Wake Vortex Prediction and Turbulence Avoidance with Risk Factor Analysis

Abstract—Wake turbulence poses a critical safety threat in aviation, especially during takeoff and landing. This project leverages machine learning to dynamically predict turbulence risk using real-time aircraft data, environmental conditions, and flight scenarios. A custom risk formula incorporates continuous aircraft weight categories, required separation time, and weather factors. Visualization is achieved using PyOpenGL and Tkinter, with data sourced from MSFS and FlightRadar24. Monte Carlo simulations across 12 aircraft pairs yielded 83.3% accuracy. The system offers real-time risk assessment and 3D simulation, enabling smarter air traffic control and paving the way for safer, adaptive wake turbulence mitigation in congested airspaces.