Turbulence along the Runway Glide Path: The Invisible Hazard Assessment Based on a Wind Tunnel Study and Interpretable TPE-Optimized KTBoost Approach

Aircraft landings can be dangerous near airport runways due to wind variability. As a result, an aircraft could potentially miss approach or divert off its flight path. In this study, turbulence intensity along the runway glide path was investigated using scaled-down model of Hong Kong International Airport (HKIA) and complex terrain nearby built in TJ-3 atmospheric boundary layer tunnel. Different factors, including effect terrain, distance from threshold, assigned runway, direction, speed, were taken into consideration. Next, based on experimental results, we trained tested novel tree-structured Parzen estimator (TPE)-optimized kernel tree-boosting (KTBoost) model. The results obtained by TPE-optimized KTBoost outperformed other advanced machine learning models terms MAE (0.83), MSE (1.44), RMSE (1.20), R2 (0.89). permutation-based importance analysis also revealed that top three factors contributed high direction. presence shorter direction 90 degrees 165 all intensity.