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

Abstract

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.