基于随机森林的对流天气下终端区容量预测

毛利民, 彭 瑛, 李 杰, 郭聪聪, 康 博, 曹 正

系统工程理论与实践 ›› 2021, Vol. 41 ›› Issue (8) : 2125-2136.

PDF(1469 KB)
PDF(1469 KB)
系统工程理论与实践 ›› 2021, Vol. 41 ›› Issue (8) : 2125-2136. DOI: 10.12011/SETP2019-1650
论文

基于随机森林的对流天气下终端区容量预测

    毛利民1, 彭 瑛1, 李 杰1, 郭聪聪1, 康 博2, 曹 正2
作者信息 +

Random-forest based terminal capacity prediction under convective weather

    MAO Limin1, PENG Ying1, LI Jie1, GUO Congcong1, KANG Bo2, CAO Zheng2
Author information +
文章历史 +

摘要

分析了对流天气影响下的管制运行特点, 从空域、交通和气象的角度量化了影响终端区起降容量的特征, 进行了基于信息增益的特征筛选, 建立了基于随机森林的终端区小时起降容量预测模型. 以广州终端区为例, 使用10折交叉检验和自助法的模型评估方法以及均方误差和决定系数度量了模型的性能, 与基于最大流最小割解析模型的容量预测方法相比, 容量预测的绝对平均误差降低了83%, 绝对平均误差方差降低了80%.

Abstract

The air traffic control (ATC) operational characteristics under convective weather were analyzed. The features of the impacted terminal control area were quantified from the perspectives of airspace, traffic and meteorology. The information-gain based feature selection was carried out, and the terminal hourly take-off and landing capacity prediction model based on random forest was established. Taking the Guangzhou terminal area as an example, the 10-fold cross-validation and bootstrapping model evaluation methods were used to measure the model performance as well as mean square error (MSE) and determination coefficient (R2) metrics. Compared with the capacity prediction method based on the MAXFLOW-MINCUT analytical model, the mean absolute error (MAE) of the hourly prediction was reduced by 83% and the predicted variance was reduced by 80%.

关键词

空中交通管理 / 对流天气 / 容量预测 / 机器学习 / 随机森林

Key words

air traffic management / convective weather / capacity prediction / machine learning / random forest

引用本文

导出引用
毛利民 , 彭 瑛 , 李 杰 , 郭聪聪 , 康 博 , 曹 正. 基于随机森林的对流天气下终端区容量预测. 系统工程理论与实践, 2021, 41(8): 2125-2136 https://doi.org/10.12011/SETP2019-1650
MAO Limin , PENG Ying , LI Jie , GUO Congcong , KANG Bo , CAO Zheng. Random-forest based terminal capacity prediction under convective weather. Systems Engineering - Theory & Practice, 2021, 41(8): 2125-2136 https://doi.org/10.12011/SETP2019-1650
中图分类号: V355   

