基于气象因素的机场进离港延误预测

doi:10.12305/j.issn.1001-506X.2023.06.16

摘要/Abstract

摘要：

针对机场延误预测过程中难以提取延误传播时空特征、预测结果受天气扰动大的问题, 提出了基于气象因素的时空图卷积网络(meteorology-based spatio-temporal graph convolutional networks, MSTGCN)机场延误预测模型。该模型使用图卷积神经网络(graph convolutional neural network, GCNN)与门控卷积神经网络(gated convolutional neural network, Gated CNN)挖掘机场延误的时空特征, 同时加入气象特征提取模块对机场延误时间进行预测。实验结果表明, 该模型在中短时预测上的表现均优于其他对比模型; 相较于不考虑气象因素的模型, MSTGCN对未来1 h、4 h和12 h预测的平均绝对误差分别降低了7.03%, 7.93%, 11.54%, 对预测结果起到了极大的修正作用。

关键词: 机场延误预测, 图卷积神经网络, 气象因素, 机场网络, 深度学习

Abstract:

In order to solve the problem of great effect by weather conditions and the difficulty in extracting the temporal and spatial features of delay in the process of airport delay prediction, a meteorology-based spatio-temporal graph convolutional networks(MSTGCN) model is proposed in this paper. This model uses graph convolutional neural network (GCNN) and gated convolutional neural network (Gated CNN) to extract the temporal and spatial features of airport delays, and integrates meteorological characteristics extracting module to predict delay time of airports. The experiment results show that the performance of the proposed model in medium and short term prediction is superior to other comparative models. Compared with the model that does not consider meteorological factors, the mean absolute errors of MSTGCN for the next 1 h, 4 h and 12 h are respectively decreased by 7.03%, 7.93%, 11.54%, which greatly revises the prediction results.

Key words: airport delay prediction, graph convolutional neural network (GCNN), meteorological factors, airport network, deep learning

中图分类号:

V351

姜雨, 袁琪, 胡志韬, 吴薇薇, 顾欣. 基于气象因素的机场进离港延误预测[J]. 系统工程与电子技术, 2023, 45(6): 1722-1731.

Yu JIANG, Qi YUAN, Zhitao HU, Weiwei WU, Xin GU. Airport arrival and departure delay time prediction based on meteorological factors[J]. Systems Engineering and Electronics, 2023, 45(6): 1722-1731.

