Terminal Airspace

Terminal airspace management is focused on improving the safety and efficiency of aircraft operations near airports, primarily through accurate prediction and modeling of flight trajectories. Current research heavily utilizes data-driven approaches, employing machine learning models like neural networks (including transformers and seq2seq architectures) and Gaussian mixture models to forecast aircraft movements with high temporal resolution, leveraging large datasets of ADS-B, surface movement, and even multimodal data (including images and ATC communications). These advancements enable improved air traffic control, proactive risk assessment, and optimized resource allocation, contributing significantly to safer and more efficient air travel.