A Dynamic Multi-Graph Convolutional Spatial-Temporal Network for Airport Arrival Flow Prediction

In air traffic systems, aircraft trajectories between airports are monitored by the radar networking system forming dynamic air traffic flow. Accurate airport arrival flow prediction is significant in implementing large-scale intelligent air traffic flow management. Despite years of studies to impro...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunyang Huang, Hongyu Yang, Zhen Yan
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Aerospace
Subjects:
Online Access:https://www.mdpi.com/2226-4310/12/5/395
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327646702305280
author Yunyang Huang
Hongyu Yang
Zhen Yan
author_facet Yunyang Huang
Hongyu Yang
Zhen Yan
author_sort Yunyang Huang
collection DOAJ
description In air traffic systems, aircraft trajectories between airports are monitored by the radar networking system forming dynamic air traffic flow. Accurate airport arrival flow prediction is significant in implementing large-scale intelligent air traffic flow management. Despite years of studies to improve prediction precision, most existing methods only focus on a single airport or simplify the traffic network as a static and simple graph. To mitigate this shortage, we propose a hybrid neural network method, called Dynamic Multi-graph Convolutional Spatial-Temporal Network (DMCSTN), to predict network-level airport arrival flow considering the multiple operation constraints and flight interactions among airport nodes. Specifically, in the spatial dimension, a novel dynamic multi-graph convolutional network is designed to adaptively model the heterogeneous and dynamic airport networks. It enables the proposed model to dynamically capture informative spatial correlations according to the input traffic features. In the temporal dimension, an enhanced self-attention mechanism is utilized to mine the arrival flow evolution patterns. Experiments on a real-world dataset from an ATFM system validate the effectiveness of DMCSTN for arrival flow forecasting tasks.
format Article
id doaj-art-58f1d1089caf4e378318dec124d56d48
institution Kabale University
issn 2226-4310
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Aerospace
spelling doaj-art-58f1d1089caf4e378318dec124d56d482025-08-20T03:47:49ZengMDPI AGAerospace2226-43102025-04-0112539510.3390/aerospace12050395A Dynamic Multi-Graph Convolutional Spatial-Temporal Network for Airport Arrival Flow PredictionYunyang Huang0Hongyu Yang1Zhen Yan2College of Computer Science, Sichuan University, Chengdu 610065, ChinaNational Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, ChinaThe State Key Laboratory of Air Traffic Management System, Nanjing 210000, ChinaIn air traffic systems, aircraft trajectories between airports are monitored by the radar networking system forming dynamic air traffic flow. Accurate airport arrival flow prediction is significant in implementing large-scale intelligent air traffic flow management. Despite years of studies to improve prediction precision, most existing methods only focus on a single airport or simplify the traffic network as a static and simple graph. To mitigate this shortage, we propose a hybrid neural network method, called Dynamic Multi-graph Convolutional Spatial-Temporal Network (DMCSTN), to predict network-level airport arrival flow considering the multiple operation constraints and flight interactions among airport nodes. Specifically, in the spatial dimension, a novel dynamic multi-graph convolutional network is designed to adaptively model the heterogeneous and dynamic airport networks. It enables the proposed model to dynamically capture informative spatial correlations according to the input traffic features. In the temporal dimension, an enhanced self-attention mechanism is utilized to mine the arrival flow evolution patterns. Experiments on a real-world dataset from an ATFM system validate the effectiveness of DMCSTN for arrival flow forecasting tasks.https://www.mdpi.com/2226-4310/12/5/395airport arrival flow predictiondeep learningspatial-temporal dependenciesmulti-graph fusiongraph neural network
spellingShingle Yunyang Huang
Hongyu Yang
Zhen Yan
A Dynamic Multi-Graph Convolutional Spatial-Temporal Network for Airport Arrival Flow Prediction
Aerospace
airport arrival flow prediction
deep learning
spatial-temporal dependencies
multi-graph fusion
graph neural network
title A Dynamic Multi-Graph Convolutional Spatial-Temporal Network for Airport Arrival Flow Prediction
title_full A Dynamic Multi-Graph Convolutional Spatial-Temporal Network for Airport Arrival Flow Prediction
title_fullStr A Dynamic Multi-Graph Convolutional Spatial-Temporal Network for Airport Arrival Flow Prediction
title_full_unstemmed A Dynamic Multi-Graph Convolutional Spatial-Temporal Network for Airport Arrival Flow Prediction
title_short A Dynamic Multi-Graph Convolutional Spatial-Temporal Network for Airport Arrival Flow Prediction
title_sort dynamic multi graph convolutional spatial temporal network for airport arrival flow prediction
topic airport arrival flow prediction
deep learning
spatial-temporal dependencies
multi-graph fusion
graph neural network
url https://www.mdpi.com/2226-4310/12/5/395
work_keys_str_mv AT yunyanghuang adynamicmultigraphconvolutionalspatialtemporalnetworkforairportarrivalflowprediction
AT hongyuyang adynamicmultigraphconvolutionalspatialtemporalnetworkforairportarrivalflowprediction
AT zhenyan adynamicmultigraphconvolutionalspatialtemporalnetworkforairportarrivalflowprediction
AT yunyanghuang dynamicmultigraphconvolutionalspatialtemporalnetworkforairportarrivalflowprediction
AT hongyuyang dynamicmultigraphconvolutionalspatialtemporalnetworkforairportarrivalflowprediction
AT zhenyan dynamicmultigraphconvolutionalspatialtemporalnetworkforairportarrivalflowprediction