基于气象因素与特征选择的进港航班延误可解释预测研究

doi:10.16097/j.cnki.1009-6744.2023.05.018

交通运输系统工程与信息 ›› 2023, Vol. 23 ›› Issue (5): 162-171.DOI: 10.16097/j.cnki.1009-6744.2023.05.018

基于气象因素与特征选择的进港航班延误可解释预测研究

王维莉^*，王逸文

上海海事大学，物流研究中心，上海 201306

收稿日期:2023-06-02 修回日期:2023-08-05 接受日期:2023-08-16 出版日期:2023-10-25 发布日期:2023-10-22
作者简介:王维莉(1987- )，女，湖北武汉人，副教授。
基金资助:
上海市科技创新行动计划项目 (19DZ1209600)

Explainable Prediction of Inbound Flight Delays Based on Meteorological Factors and Feature Selection

WANG Wei-li^*, ANG Yi-wen

Logistics Research Center, Shanghai Maritime University, Shanghai 201306, China

Received:2023-06-02 Revised:2023-08-05 Accepted:2023-08-16 Online:2023-10-25 Published:2023-10-22
Supported by:
Shanghai Science and Technology Innovation Action Project (19DZ1209600)

摘要/Abstract

摘要： 航班延误预测对于提高旅客满意度和优化资源配置具有重要意义，然而，预测模型的不可见性限制了其进一步发展。为提高航班延误预测问题的准确性与可解释性，以某机场航线到港航班为例，在考虑机场不同气象因素的基础上，基于mRMR(max-Relevance and min-Redundancy)算法剔除冗余特征，筛选最优特征子集作为预测模型的输入，在比较多种机器学习算法后，选择Catboost算法，利用SHAP(Shapley Additive Explanation)归因分析方法，从局部解释和全局解释深入挖掘各因素对航班延误时间的不同影响程度，并采用偏依赖分析提取关键因素的最佳阈值。结果表明：经过特征选择后的Catboost预测模型能够更好地捕捉非线性特征，相比于未经过特征选择的模型，MAE(Mean Absolute Error)、RMSE(Root Mean Square Error)及MAPE(Mean Absolute Percentage Error)分别降低了3.84%，3.35%，4.22%，并利用DM(Diebold-Mariano)检验从统计学上检验模型的差异性；同时，航班延误时间受到多种气象特征以及前序延误等因素共同影响，其中，机场风速和降水量对延误时间有显著正向影响，而机场有效风力和能见度则对延误时间有显著负向影响。

关键词: 航空运输, 航班延误预测, SHAP归因分析, 进港航班, mRMR算法, Catboost算法

Abstract: Flight delay prediction is crucial for improving passenger satisfaction and optimizing resource allocation. However, the lack of visibility in predictive models hinders their further development. This paper aims to enhance the accuracy and interpretability of flight delay prediction. We focus on inbound flights of a specific airport route and develop a prediction model. We employ the max-Relevance and min-Redundancy (mRMR) algorithm to eliminate redundant features based on different meteorological factors at the airport. The optimal feature subset is then selected as input for the prediction model. The Catboost algorithm is chosen by comparing various machine learning algorithms. The Shapley Additive Explanation (SHAP) method is utilized for attribution analysis, which helps uncover the different influences of various factors on flight delay time through local and global explanations. By conducting a partial dependence analysis, the optimal threshold of key factors is extracted. The results demonstrate that the Catboost prediction model, after feature selection, performs better in capturing nonlinear features. Compared to a model without feature selection, the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) are reduced by 3.84%, 3.35%, and 4.22%, respectively. Statistical tests, such as the DM test, confirm the significance of the model's improvement. Moreover, the study reveals that flight delay time is influenced by various meteorological characteristics and previous delays. Specifically, airport wind speed and precipitation have a significant positive effect on delay time, while airport effective wind speed and visibility have a significant negative effect.

Key words: air transportation, flight delay prediction, SHAP attribution analysis, inbound flights, mRMR algorithm; Catboost algorithm

中图分类号:

U8
V355

王维莉, 王逸文. 基于气象因素与特征选择的进港航班延误可解释预测研究[J]. 交通运输系统工程与信息, 2023, 23(5): 162-171.

