Prediction of Aircraft Go-Around during Wind Shear Using the Dynamic Ensemble Selection Framework and Pilot Reports

被引:4
|
作者
Khattak, Afaq [1 ]
Chan, Pak-Wai [2 ]
Chen, Feng [1 ]
Peng, Haorong [3 ]
机构
[1] Tongji Univ, Key Lab Infrastructure Durabil & Operat Safety Air, 4800 Caoan Rd,Jiading, Shanghai 201804, Peoples R China
[2] Hong Kong Observ, Kowloon, 134A Nathan Rd, Hong Kong, Peoples R China
[3] Shanghai Res Ctr Smart Mobil & Rd Safety, Shanghai 200092, Peoples R China
基金
中国国家自然科学基金;
关键词
wind shear; go-around; machine learning; dynamic ensemble selection; SHapley Additive exPlanations; DECISION-MAKING; AVIATION; LIDAR;
D O I
10.3390/atmos13122104
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Pilots typically implement the go-around protocol to avoid landings that are hazardous due to wind shear, runway excursions, or unstable approaches. Despite its rarity, it is essential for safety. First, in this study, we present three Dynamic Ensemble Selection (DES) frameworks: Meta-Learning for Dynamic Ensemble Selection (META-DES), Dynamic Ensemble Selection Performance (DES-P), and K-Nearest Oracle Elimination (KNORAE), with homogeneous and heterogeneous pools of machine learning classifiers as base estimators for the prediction of aircraft go-around in wind shear (WS) events. When generating a prediction, the DES approach automatically selects the subset of machine learning classifiers which is most probable to perform well for each new test instance to be classified, thereby making it more effective and adaptable. In terms of Precision (86%), Recall (83%), and F1-Score (84%), the META-DES model employing a pool of Random Forest (RF) classifiers outperforms other models. Environmental and situational factors are subsequently assessed using SHapley Additive exPlanations (SHAP). The wind shear magnitude, corridor, time of day, and WS altitude had the greatest effect on SHAP estimation. When a strong tailwind was present at low altitude, runways 07R and 07C were highly susceptible to go-arounds. The proposed META-DES with a pool of RF classifiers and SHAP for predicting aircraft go-around in WS events may be of interest to researchers in the field of air traffic safety.
引用
收藏
页数:18
相关论文
共 5 条
  • [1] Explainable Boosting Machine for Predicting Wind Shear-Induced Aircraft Go-around based on Pilot Reports
    Afaq Khattak
    Pak-wai Chan
    Feng Chen
    Haorong Peng
    KSCE Journal of Civil Engineering, 2023, 27 : 4115 - 4129
  • [2] Explainable Boosting Machine for Predicting Wind Shear-Induced Aircraft Go-around based on Pilot Reports
    Khattak, Afaq
    Chan, Pak-wai
    Chen, Feng
    Peng, Haorong
    KSCE JOURNAL OF CIVIL ENGINEERING, 2023, 27 (10) : 4115 - 4129
  • [3] AI-supported estimation of safety critical wind shear-induced aircraft go-around events utilizing pilot reports
    Khattak, Afaq
    Zhang, Jianping
    Chan, Pak-Wai
    Chen, Feng
    Matara, Caroline Mongina
    HELIYON, 2024, 10 (07)
  • [4] A machine learned go-around prediction model using pilot-in-the-loop simulations
    Dhief, Imen
    Alam, Sameer
    Lilith, Nimrod
    Mean, Chan Chea
    TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES, 2022, 140
  • [5] Pilot Flying and Pilot Monitoring's Aircraft State Awareness During Go-Around Execution in Aviation: A Behavioral and Eye Tracking Study
    Dehais, Frederic
    Behrend, Julia
    Peysakhovich, Vsevolod
    Causse, Mickael
    Wickens, Christopher D.
    INTERNATIONAL JOURNAL OF AEROSPACE PSYCHOLOGY, 2017, 27 (1-2): : 15 - 28