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

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.