WANG Wei-li, WANG Yi-wen. Explainable Prediction of Inbound Flight Delays Based on Meteorological Factors and Feature Selection[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(5): 162-171.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2023.05.018

http://www.tseit.org.cn/CN/Y2023/V23/I5/162

参考文献

[1] BRITTO R, DRESNER M, VOLTESs A. The impact of flight delays on passenger demand and societal welfare [J]. Transportation Research Part E, 2014, 48(2): 460- 469.

[2] RYERSON M S, HANSEN M, BONN J. Time to burn: Flight delay, terminal efficiency, and fuel consumption in the National Airspace System[J]. Transportation Research Part A: Policy and Practice, 2014, 69(11): 286- 298.

[3] 朱江, 黄建伟, 亓洋洋, 等. 基于超越对数成本函数的航空公司延误成本测算[J]. 物流科技, 2020, 43(12): 35- 38, 45. [ZHU J, HUANG J W, QI Y Y, et al. Calculation of airline delay cost based on translog cost function[J]. Logistics Sci-Tech, 2020, 43(12): 35-38, 45.] 、[4] 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): 452-465. [WANG C Z, HU M H, YANG L, et al. Airport network delay prediction based on Agent model[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(7): 452-465.]

[5] WANG C, HU M, 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.

[6] 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.

[7] 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(5): 203-221.

[8] 罗赟骞, 陈志杰, 汤锦辉, 等. 采用支持向量机回归的航班延误预测研究 [J]. 交通运输系统工程与信息, 2015, 15(1): 143-149, 172. [LUO Y Q, CHEN Z J, TANG J H, et al. Flight delay prediction using support vector machine regression[J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(1): 143-149, 172.]

[9] 吴仁彪, 赵娅倩, 屈景怡, 等. 基于CBAM-CondenseNet 的航班延误波及预测模型[J]. 电子与信息学报, 2021, 43(1): 187-195. [WU R B, ZHAO Y Q, QU J Y, et al. Flight delay propagation prediction model based on CBAM-CondenseNet[J]. Journal of Electronics and Information Technology, 2021, 43(1): 187-195.]

[10] 姜雨, 陈名扬, 袁琪, 等. 基于时空图卷积神经网络的离港航班延误预测[J]. 北京航空航天大学学报, 2023, 49(5): 1044-1052. [JIANG Y, CHEN M Y, YUAN Q, et al. Convolution neural network based on the space-time map of departure flight delay prediction[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(5): 1044-1052.]

[11] 刘晓琳, 郭梦娇, 李卓. 基于自适应注意力图卷积循环网络的航班延误组合预测方法[J/OL]. 北京航空航天大学学报, (2023-02-28)[2023-09-01]. https://doi.org/ 10.13700/j.bh.1001-5965.2022.0990. [LIU X L, GUO M J, LI Z. Flight delay prediction based on attention-based adaptive graph convolution-Gated Recurrent Unit[J/ OL]. Journal of Beijing University of Aeronautics and Astronautics, (2023- 02- 28) [2023- 09- 01]. https://doi. org/10.13700/j.bh.1001-5965.2022.0990.]

[12] 姜雨, 袁琪, 胡志韬, 等. 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. [JIANG Y, YUAN Q, HU Z T, et al. Airport arrival and departure delay prediction based on meteorological factors[J]. Systems Engineering and Electronics, 2023, 45 (6): 1722-1731.]

[13] 中国民用航空局. 2020年民航行业发展统计公报[EB/ OL]. (2022-05-18) [2023-09-01]. http://www.caac.gov. cn/XXGK/XXGK/TJSJ/202205/t20220518_213297. html. [Civil Aviation Administration of China. In 2020, the civil aviation industry development statistical bulletin [EB/OL]. (2022-05-18) [2023-09-01]. http://www.caac. gov. cn/XXGK/XXGK/TJSJ/202205/t20220518 _ 213297 . html.]

