Forecasting a Complete Picture of Future Launches in Terms of Orbital Region and Physical Parameters
Wiebke RETAGNE, Camilla COLOMBO
Abstract This paper provides a step-by-step guide to go from a given future number of launches to a complete picture in terms of orbital region and physical parameters. This paper only describes non-constellation launches. For these non-constellation launches distributions are built using historical data from DISCOS. Here, the orbital parameter distribution is built using Gaussian-Mixture Models. The object class is determined from a simple probability distribution. A special focus is given to the mass of the objects, since this is an important quantity to be considered when talking about the evolution of the space environment. For the mass, an XGBoost algorithm is employed, which uses the other object characteristics as an input. Finally, the area of the object is determined based on the mass.
Keywords
Launch Traffic, Launch Trends, Space Debris Evolution, Machine Learning, Historical Sampling
Published online 7/20/2026, 6 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Wiebke RETAGNE, Camilla COLOMBO, Forecasting a Complete Picture of Future Launches in Terms of Orbital Region and Physical Parameters, Materials Research Proceedings, Vol. 69, pp 994-999, 2026
DOI: https://doi.org/10.21741/9781644904251-172
The article was published as article 172 of the book CEAS – AIDAA Conference 2025
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] European Space Agency. DISCOS: Database and Information System Characterising Objects in Space. https://discosweb.esoc.esa.int/, 2024. Accessed: 2025-07-21.
[2] Alyssa P. Manis, Mark J. Matney, Phillip D. Anz-Meador, and Andrew B. Vavrin. Time-dependent satellite explosion probabilities for long-term orbital debris environment mod-eling. Journal of Spacecraft and Rockets, 62(3):989-998, 2025. https://doi.org/10.2514/1.A36118
[3] Douglas Reynolds. Gaussian Mixture Models, pages 659-663. Springer US, Boston, MA, 2009. https://doi.org/10.1007/978-0-387-73003-5_196
[4] Callum J. Wilson, Massimiliano Vasile, Jinglang Feng, Keiran McNally, Alfredo Ant’on, and Francesca Letizia. Modelling future launch traffic and its effect on the leo operational environment. In AIAA SciTech 2024 Forum, Orlando, Florida, United States, 2024. American Institute of Aeronautics and Astronautics, AIAA. Peer-reviewed, accepted author manuscript. https://doi.org/10.2514/6.2024-1814
[5] Gideon Schwarz. Estimating the dimension of a model. The Annals of Statistics, 6(2):461-464, March 1978. https://doi.org/10.1214/aos/1176344136
[6] Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. CoRR, abs/1603.02754, 2016. https://doi.org/10.1145/2939672.2939785
[7] A. S. Botelho and A. R. C. Xavier Jr. A unified satellite taxonomy proposal based on mass and size. Advances in Aerospace Science and Technology, 4:57-73, 2019. https://doi.org/10.4236/aast.2019.44005
[8] NASA. Sts-116 mission overview. https://www.nasa.gov/mission/sts-116/, 2006. Accessed: 2025-11-06.
[9] European Space Agency (ESA). Envisat mission overview. https://www.esa.int/ Applications/Observing_the_Earth/Envisat/, 2002. Accessed: 2025-11-06.

