Flight Trajectory Prediction Enabled By Time-frequency Wavelet Transform

This article discusses an innovative wavelet transform-based framework for flight trajectory prediction, which is a crucial and challenging task in air traffic control. An encoder-decoder neural architecture is developed to estimate wavelet components, focusing on the effective modeling of global flight trends and local motion details. The proposed framework exhibits higher accuracy than other comparative baselines, obtaining improved prediction performance in terms of four measurements, especially in the climb and descent phase with maneuver control.