Forecasting Thermospheric Density with Transformers for Multi-Satellite Orbit Management

TL;DR

This paper introduces a transformer-based model for predicting thermospheric density up to three days ahead, aiming to enhance satellite orbit management by balancing accuracy and computational efficiency.

Contribution

The work presents a novel transformer model that operates directly on compact inputs, outperforming empirical baselines without complex preprocessing.

Findings

Model improves prediction metrics on real-world data.

Operates directly on compact input set without spatial reduction.

Supports satellite mission planning with accurate forecasts.

Abstract

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.