[14] 李郅琴, 杜建强, 聂斌, 等. 特征选择方法综述[J]. 计算机工程与应用, 2019, 55(24): 10-19. [LI Z Q, DU J Q, NIE B, et al. Review of feature selection methods[J]. Computer Engineering and Applications, 2019, 55(24): 10-19.]

[15] 雷欣南, 林乐凡, 肖斌卿, 等. 小微企业违约特征再探索：基于SHAP解释方法的机器学习模型[J/OL]. 中国管理科学, (2022-03-21) [2023-09-01]. https://doi.org/ 10.16381/j.cnki.issn1003-207x.2021.0027. [LEI X N, LIN L F, XIAO B Q, et al. Re-exploration of small and micro enterprises' default characteristics based on machine learning models with SHAP[J/OL]. Chinese Journal of Management Science, (2022-03-21) [2023- 09- 01]. https://doi.org/10.16381/j.cnki.issn1003- 207x. 2021.0027.]

基于气象因素与特征选择的进港航班延误可解释预测研究

Explainable Prediction of Inbound Flight Delays Based on Meteorological Factors and Feature Selection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李善梅, 王雨鑫, 雷青蕾, 宋思霓, 王超. 终端区交通拥堵识别及其时空演化特性分析[J]. 交通运输系统工程与信息, 2023, 23(6): 120-132.
[2]	李艳华, 阳杰, 刘志硕, 邓杰. 考虑旅客跨楼中转的航空公司所属航站楼分配优化研究[J]. 交通运输系统工程与信息, 2023, 23(5): 298-311.
[3]	王建忠, 丁小芹, 王树伟. 考虑潜在冲突的进离场航班协同排序[J]. 交通运输系统工程与信息, 2023, 23(5): 312-320.
[4]	吴维, 林芷伊, 陈旭梅. 基于双层博弈模型的机场间航线网络协同演化研究[J]. 交通运输系统工程与信息, 2023, 23(4): 237-250.
[5]	胡小兵, 杨常澍, 周隽. 复杂城市环境下无人机路网模型研究[J]. 交通运输系统工程与信息, 2023, 23(4): 251-261.
[6]	彭宏勤, 张国伍. “双碳”目标下高铁与民航高质量发展策略——“交通7+1论坛”第五十九次会议[J]. 交通运输系统工程与信息, 2023, 23(3): 1-5.
[7]	赵桂红, 马晨傲, 赵巧同, 李建伏. 考虑收益的航空升舱服务产品动态定价方法[J]. 交通运输系统工程与信息, 2023, 23(3): 76-84.
[8]	胡小兵, 赵宇勃, 王瑞昕, 吴志冬, 曾志鸿. 基于组合优化的飞机定检任务调度优化方法研究[J]. 交通运输系统工程与信息, 2023, 23(3): 214-222.
[9]	王红勇, 张加豪, 许平. 基于复杂性的多扇区移交策略优化[J]. 交通运输系统工程与信息, 2023, 23(1): 284-294.
[10]	戢晓峰, 乔新. 建成环境对行人交通事故严重程度的非线性影响[J]. 交通运输系统工程与信息, 2023, 23(1): 314-323.
[11]	张勰, 肖恩媛, 刘宏志, 赵嶷飞, 王梦琦. 基于有限穿越可视图的进场航班流量波动特性研究[J]. 交通运输系统工程与信息, 2022, 22(6): 244-257.
[12]	温瑞英, 刘文瀚, 王红勇. 编队飞行中基于危险区域的后机最优位置研究[J]. 交通运输系统工程与信息, 2022, 22(5): 300-308.
[13]	唐小卫, 陈祯, 张生润, 丁叶. 繁忙机场机坪空间构型对航班离港滑行时间的影响[J]. 交通运输系统工程与信息, 2022, 22(5): 309-317.
[14]	韩博, 邓志强, 于敬磊, 石依琳, 于剑. 碳达峰目标下中国民航CO₂与NO_x减排协同效益分析[J]. 交通运输系统工程与信息, 2022, 22(4): 53-62.
[15]	蒋丽, 杨露, 梁昌勇, 董骏峰. 基于无人机的高层住宅最后“一百米”配送优化[J]. 交通运输系统工程与信息, 2022, 22(4): 236-245.