图/表 14

图1

图2

图3

图4

图5

图6

表1

表2

表3

图7

表4

表5

图8

图9

参考文献 30

1	WU C L , LAW K . Modelling the delay propagation effects of multiple resource connections in an airline network using a Bayesian network model[J]. Transportation Research Part E: Logistics and Transportation Review, 2019, 122, 62- 77. doi: 10.1016/j.tre.2018.11.004
2	PYRGIOTIS N , MALONE K M , ODONI A . Modelling delay propagation within an airport network[J]. Transportation Research Part C: Emerging Technologies, 2013, 27, 60- 75. doi: 10.1016/j.trc.2011.05.017
3	王时敏. 恶劣天气对航班延误影响的初步量化研究[D]. 南京: 南京航空航天大学, 2017: 28-47.
	WANG S M. Research on the impact of severe weather on flight delay[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2017: 28-47.
4	程华, 李艳梅, 罗谦, 等. 基于C4.5决策树方法的到港航班延误预测问题研究[J]. 系统工程理论与实践, 2014, 34 (S1): 239- 247. doi: 10.12011/1000-6788(2014)s1-239
	CHENG H , LI Y M , LUO Q , et al. Study on flight delay with C4.5 decision tree based prediction method[J]. Systems Engineering-Theory and Practice, 2014, 34 (S1): 239- 247. doi: 10.12011/1000-6788(2014)s1-239
5	REBOLLO J J , BALAKRISHNAN H . Characterization and prediction of air traffic delays[J]. Transportation Research Part C: Emerging Technologies, 2014, 44, 231- 241. doi: 10.1016/j.trc.2014.04.007
6	CHAKRABARTY N. A data mining approach to flight arrival delay prediction for american airlines[C]//Proc. of the 9th Annual Information Technology, Electromechanical and Microelectronics Conference, 2019: 102-107.
7	LI Q , JING R Z . Characterization of delay propagation in the air traffic network[J]. Journal of Air Transport Management, 2021, 94, 102075. doi: 10.1016/j.jairtraman.2021.102075
8	RODRÍGUEZ S Á , COMENDADOR F G , VALDÉS R A , et al. Assessment of airport arrival congestion and delay: prediction and reliability[J]. Transportation Research Part C: Emerging Technologies, 2019, 98, 255- 283. doi: 10.1016/j.trc.2018.11.015
9	FLEURQUIN P , RAMASCO J J , EGUILUZ V M . Systemic delay propagation in the US airport network[J]. Scientific Reports, 2013, 3 (1): 3747- 3752.
10	WANG C Z , HU M H , YANG L , et al. Prediction of air traffic delays: an agent-based model introducing refined parameter estimation methods[J]. PLoS One, 2021, 16 (4): e0249754. doi: 10.1371/journal.pone.0249754
11	WANG H W , PENG Z R , WANG D S , et al. Evaluation and prediction of transportation resilience under extreme weather events: a diffusion graph convolutional approach[J]. Transportation Research Part C: Emerging Technologies, 2020, 115, 102619. doi: 10.1016/j.trc.2020.102619
12	YU B , LEE Y , SOHN K . Forecasting road traffic speeds by considering area-wide spatio-temporal dependencies based on a graph convolutional neural network (GCN)[J]. Transportation Research Part C: Emerging Technologies, 2020, 114, 189- 204. doi: 10.1016/j.trc.2020.02.013
13	ZHAO L , SONG Y J , ZHANG C , et al. T-GCN: a temporal graph convolutional network for traffic prediction[J]. IEEE Trans.on Intelligent Transportation Systems, 2020, 21 (9): 3848- 3858. doi: 10.1109/TITS.2019.2935152
14	KIM Y J, CHOI S, BRICENO S, et al. A deep learning approach to flight delay prediction[C]//Proc. of the IEEE/AIAA 35th Digital Avionics Systems Conference, 2016.
15	YU B , GUO Z , ASIAN S , et al. Flight delay prediction for commercial air transport: a deep learning approach[J]. Transportation Research Part E: Logistics and Transportation Review, 2019, 125, 203- 221. doi: 10.1016/j.tre.2019.03.013
16	AI Y , PAN W J , YANG C Q , et al. A deep learning approach to predict the spatial and temporal distribution of flight delay in network[J]. Journal of Intelligent & Fuzzy Systems, 2019, 37 (5): 6029- 6037.
17	屈景怡, 叶萌, 渠星. 基于区域残差和LSTM网络的机场延误预测模型[J]. 通信学报, 2019, 40 (4): 149- 159.
	QU J Y , YE M , QU X . Airport delay prediction model based on regional residual and LSTM network[J]. Journal on Communications, 2019, 40 (4): 149- 159.
18	LUO C Y , LI X T , YE Y M . PFST-LSTM: a spatio temporal LSTM model with pseudoflow prediction for precipitation nowcasting[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 14 (11): 843- 857.
19	CAI K Q , LI Y , FANG Y P , et al. A deep learning approach for flight delay prediction through time-evolving graphs[J]. IEEE Trans.on Intelligent Transportation Systems, 2022, 23 (8): 11397- 11407. doi: 10.1109/TITS.2021.3103502
20	李娟. 基于深度学习的航班延误预测方法研究[D]. 南京: 南京航空航天大学, 2020: 35-55.
	LI J. Research on flight delay forecasting method based on deep learning[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2020: 35-55.
21	ZENG W L , LI J , QUAN Z B , et al. A deep graph-embedded LSTM neural network approach for airport delay prediction[J]. Journal of Advanced Transportation, 2021, 2021, 6638130.
22	BAO J , YANG Z , ZENG W L . Graph to sequence learning with attention mechanism for network-wide multi-step-ahead flight delay prediction[J]. Transportation Research Part C: Emerging Technologies, 2021, 130, 103323. doi: 10.1016/j.trc.2021.103323
23	中国民用航空局. 2020年民航行业发展统计公报[EB/OL]. [2022-02-20]. http://www.caac.gov.cn/XXGK/XXGK/TJSJ/202106/P020210610582600192012.pdf.
	Civil Aviation Administration of China. 2020 civil aviation industry development statistical bulletin[EB/OL]. [2022-02-20]. http://www.caac.gov.cn/XXGK/XXGK/TJSJ/202106/P020210610582600192012.pdf.
24	WU Y K , TAN H C , QIN L Q , et al. A hybrid deep learning based traffic flow prediction method and its understanding[J]. Transportation Research Part C: Emerging Technologies, 2018, 90, 166- 180. doi: 10.1016/j.trc.2018.03.001
25	DO L N N , VU H L , VO B Q , et al. An effective spatial-temporal attention based neural network for traffic flow prediction[J]. Transportation Research Part C: Emerging Technologies, 2019, 108, 12- 28. doi: 10.1016/j.trc.2019.09.008
26	YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proc. of the 27th International Joint Conference on Artificial Intelligence, 2018: 3634-3640.
27	SHUMAN D I , NARANG S K , FROSSARD P , et al. The emerging field of signal processing on graphs: extending high-dimensional data analysis to networks and other irregular domains[J]. IEEE Signal Processing Magazine, 2013, 30 (3): 83- 98. doi: 10.1109/MSP.2012.2235192
28	DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]//Proc. of the International Conference on Neural Information Processing Systems, 2016, 29: 3844-3852.
29	GUI G , LIU F , SUN J L , et al. Flight delay prediction based on aviation big data and machine learning[J]. IEEE Trans.on Vehicular Technology, 2020, 69 (1): 140- 150. doi: 10.1109/TVT.2019.2954094
30	BALLAKUR A A, ARYA A. Empirical evaluation of gated recurrent neural network architectures in aviation delay prediction[C]//Proc. of the 5th International Conference on Computing, Communication and Security, 2020.

