Kp forecasting with a recurrent neural network | Journal of Space Weather and Space Climate

System Science: Application to Space Weather Analysis, Modelling, and Forecasting

Open Access

Fig. 5

(A) 6528 Kp predictions 01/01/2017–09/30/17 from a network trained on the original Wing model inputs: B_z, n, V, |B|. (B) Frequency of Kp values for full data set 1986–2016 and 2017 predictions. The model consistently predicts Kp values lower than the actual measured values.

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.