GEO manoeuvre detection and pattern of life
A geostationary satellite changes its behaviour and the people responsible for the catalogue find out late, or not at all. The hard part is not seeing that the residuals moved — it is deciding whether that movement was a real manoeuvre, a mismodelled solar radiation pressure, or simply a bad track. Get that call wrong in one direction and you lose custody of the object; get it wrong in the other and you generate alarms nobody trusts.
Doing this at the scale of the GEO belt makes it worse. Analyst-led assessment does not scale to hundreds of objects observed nightly, and detectors trained on assumed dynamics degrade quietly as the population and operating practices change around them.
Capability
We develop manoeuvre detection and pattern-of-life identification from optical observations:
- OPAL: a labelled optical dataset for detector training and evaluation.
- Detection: image-based and time-series transformer models, benchmarked against residual thresholds.
- Pattern of life: combining detections to characterise an object’s behaviour over time.
The project is led by Michael Ling through the NSW Space Research Network. Related, but distinct, is GEO tracklet-to-orbit association: Yuting (Angela) Ng is researching range/range-constrained admissible regions for associating short optical arcs with GEO orbits, including manoeuvring objects.
Demonstrated result
- Funded as a 2025–2026 NSW Space Research Network pilot, in collaboration with Macquarie University and the University of Adelaide.
- OPAL and transformer-based manoeuvre detection have been presented at UNSW (slides).
- Angela Ng’s tracklet-to-orbit association uses a separate range/range-constrained approach. View her presentation deck for the 2026 Australian Space Domain Awareness and Space Traffic Management Conference (PDF).
Conference presentation
Michael Ling will present Optical Pattern of Life Analysis Library (OPAL) at the 2026 Australian Space Domain Awareness and Space Traffic Management Conference. The work explores classifying satellite patterns of life from optical angles using time-series transformers.
View the OPAL presentation deck (PDF).
External use
The project is co-delivered with Macquarie University under NSW Space Research Network funding, and it feeds the NSW Space Research Network white paper on Space Domain Awareness.
Next partnership opportunity
A manoeuvre and pattern-of-life assessment on your GEO or LEO time series: a labelled event list over the period you care about, and detection performance benchmarked against your current baseline, with false-alarm behaviour stated openly. See Partner with us.