SkySoft ATM has curated this dataset for the Innosuisse MALAT project, aimed at improving forecasts for aircraft climb and descent rates
The dataset comprises detailed altitude tracking (`TRACK_ALTITUDE`) for over 25,000 flights across European airspace, amassed over four different weeks. Each flight track is matched with its corresponding cleared flight level (`CFL`) and supplemented with anonymized `AIRCRAFT_TYPE` and can be grouped using the `FLIGHT_ID` field.
If you use this database, please cite the following publication:
@INPROCEEDINGS{Pannatier_ECMLPKDD_2024,
author = {Pannatier, Arnaud and Courdier, Evann and Fleuret, Francois},
keywords = {Autoregressive models, Permutations, Rejection Sampling, transformers},
projects = {MALAT},
month = sep,
title = {σ-GPTs: A New Approach to Autoregressive Models.},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2024},
pdf = {https://publications.idiap.ch/attachments/papers/2024/Pannatier_ECMLPKDD_2024.pdf}
}