数据特征	示例
月	11
日	2
时	13
节点编码	69
每1 h机场进(离)港延误时长/min	12

天气特征	编码类型	天气特征	编码类型
风速	实数	PL=冰珠	整数
能见度	实数	SH=阵雨	0-1
RA=雨	整数	IC=冰晶	0-1
TS=雷暴	整数	SG=雪粒	0-1
GR=冰雹	整数	BR=薄雾	0-1
SN=雪	整数	FU=烟	0-1

数据组	评价指标	预测窗口/h	历史均值法	随机森林	LSTM	GRU	NMGCN	MSTGCN
N67	MAE	1	5.383	4.133	4.022	3.954	4.083	3.796
		4	5.383	4.472	4.302	4.323	4.283	3.943
		12	5.383	4.734	4.406	4.430	4.650	4.113
	RMSE	1	8.037	7.051	6.875	6.866	7.178	6.742
		4	8.037	7.631	7.431	7.431	7.774	7.338
		12	8.037	8.049	7.767	7.770	8.260	7.849
N40	MAE	1	5.105	3.502	3.420	3.420	3.444	3.326
		4	5.105	3.950	3.786	3.849	3.844	3.606
		12	5.105	4.361	4.070	4.125	4.183	3.864
	RMSE	1	7.910	5.850	5.747	5.759	5.973	5.727
		4	7.910	6.794	6.611	6.614	7.011	6.567
		12	7.910	7.509	7.213	7.214	7.907	7.279
N67(40)	MAE	1	5.105	3.557	3.490	3.449	3.536	3.327
		4	5.105	3.977	3.851	3.878	3.789	3.541
		12	5.105	4.353	4.031	4.076	4.315	3.801
	RMSE	1	7.910	5.890	5.777	5.783	5.968	5.705
		4	7.910	6.779	6.634	6.622	6.932	6.611
		12	7.910	7.483	7.211	7.223	7.764	7.333

数据组	预测窗口/h	MAE/min		η/%
数据组	预测窗口/h	NMGCN模型	MSTGCN模型	η/%
N67	1	4.083	3.796	54.300
	4	4.283	3.943	53.400
	12	4.650	4.113	57.300
N40	1	3.444	3.326	50.300
	4	3.844	3.606	51.800
	12	4.183	3.864	52.000

机场代码	MAE/min		平均小时延误时间/min		年旅客吞吐量/人次
机场代码	进港	离港	进港	离港	年旅客吞吐量/人次
ATL	2.289	1.702	3.670	3.170	110 531 300
JFK	3.135	3.703	5.170	6.500	62 551 072
ONT	5.783	8.564	6.380	8.920	5 583 732