Thermospheric Density and Reentry Prediction

Problem

Below about 600 km, atmospheric drag dominates the error budget, and drag is only as good as the density model behind it. JB2008, NRLMSIS 2.1 and DTM2020 disagree with each other and with reality, worst during geomagnetic storms. Reentry windows stay wide until late, and conjunction screening inherits the same uncertainty.

Capability

Reduced-order density modelling calibrated against real orbital behaviour rather than against another model: Starlink ephemerides assimilated through an Unscented Kalman Filter, comparing linear (POD with DMDc) and nonlinear (diffusion maps with m-PCE) reduction, each initialised from the three empirical baselines. The aim is a model fast enough for operational tracking and space traffic management.

Demonstrated result

Early stage — no published accuracy figure yet. The framework and assimilation pipeline are built and running as MPhil research by Ruoyan (Arthur) Zhao; the comparison against the baselines is in progress.

External use

Density error is the shared root cause behind wide reentry windows and weak conjunction screening, and it degrades orbit determination for the tracking and manoeuvre-detection work on this site.

Next partnership opportunity

Calibrating the model against your tracking or ephemeris data, or applying it to a specific reentry problem. Best suited to a co-funded or sponsored project while the method matures — see Partner with us.

Yang Yang
Senior Lecturer in Space Engineering

We turn sparse and noisy space-tracking data into reliable navigation and operational intelligence for safer satellite and cislunar missions, working across optical tracking, orbit determination, satellite manoeuvre detection and lunar PNT.