Airport surface dataset for machine learning based taxi-out time prediction

Sep 17, 2026

Uploaded by Skyler

Airport surface operation is an important part of air traffic management and a key driver of overall flight efficiency. This thesis develops a dataset for machine learning to predict aircraft taxi-out time, aiming to reduce delays and support more robust scheduling. Using radar and sensor data collected at one major airport, the work builds a preprocessing pipeline to harmonize A-SMGCS and ASTERIX-based data, then reconstructs congestion, aircraft, infrastructure, temporal, and weather-related features. Feature selection, multicollinearity checks, supervised modeling, cross validation, and SHAP-based interpretation evaluate the dataset.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages85

Reading Time3 h 34 min

AccessFree to download

Abstract

Keywords

Preface

Acknowledgements

List of Acronyms

Airport surface dataset for machine learning based taxi-out time prediction Lisa Holländer Moa Kallén DEPARTMENT OF MECHANICS AND MARITIME SCIENCES CHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2026 [www.chalmers.se](www.chalmers.se) Master’s Thesis in Complex adaptive systems Airport surface dataset for machine learning based taxi-out time prediction Lisa Holländer Moa Kallén Department of Mechanics and Maritime Sciences Division of Vehicle Engineering and Autonomous Systems Chalmers University of Technology Gothenburg, Sweden 2026 Airport surface dataset for machine learning based taxi-out time prediction Lisa Holländer Moa Kallén © Lisa Holländer, Moa Kallén, 2026 . Supervisor: Michael Forschlé, Saab Air Traffic Management Examiner and supervisor: Ola Benderius, Department of Mechanics and Maritime Sciences Master’s Thesis 2026 Department of Mechanics and Maritime Sciences Chalmers University of Technology SE-412 96 Gothenburg Sweden Telephone +46 31 772 1000 Cover: Air traffic control tower at night with sunset view [1] . Typeset in LATEX Gothenburg, Sweden 2026 Airport surface dataset for machine learning based taxi-out time prediction Lisa Holländer Moa Kallén Department of Mechanics and Maritime Sciences Division of Vehicle Engineering and Autonomous Systems Chalmers University of Technology Abstract Airport surface operation is an important part of air traffic management. It is a critical contributor of overall flight efficiency. Accurate prediction of taxi-out time for aircraft can help reduce delays and allow for more robust scheduling. This thesis uses airport surface movement data to predict taxi-out time using machine learning. By using radar and sensor data collected at one major airport, the goal is to create a dataset suitable for machine learning. To achieve this, a comprehensive preprocessing pipeline was developed to harmonize airport data from A-SMGCS surveillance systems and ASTERIX-based systems. Key features influencing taxi times, such as traffic congestion, aircraft characteristics, airport infrastructure, temporal patterns, and weather conditions, were identified through a literature review. This thesis reconstructs the identified features using the available airport data. Additionally, feature selection and multicollinearity analysis were performed using correlation matrices, variance inflation factor (VIF), and Cramer’s V statistics to ensure the robustness of the predictive model. Finally, in order to evaluate the dataset, two supervised machine learning models were used. The models implemented were Multiple linear regression and Random forest. Random forest outperformed linear regression, showcasing its ability to capture nonlinear and complex patterns in the dataset. For a final robust evaluation of the dataset, k-fold cross validation was used on Random forest. The results were then interpreted using SHAP. SHAP identified features pertaining to the airport geometry and congestion-related features as the features with the most impact on the taxi-out time prediction. This study demonstrates the feasibility and limitations of creating an airport surface dataset for machine learning for predicting taxi-out times. It highlights the importance of the data preprocessing steps, as well as the feature engineering, in airport surface-related predictive modeling. Keywords: Airport operations, Air traffic management (ATM), Machine learning, Aircraft taxi-out time (AXOT), Taxi-out time prediction, Feature selection, Data harmonization, Explainable AI, SHAP Preface This report presents the outcome of our master’s thesis project, at the Department of Mechanical Engineering at Chalmers University of Technology during the spring of 2026 . The thesis investigates the oppertunity of predicting aircraft taxi-out times using historical airport surface movement data and machine learning algorithms. Acknowledgements We would like to express our

FAQs

What problem does the thesis address?

It addresses predicting aircraft taxi-out time to reduce delays and improve scheduling robustness in air traffic management.

How is the dataset intended to be created?

It uses airport surface movement data from radar and sensors to build a preprocessing pipeline that harmonizes data from A-SMGCS and ASTERIX-based systems.

Which machine learning models are evaluated, and what is the outcome?

Multiple linear regression and Random forest are tested; Random forest outperforms linear regression and is evaluated further with k-fold cross validation, with SHAP used for interpretation.

Sep 17, 2026

Uploaded by Skyler

Airport surface dataset for machine learning based taxi-out time prediction_Page 1

Open in WPS to view all 85 pages