AI-supported estimation of safety critical wind shear-induced aircraft go-around events utilizing pilot reports

The occurrence of wind shear and severe thunderstorms during the final approach phase contributes to nearly half of all aviation accidents. Pilots usually employ the go-around procedure in order to lower the likelihood of an unsafe landing. However, multiple factors influence the go-arounds induced by wind shear. In order to predict the wind shear-induced go-around, this study utilized a cutting-edge AI-based Combined Kernel and Tree Boosting (KTBoost) framework with various data augmentation strategies. First, the KTBoost model was trained, tested, and compared to other Machine Learning models using the data extracted from Hong Kong International Airport (HKIA)-based Pilot Reports for the years 2017-2021. The performance evaluation revealed that the KTBoost model with Synthetic Minority Oversampling Technique - Edited Nearest Neighbor (SMOTE-ENN)- augmented data demonstrated superior performance as measured by the F1-Score (94.37%) and G-Mean (94.87%). Subsequently, the SHapley Additive exPlanations (SHAP) approach was employed to elucidate the interpretation of the KTBoost model using data that had been treated with the SMOTE-ENN technique. According to the findings, flight type, wind shear magnitude, and approach runway contributed the most to the wind shear-induced go-around. Compared to international flights, Hong Kong-based airlines endured the highest number of wind shear-induced go-arounds. Shear due to the tailwind contributed more to the go-around than the headwinds. The runways with the most wind shear-induced Go-arounds were 07C and 07R.

Go-around accidents and general aviation safety

INTRODUCTION

Changes in General Aviation (GA) accident rates, specifically in the go-around phase, are examined by comparing the number of accidents, the proportion of fatal accidents, and the proportion of certain causes of accidents over time.

METHODS

Two sets of accidents from 2000 to 2004 and from 2013 to 2017 were extracted from the National Transportation Safety Board (NTSB) online database.

RESULTS

Although the total number of GA accidents per landing significantly decreased over time, the proportion of fatal accidents in the go-around phase increased. Fatalities most often occurred in instrument meteorological conditions.

CONCLUSION

Advances in technology and training show improvements in GA accident rates, but not for accidents in the go-around phase.

PRACTICAL APPLICATIONS

Scenario-based learning is recommended to include specific instruction concerning the timing of go-around procedures in unstable flights.

Evaluating process-based and crew- centred approaches to procedure design in aviation: workload and performance changes in go-around manoeuvres

In this article, we compare and evaluate two methods of procedure design using an aircraft go-around (GA) as a test scenario. We contrast the manufacturer specified, crew-centric procedure with a redesigned process-centred perspective. We test the claim that the process-centred design can take into account situational factors more effectively and generate less workload. We report a heuristic assessment of the new procedure against design guidelines and an evaluation in a full-flight simulator at the German Aerospace Centre (DLR) using qualified airline pilots to assess workload and performance. Both the manufacturer specified and new procedure were employed in three GA scenarios representative of increasing operational complexity. Results demonstrate an advantage for the new procedure design in the most complex scenario. The new, process-based procedure can reduce reported crew workload and improve response flexibility in more complex scenarios, improving rated performance. This study suggests that the process-based account in procedure design has advantages when compared to the flight crew-centric approach. These advantages include enhanced flexibility, robustness and improved crew performance during GA.