Multi-Airport Delay Prediction with Transformers

TL;DR

This paper introduces a novel multi-airport delay prediction method using Temporal Fusion Transformers, incorporating a self-supervised weather data encoding to improve accuracy and interpretability for better traffic management.

Contribution

It proposes a new multi-airport delay prediction model based on TFT with a self-supervised weather encoding, enhancing prediction accuracy and interpretability.

Findings

Achieved smaller prediction errors on test data.

Effectively encoded high-dimensional weather data.

Identified key factors influencing delays.

Abstract

Airport performance prediction with a reasonable look-ahead time is a challenging task and has been attempted by various prior research. Traffic, demand, weather, and traffic management actions are all critical inputs to any prediction model. In this paper, a novel approach based on Temporal Fusion Transformer (TFT) was proposed to predict departure and arrival delays simultaneously for multiple airports at once. This approach can capture complex temporal dynamics of the inputs known at the time of prediction and then forecast selected delay metrics up to four hours into the future. When dealing with weather inputs, a self-supervised learning (SSL) model was developed to encode high-dimensional weather data into a much lower-dimensional representation to make the training of TFT more efficiently and effectively. The initial results show that the TFT-based delay prediction model achieves satisfactory performance measured by smaller prediction errors on a testing dataset. In addition, the interpretability analysis of the model outputs identifies the important input factors for delay prediction. The proposed approach is expected to help air traffic managers or decision makers gain insights about traffic management actions on delay mitigation and once operationalized, provide enough lead time to plan for predicted performance degradation.