Interpretable ensemble imbalance learning strategies for the risk assessment of severe-low-level wind shear based on LiDAR and PIREPs.

Autor: Khattak A; Key Laboratory of Infrastructure Durability and Operation Safety in Airfield of Civil Aviation Administration of China, College of Transportation Engineering, Tongji University, Jiading, Shanghai, China., Chan PW; Hong Kong Observatory, Kowloon, Hong Kong, China., Chen F; Key Laboratory of Infrastructure Durability and Operation Safety in Airfield of Civil Aviation Administration of China, College of Transportation Engineering, Tongji University, Jiading, Shanghai, China., Peng H; Key Laboratory of Infrastructure Durability and Operation Safety in Airfield of Civil Aviation Administration of China, College of Transportation Engineering, Tongji University, Jiading, Shanghai, China.
Jazyk: angličtina
Zdroj: Risk analysis : an official publication of the Society for Risk Analysis [Risk Anal] 2024 May; Vol. 44 (5), pp. 1084-1102. Date of Electronic Publication: 2023 Sep 13.
DOI: 10.1111/risa.14215
Abstrakt: The occurrence of severe low-level wind shear (S-LLWS) events in the vicinity of airport runways poses a significant threat to flight safety and exacerbates a burgeoning problem in civil aviation. Identifying the risk factors that contribute to occurrences of S-LLWS can facilitate the improvement of aviation safety. Despite the significant influence of S-LLWS on aviation safety, its occurrence is relatively infrequent in comparison to non-SLLWS incidents. In this study, we develop an S-LLWS risk prediction model through the utilization of ensemble imbalance learning (EIL) strategies, namely, BalanceCascade, EasyEnsemble, and RUSBoost. The data for this study were obtained from PIREPs and LiDAR at Hong Kong International Airport. The analysis revealed that the BalanceCascade strategy outperforms EasyEnsemble and RUSBoost in terms of prediction performance. Afterward, the SHapley Additive exPlanations (SHAP) interpretation tool was used in conjunction with the BalanceCascade model for the risk assessment of various factors. The four most influential risk factors, according to the SHAP interpretation tool, were hourly temperature, runway 25LD, runway 25LA, and RWY (encounter location of LLWS). S-LLWS was likely to happen at Runway 25LD and Runway 25LA in temperatures ranging from low to moderate. Similarly, a high proportion of S-LLWS events occurred near the runway threshold, and a relatively small proportion occurred away from it. The EIL strategies in conjunction with the SHAP interpretation tool may accurately predict the S-LLWS without the need for data augmentation in the data pre-processing phase.
(© 2023 Society for Risk Analysis.)
Databáze: MEDLINE
Externí odkaz: