Probabilistic Flight Delay Predictions Using Machine Learning and Applications to the Flight-to-Gate Assignment Problem

Micha Zoutendijk,Mihaela Mitici

doi:10.3390/aerospace8060152

Abstract

The problem of flight delay prediction is approached most often by predicting a delay class or value. However, the aviation industry can benefit greatly from probabilistic delay predictions on an individual flight basis, as these give insight into the uncertainty of the delay predictions. Therefore, in this study, two probabilistic forecasting algorithms, Mixture Density Networks and Random Forest regression, are applied to predict flight delays at a European airport. The algorithms estimate well the distribution of arrival and departure flight delays with a Mean Absolute Error of less than 15 min. To illustrate the utility of the estimated delay distributions, we integrate these probabilistic predictions into a probabilistic flight-to-gate assignment problem. The objective of this problem is to increase the robustness of flight-to-gate assignments. Considering probabilistic delay predictions, our proposed flight-to-gate assignment model reduces the number of conflicted aircraft by up to 74% when compared to a deterministic flight-to-gate assignment model. In general, the results illustrate the utility of considering probabilistic forecasting for robust airport operations’ optimization.

Highlights

On-time flight performance is an important measure of the service quality of airports and airlines
Since the root mean square error (RMSE) and mean absolute error (MAE) are not suitable to assess an estimated flight delay distribution, we propose the variants RMSEM and MAEM, which are calculated by comparing the mean value of the estimated distribution against the actual delay value
The Mixture Density Networks (MDN) and Random Forests regression (RFR) algorithms have been used to estimate the distribution of the arrival and departure flight delays

Summary

Introduction

On-time flight performance is an important measure of the service quality of airports and airlines. During the period 2013–2019, while the number of flights in Europe increased by 16% [1], the average departure delay of European flights increased by 41% [2]. Such an increase has a negative impact on the airports’ and airlines’ quality of service. Accurate flight delay predictions will remain central to support airports and airlines in offering a high-quality service. Several machine learning algorithms have been proposed to predict flight delays. Most studies predict flight delays using (i) binary classifiers (delayed/not delayed flight), (ii) multi-class classifiers (multiple delay classes), or (iii) regression (estimating the delay value)

Objectives

Results

Conclusion