Learning to Land Anywhere: Transferable Generative Models for Aircraft Trajectories
This addresses data scarcity for Air Traffic Management solutions at secondary and regional airports, enabling realistic synthetic trajectory generation with limited historical records.
The paper tackles the problem of data scarcity for aircraft trajectory generation at secondary airports by investigating whether generative models trained on data-rich airports can be efficiently adapted to data-scarce ones using transfer learning. Results show that diffusion-based models achieve competitive performance with only 5% of target data and reach baseline-level performance with 20%, reducing data requirements substantially.
Access to trajectory data is a key requirement for developing and validating Air Traffic Management (ATM) solutions, yet many secondary and regional airports face severe data scarcity. This limits the applicability of machine learning methods and the ability to perform large-scale simulations or "what-if" analyses. In this paper, we investigate whether generative models trained on data-rich airports can be efficiently adapted to data-scarce airports using transfer learning. We adapt state-of-the-art diffusion- and flow-matching-based architectures to the aviation domain and evaluate their transferability between Zurich (source) and Dublin (target) landing trajectory datasets. Models are pretrained on Zurich and fine-tuned on Dublin with varying amounts of local data, ranging from 0% to 100%. Results show that diffusion-based models achieve competitive performance with as little as 5% of the Dublin data and reach baseline-level performance around 20%, consistently outperforming models trained from scratch across metrics and visual inspections. Latent flow matching and latent diffusion models also benefit from pretraining, though with more variable gains, while flow matching models show weaker generalization. Despite challenges in capturing rare trajectory patterns, these findings demonstrate the potential of transfer learning to substantially reduce data requirements for trajectory generation in ATM, enabling realistic synthetic data generation even in environments with limited historical records.