This open source tool provides 27-day forecasts of the solar radio flux at 10.7 cm (the
F10.7), along with its associated forecast uncertainty, for spacecraft and space debris
operators and researchers in Low Earth Orbit (LEO). Acting as a proxy for solar activity, the
F10.7 is routinely used by thermospheric density models which are used for orbit
determination and propagation, and consequently critical activities such as collision
avoidance and re-entry campaigns. The forecasts and uncertainties are generated using a
deep ensemble of models based on the novel N-BEATS deep residual network architecture,
as described in [1].
[1] Stevenson, E., Rodriguez-Fernandez, V., Minisci, E., Camacho, D. (2021). A Deep
Learning Approach to Solar Radio Flux Forecasting. Acta Astronautica. ISSN 0094-5765,