Computational Solution to Prevent Aeronautics Accidents Cause by Wake Turbulence Using Machine Learning

Wake turbulence (WT) is a disturbance in the atmosphere observed behind an aircraft when it moves through the air. Several accidents and incidents have occurred and still occur worldwide as aircraft enter the WT of larger aircraft. Within such scenario, our study proposes a Machine Learning (ML) framework targeting the improvement of Automatic dependent surveillance-broadcast (ADS-B) alerts accuracy, so that pilots may avoid WT areas with the guidance of the developed system. The raw data is processed and transformed to show suitable features, which will enable the ML models to make predictions with high performance. Four prevailing ML methods (Naive Bayes-NB, Decision Tree, K-Nearest Neighbors-KNN and Backpropagation Neural Network-BP/NN) are used to predict the ADS-B alerts for pilot. The simulation results demonstrate that the NB and the KNN (K = 1 or 3) are the best prediction models in WT detection. The developed system establishes an intelligent ADS-B that generates visual and oral alerts to warn the pilot that the wake turbulent appears from other aircraft flying nearly.