参考文献

[1] 中国民用航空局. 《2018年民航行业发展统计公报》[EB/OL].[2019-05-08]. http://www.caac.gov.cn/XXGK/XXGK/TJSJ/201905/t20190508_196033.html.
[2] DeLaura R, Allan S. Route selection decision support in convective weather:A case study of the effects of weather and operational assumptions on departure throughput[C]//5th Eurocontrol/FAA ATM R&D Seminar, 2003:1-10.
[3] Underhill N, Delaura R. Route availability planning tool evaluation visualizations for the New York and Chicago departure flows[M/OL]//Infotech@Aerospace 2011. American Institute of Aeronautics and Astronautics, 2011. https://doi.org/10.2514/6.2011-1440.
[4] Krozel J, Penny S, Prete J, et al. Comparison of algorithms for synthesizing weather avoidance routes in transition airspace[C]//AIAA Guidance, Navigation, and Control Conference, 2004:1-16.
[5] Krozel J, Prete J, Mitchell J, et al. Capacity estimation for super-dense operations[C]//AIAA Guidance, Navigation and Control Conference and Exhibit, 2008:1-15.
[6] Song L, Wanke C, Greenbaum D, et al. Predicting sector capacity under severe weather impact for traffic flow management[C]//7th AIAA Aviation Technology, Integration, and Operations Conference, 2007:7887.
[7] Zou J, Krozel J W, Krozel J, et al. Two methods for computing directional capacity given convective weather constraints[C]//AIAA Guidance, Navigation, and Control Conference, 2009:10-13.
[8] 常茂军. 机场终端区容量动态预测方法研究[D]. 南京:南京航空航天大学, 2007. Chang M J. Research on the method of airport terminal airspace capacity dynamic estimation[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2007.
[9] 李印凤, 胡明华, 彭瑛, 等. 基于阻塞流的多场景终端区容量影响机理[J]. 西南交通大学学报, 2014, 49(5):928-934. Li Y F, Hu M H, Peng Y, et al. Effect mechanism of multi-scenarios terminal capacity based on flow decomposition barrier[J]. Journal of Southwest Jiaotong University, 2014, 49(5):928-934.
[10] 赵征. 空域容量评估与预测技术研究[D]. 南京:南京航空航天大学, 2015. Zhao Z. Research on airspace capacity assessment and forecast[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2015.
[11] Ramamoorthy K, Hunter G. Simulation-based airport capacity estimation[C]//2013 Aviation Technology, Integration, and Operations Conference, 2013:1-14.
[12] Song L, Wanke C, Greenbaum D. Predicting sector capacity for TFM decision support[C]//6th AIAA Aviation Technology, Integration, and Operations Conference, 2006:1-10.
[13] Song L, Wanke C, Greenbaum D. Predicting sector capacity for TFM decision support[C]//7th ATM Seminar, 2007:1-10.
[14] Chandramouleeswaran K R, Krzemien D, Burn S K, et al. Machine learning prediction of airport delays in the US air transportation network[C]//2018 Aviation Technology, Integration, and Operations Conference, 2018:1-10.
[15] Ukai T, Chao H, DeLaurentis D. An aircraft deployment prediction model using machine learning techniques[C]//17th AIAA Aviation Technology, Integration, and Operations Conference, 2017:1-14.
[16] Altinok A, Kiran R, Bue B, et al. Modeling key predictors of airport runway configurations using learning algorithms[C]//2018 Aviation Technology, Integration, and Operations Conference, 2018:1-16.
[17] Zhu G, Matthews C, Wei P, et al. En route flight time prediction under convective weather events[C]//2018 Aviation Technology, Integration, and Operations Conference, 2018:1-16.
[18] 周雄飞. 恶劣天气影响下扇区动态容量预测[D]. 南京:南京航空航天大学, 2016. Zhou X F. Sector dynamic capacity forecast under severe weather[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2016.
[19] 蒋昕. 危险天气下的动态航班改航研究[D]. 南京:南京航空航天大学, 2016. Jiang X. Research on dynamic flight rerouting in severe weather[D]. Nanjing:Nanjing University of Aeronautics and Astronautics, 2016.
[20] 田勇, 杨双双, 万莉莉, 等. 扇区动态容量评估方法研究[J]. 系统工程理论与实践, 2014, 34(8):2163-2169. Tian Y, Yang S S, Wan L L, et al. Research on the method of sector dynamic capacity evaluation[J]. Systems Engineering-Theory & Practice, 2014, 34(8):2163-2169.
[21] DeLaura R, Evans J. An exploratory study of modeling enroute pilot convective storm flight deviation behavior[R]. Lexington, Massachusetts:Lincoln Laboratory, Massachusetts Institute of Technology, 2006.
[22] Krozel J, Mitchell J, Polishchuk V, et al. Capacity estimation for airspaces with convective weather constraints[C]//AIAA Guidance, Navigation and Control Conference and Exhibit, 2007:1-15.
[23] Mitchell J, Polishchuk V, Krozel J. Airspace throughput analysis considering stochastic weather[C]//AIAA Guidance, Navigation and Control Conference and Exhibit, 2006:1-19.
[24] Hagberg A, Schult D, Swart P. Exploring network structure, dynamics, and function using NetworkX[C]//7th Python in Science Conference (SciPy2008), 2008:11-15.
[25] Pedregosa F, Varoquaux G, Gramfort A. Scikit-learn:Machine learning in Python[J]. Journal of Machine Learning Research, 2011, 12(10):2825-2830.
[26] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.

基金

国家自然科学基金(71731001)
PDF(1469 KB)

607

Accesses

0

Citation

Detail

段落导航
相关文章

/