[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126230-en":3,"doc-seo-126230-105":31,"detail-sidebar-cat-0-en-105":93},{"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},126230,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Open Machine Learning Models for Actual Takeoff Weight Prediction","Aircraft weight is a key input in flight trajectory prediction and environmental impact assessment, yet actual takeoff weight data is rarely openly available during flights. To address this gap, the study leverages large-scale open aviation data from Eurocontrol’s Performance Review Commission to train and evaluate an open-source machine learning workflow. The dataset covers 369,013 flights in European airspace during 2022, with engineered operational features capturing horizontal and vertical profiles. Models including CatBoost, LightGBM, XGBoost, neural networks, and an ensemble are compared for efficiency, accuracy, and real-world applicability. The best model achieves 1.73% mean percentage error.","Journal of Open Aviation Science (2025), Vol.3 doi:10.59490/joas.2025.7963  \nARTICLE  \nOpen Machine Learning Models for Actual Takeoff Weight Prediction  \nMayara C. R. Murça ,*,1 Marcos R. O. A. Maximo ,2 Joao P. A. Dantas ,3 João B. T. Szenczuk ,1 Carolina R. Lima ,2 Lucas O. Carvalho ,1 and Gabriel A. Melo 2  \n1 Civil Engineering Division, Aeronautics Institute of Technology, São José dos Campos, Brazil  \n2Autonomous Computational Systems Lab (LAB-SCA), Computer Science Division, Aeronautics Institute of Technology, São José dos Campos, Brazil  \n3Decision Support Systems Subdivision, Institute for Advanced Studies, São José dos Campos, Brazil  \n*[Corresponding author:](Corresponding author: mayara@ita.br)[ mayara@ita.br](Corresponding author: mayara@ita.br)  \n(Received: 20 Dec 2024; Revised: 24 Mar 2025; Accepted: 24 Mar 2025; Published: 8 Apr 2025)  \n(Editor: Xavier Olive; Reviewers: Richard Alligier, Ryota Mori, and Junzi Sun)  \nAbstract  \nAircraft weight is a key input in flight trajectory prediction and environmental impact assessment tools. However, the lack of openly available data regarding the actual aircraft weight throughout the flight requires the development of mass estimation approaches to be incorporated into these tools. This study uses large-scale open aviation data made available by Eurocontrol’s Performance Review Commission to develop an open-source machine learning model to predict commercial flights’ actual takeoff weight. The data combines detailed flight, trajectory, and meteorological information for 369,013 flights that transited through the European airspace in 2022 . Several operational features are created to represent each flight’s horizontal and vertical profiles accurately. For model learning, we employ CatBoost, LightGBM, XGBoost, artificial neural networks, and an ensemble of these models, which were selected for their robust performance in structured data analysis and potential for high predictive accuracy. The models are evaluated based on their efficiency, accuracy, and applicability to real-world data. The best-performing model is found to predict the aircraft takeoff weights with a mean percentage of error of 1.73% .  \nKeywords: Air traffic management; aircraft mass; predictive modeling; machine learning  \n1. Introduction  \nAdvances in Air Traffic Management (ATM) are important to achieve a globally sustainable aviation industry. The implementation of novel technologies and operational concepts, such as TrajectoryBased Operations (TBO), have been explored worldwide to reach increasingly stringent environmental performance targets [1] . This requires advanced tools for modeling and predicting flight trajectory performance and its associated environmental impact across multiple scales. To this goal, extensive previous work has explored analytical and empirical approaches for trajectory prediction [2, 3], fuel burn estimation [4, 5, 6] and emissions assessment [7, 8], considering the different phases of the flight operation.  \nAs a fundamental parameter in flight dynamics, aircraft weight is an essential input for these models. However, this information is only available in detailed aircraft data registered by Flight Data Recorder (FDR) systems, being considered proprietary and kept confidential by airlines. This lack of  \n© 2025 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 Mayara C. R. Murça  et al.  \nopenly available data is typically compensated with assumptions and estimations of aircraft mass, which might introduce a significant source of error and lead to inaccurate trajectory predictions [9] .  \nPrevious studies have focused on improving mass estimations with the use of other sources of data, such as aircraft surveillance data. Alligier et al. [10] introduced a least squares method t","cbCaitLJ8VoO7905","https://ap.wps.com/l/cbCaitLJ8VoO7905","pdf",3796669,5,1,26,"English","en",105,"# Introduction\n# Proposed Open-Source Machine Learning Approach\n## Data source and problem setup\n## Feature engineering for flight profiles\n# Model training and evaluation\n## Algorithms used\n## Performance metrics and results","[{\"question\":\"Why is predicting actual takeoff weight important for aviation modeling?\",\"answer\":\"Aircraft weight is a core input for flight trajectory prediction and environmental impact assessment tools. Without accurate weight information, downstream predictions can become biased due to estimation errors.\"},{\"question\":\"What dataset is used to train the models?\",\"answer\":\"The study uses large-scale open aviation data provided by Eurocontrol’s Performance Review Commission, covering 369,013 commercial flights that transited European airspace in 2022.\"},{\"question\":\"Which machine learning methods achieve the best prediction accuracy?\",\"answer\":\"The study evaluates CatBoost, LightGBM, XGBoost, artificial neural networks, and an ensemble of these models. The best-performing approach predicts takeoff weights with a mean percentage error of 1.73%.\"}]","Open Machine Learning Models for Actual Takeoff Weight Prediction | PDF",1785903949,66,{"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":88,"head_meta":90,"extra_data":92,"updated_unix":29},"open-machine-learning-models-for-actual-takeoff-weight-prediction","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/open-machine-learning-models-for-actual-takeoff-weight-prediction/126230/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"Why is predicting actual takeoff weight important for aviation modeling?","Question",{"text":77,"@type":78},"Aircraft weight is a core input for flight trajectory prediction and environmental impact assessment tools. Without accurate weight information, downstream predictions can become biased due to estimation errors.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"What dataset is used to train the models?",{"text":82,"@type":78},"The study uses large-scale open aviation data provided by Eurocontrol’s Performance Review Commission, covering 369,013 commercial flights that transited European airspace in 2022.",{"name":84,"@type":75,"acceptedAnswer":85},"Which machine learning methods achieve the best prediction accuracy?",{"text":86,"@type":78},"The study evaluates CatBoost, LightGBM, XGBoost, artificial neural networks, and an ensemble of these models. The best-performing approach predicts takeoff weights with a mean percentage error of 1.73%.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"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":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":20,"slug":139},19,"General","general"]