A Deep Graph-Embedded LSTM Neural Network Approach for Airport Delay Prediction

Abstract

Due to the strong propagation causality of delays between airports, this paper proposes a delay prediction model based on a deep graph neural network to study delay prediction from the perspective of an airport network. We regard airports as nodes of a graph network and use a directed graph network to construct airports’ relationship. For adjacent airports, weights of edges are measured by the spherical distance between them, while the number of flight pairs between them is utilized for airports connected by flights. On this basis, a diffusion convolution kernel is constructed to capture characteristics of delay propagation between airports, and it is further integrated into the sequence-to-sequence LSTM neural network to establish a deep learning framework for delay prediction. We name this model as deep graph-embedded LSTM (DGLSTM). To verify the model’s effectiveness and superiority, we utilize the historical delay data of 325 airports in the United States from 2015 to 2018 as the model training set and test set. The experimental results suggest that the proposed method is superior to the existing mainstream methods in terms of accuracy and robustness.

Assessing Identifiability in Airport Delay Propagation Roles Through Deep Learning Classification

“…The possibly first application of DL to delay prediction was proposed by Kim and co-authors, in which the sequences of departure and arrival flight delays of an airport were predicted using a Long Short-Term Memory network architecture, using input features like the delay of previous flights and the weather condition [24]. Numerous new studies have followed this initial work, mainly focusing on increasing the spectrum of information fed in the models: from micro-scale meteorological conditions [25]- [28], rea- VOLUME 4, 2016 sons of previous delays [29], airline and flights connection structure [26], [28], [30], [31], airport crowdedness [26], [32], to aircraft trajectories [33] and airspace structure [32]. The interested reader can refer to [34] for a review on the use of data analysis in the study of air transport delay.…”

Prediction of Flight Delays at Beijing Capital International Airport Based on Ensemble Methods

“…Yu et al [20] employed a deep belief network to predict flight delays. Zeng et al [21] proposed a deep graph-embedded LSTM (DGLSTM) model to predict delays at 325 airports in the United States. Bao et al [22] developed a novel graph-to-sequence learning architecture with attention mechanism (AG2S-Net) to predict hourly delays in the airport network from multiple steps ahead.…”

Airport Cluster Delay Prediction Based on TS-BiLSTM-Attention

“…Through multiple models' combination based on the deep learning paradigm, Reference [6] proposed a Long Short-Term Memory (LSTM) recursion neural network, and demonstrated that the prediction accuracy was improved with the deepened structure; to solve the coding issue in delay prediction, Reference [7] proposed a multiple layer artificial neural network to predict the airport delay of JFR Airport; Reference [8] designed and proposed a method combining a deep belief network and support vector regression to predict the airport delay of PEK-HGH; References [9][10][11] designed a Long Short-Term Memory (LSTM) network and its improved algorithm to achieve delay prediction, and achieved a satisfactory prediction result; Reference [12] applied the Graph Convolutional Neural Network (GCN) delay prediction method to explore the spatial interaction hidden in an airport network. The results show that deep learning based on graph structure input has a great potentiality in air traffic delay prediction; concerning the causality of flight delay propagation between airports, Reference [13] studied flight delay prediction standing at the perspective of an airport network, and established a DGLSTM depth learning framework based on 4-year historical data of 325 airports in the United States, and its accuracy and robustness is more competent than current popular methods; Reference [14] established a flight departure time prediction model based on deep learning with analyzing the influences of different factors on flight departure time; Reference [15] established the method of delay prediction for the whole process of transit flights, constructed an unbalanced data classification model, identified delayed flights at each prediction guarantee node, and achieved an accurate recognition rate of 96.5% for delayed flights; and Reference [16] established the airport delay prediction model based on the airport network method. Researchers established clustering models on the characteristics of multiple airports' networks, and concluded that the model based on Betweenness Centrality realized a satisfactory prediction effect through experimental comparison and verification.…”