Multi-Time prediction model of flight transit key nodes time based on GBDT

Abstract

Abstract:

To accurately predict the flight transit key nodes time such as departure and takeoff, and improve the operational

efficiency of busy airports, a multi-time prediction model of flight transit key nodes time based on gradient boosting

decision tree (GBDT) is proposed in this paper. Firstly, the flight information data items are classified according to

the generation time. Secondly, based on the GBDT algorithm and Spark platform, the prediction models of flight

transit key nodes time at different transit times are constructed respectively. Finally, flight data is obtained and processed in real-time computing manner, enabling dynamic prediction of flight departure time and take-off time at

multiple times. The experimental results show that the proposed model has good predictive performance and has the

best predictive performance compared to other algorithms, with a prediction accuracy of 95.6% within ± 15 minutes.

Key words:

flight transit key nodes time, gradient boosting decision tree (GBDT), Spark platform, dynamic prediction

CLC Number:

TP181

DING Jianli, FENG Hao. Multi-Time prediction model of flight transit key nodes time based on GBDT[J]. Journal of Civil Aviation University of China, 2024, 42(6): 27-33.

References 5(4)

	[1]
	CORRIGAN S, MARTENSSON L, KAY A, et al. Preparing for airport
	collaborative decision making (A-CDM) implementation: an evaluation
	and recommendations[J]. Cognition, Technology & Work, 2015, 17(2):
	207-218.
	[2]
	ZUO H C, DING Y, SANG X, et al． Flight off-block time prediction
	based on BP neural network optimized by genetic algorithm [C]//2021
	IEEE 3rd International Conference on Civil Aviation Safety and Infor－
	mation Technology(ICCASIT), October 20-22, 2021, Changsha, China．
	IEEE, 2021: 1-6．
	[3]
	ZHOU H, LI W C, JIANG Z Q, et al. Flight departure time prediction
	based on deep learning[J]. Aerospace, 2022, 9(7): 394-408.
	[4]
	ZHU X X, BIAN L, LIU Y, et al． An estimated time of departure model
	in the airspace in China[C]//2021 IEEE 3rd International Conference on
	CivilAviation Safety and Information Technology (ICCASIT), October 20-
	22, 2021, Changsha, China． IEEE, 2021: 437-444．
	[5]
	GUO Z, YU B, HAO M Y, et al. A novel hybrid method for flight depar－
	ture delay prediction using random forest regression and maximal infor－
	mation coefficient[J]. Aerospace Science and Technology, 2021, 116:
	106822 .
	[6]
	ANEES A, HUANG W． Flight delay prediction: data analysis and model
	development[C]//2021 26th International Conference on Automation and
	Computing (ICAC), September 2-4, 2021, Portsmouth, United Kingdom．
	IEEE, 2021: 1-6．
	[7]
	MAO J, DANG Z Y, LIU Y, et al. A method of flight off-block time pre－
	diction based on LSI-CNN model[C]//2019 IEEE 1st International Con－
	ference on Civil Aviation Safety and Information Technology(ICCASIT),
	October 17-19, 2019, Kunming, China． IEEE, 2019: 95-99.
[8]	徐涛, 丁杨, 卢敏．基于级联 BP 神经网络的航班撤轮挡时刻预
测[J]	．计算机应用与软件, 2019, 36(6): 226-232．
	[9]
	DALMAU R, BALLERINI F, NAESSENS H, et al. Improving the pre－
	dictability of take-off times with machine learning: a case study for the
	Maastricht upper area control centre area of responsibility[C]//The 9th
	SESAR Innovation Days, December 2-5, 2019: 1-8.
[10]	DALMAU R, BALLERINI F, NAESSENS H, et al. An explainable ma－
	chine learning approach to improve take-off time predictions[J]. Journal
	of Air Transport Management, 2021, 95: 102090.
[11]	CHATTERJI G, ZHENG Y． Wheels-off time prediction using surface
	traffic metrics[C]//The 12th AIAA Aviation Technology, Integration, and
	Operations (ATIO) Conference and 14th AIAA/ISSMO Multidisciplinary
	Analysis and Optimization Conference, September 17-19, 2012, Indi－
	anapolis, Indiana． Reston, Virigina: AIAA, 2012: AIAA2012-5699-5712．
[12]	王春政, 胡明华, 杨磊, 等．基于 Agent 模型的机场网络延误预测
[J]	．航空学报, 2021, 42(7): 445-458．
[13]	ZHU Q X, SONG X L, ZHANG N, et al. Novel SVD integrated with GB－
	DT based virtual sample generation and its application in soft sensor[J].
	IFAC-PapersOnLine, 2022, 55(7): 952-956.
[14]	ZHAO Z, FENG S C, SONG M W, et al. A delay prediction method for
	the whole process of transit flight[J]. Aerospace, 2022, 9(11): 645-662.
[15]	邢志伟, 李彪, 朱慧, 等．基于深度神经网络的航班保障时间预
	测研究[J]．系统仿真学报, 2020, 32(4): 678-686．
[16]	AHMED N, BARCZAK A L C, RASHID M A, et al. An enhanced
	parallelisation model for performance prediction of apache spark on a
	multinode hadoop cluster[J]. Big Data and Cognitive Computing, 2021,
5(4)	: 65.