [5] with holding pattern in-  \n© 2024 by the authors. This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) licence ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/))  \n2 Xavier Olive  et al.  \nformation. Initially, we applied information extraction techniques based on autoencoding neural networks, to explore the characteristics of holding patterns within the generated latent space. This approach allowed us to identify areas where holding patterns tended to cluster, resulting in a prelabelled dataset. This dataset was then meticulously and laboriously relabelled by the authors. Following this, the initial layers of the autoencoder were retained, and the downstream layers were replaced with a conventional classifier trained to specialize in the identification of holding patterns.  \nThis approach l","cbCaio2owv2VFlkF","https://ap.wps.com/l/cbCaio2owv2VFlkF","pdf",4051314,2,1,10,"English","en",105,"# Introduction\n## Context in Terminal Manoeuvring Areas (TMAs)\n## Holding patterns and prior work\n# Definition of a holding pattern\n## Racetrack manoeuvre and operational use\n# Dataset labelling and modelling approach\n## Autoencoding latent-space exploration\n## Relabelling and classifier training\n# Training procedure and results\n## Training workflow\n## Implications for delay monitoring","[{\"question\":\"What is the goal of this study on aircraft trajectories?\",\"answer\":\"To train a machine learning model that accurately detects holding pattern events from aircraft trajectory data.\"},{\"question\":\"Why is detecting holding patterns important for air traffic operations?\",\"answer\":\"Holding patterns strongly affect environmental outcomes and are used to manage delays in terminal airspace, so reliable detection supports performance evaluation metrics.\"},{\"question\":\"How is the labelled dataset constructed for training?\",\"answer\":\"A large dataset of 130,000+ landing trajectories from five European airports is prelabelled using information extraction with autoencoding neural networks, then carefully relabelled by the authors before training a classifier.\"}]","Training a Machine Learning Model to Detect Holding Patterns in Aircraft Trajectories | PDF",1785945103,25,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"training-a-machine-learning-model-to-detect-holding-patterns-in-aircraft-trajectories","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/training-a-machine-learning-model-to-detect-holding-patterns-in-aircraft-trajectories/128149/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the goal of this study on aircraft trajectories?","Question",{"text":76,"@type":77},"To train a machine learning model that accurately detects holding pattern events from aircraft trajectory data.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Why is detecting holding patterns important for air traffic operations?",{"text":81,"@type":77},"Holding patterns strongly affect environmental outcomes and are used to manage delays in terminal airspace, so reliable detection supports performance evaluation metrics.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the labelled dataset constructed for training?",{"text":85,"@type":77},"A large dataset of 130,000+ landing trajectories from five European airports is prelabelled using information extraction with autoencoding neural networks, then carefully relabelled by the authors before training a classifier.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":22,"slug":134},"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]