Space Weather Driven
Cloud Cover & Moonlight
Combined Prediction
Aurora Hunter decomposes visibility forecasting into two physically distinct stages, multiplied into a single calibrated probability.
A calibrated XGBoost model trained on multi-station all-sky camera archives, driven by live NOAA solar wind and geomagnetic data (Kp, Bz, Newell coupling) in AACGM magnetic coordinates.
A calibrated logistic regression estimating whether an occurring aurora is actually observable, from cloud cover (Open-Meteo) and moonlight conditions.
The product P(visible) = P(occurring) × P(clear | occurring) gives a well-calibrated probability you can act on.
Retrospective validation used archived OMNI solar-wind data and ERA5 cloud reanalysis at three Nordic stations (magnetic latitude 65–67°). This site runs the same models on real-time NOAA SWPC feeds and cloud forecasts, so its skill is expected to be lower than the published scores. Probabilities refer to a clean auroral camera view, used as a proxy for good naked-eye viewing; outside the validated latitude band and above Kp 5 they are extrapolations.