Saved in:
Bibliographic Details
Main Authors: Bös, Cedric, Bortotto, Alessandro, Ben-Larbi, Mohamed Khalil
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.06105
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910077342973952
author Bös, Cedric
Bortotto, Alessandro
Ben-Larbi, Mohamed Khalil
author_facet Bös, Cedric
Bortotto, Alessandro
Ben-Larbi, Mohamed Khalil
contents Accurate thermospheric density prediction is crucial for reliable satellite operations in Low Earth Orbits, especially at high solar and geomagnetic activity. Physics-based models such as TIE-GCM offer high fidelity but are computationally expensive, while empirical models like NRLMSIS are efficient yet lack predictive power. This work presents a transformer-based model that forecasts densities up to three days ahead and is intended as a drop-in replacement for an empirical baseline. Unlike recent approaches, it avoids spatial reduction and complex input pipelines, operating directly on a compact input set. Validated on real-world data, the model improves key prediction metrics and shows potential to support mission planning.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06105
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Forecasting Thermospheric Density with Transformers for Multi-Satellite Orbit Management
Bös, Cedric
Bortotto, Alessandro
Ben-Larbi, Mohamed Khalil
Space Physics
Machine Learning
Accurate thermospheric density prediction is crucial for reliable satellite operations in Low Earth Orbits, especially at high solar and geomagnetic activity. Physics-based models such as TIE-GCM offer high fidelity but are computationally expensive, while empirical models like NRLMSIS are efficient yet lack predictive power. This work presents a transformer-based model that forecasts densities up to three days ahead and is intended as a drop-in replacement for an empirical baseline. Unlike recent approaches, it avoids spatial reduction and complex input pipelines, operating directly on a compact input set. Validated on real-world data, the model improves key prediction metrics and shows potential to support mission planning.
title Forecasting Thermospheric Density with Transformers for Multi-Satellite Orbit Management
topic Space Physics
Machine Learning
url https://arxiv.org/abs/2511.06105