Fig. 2.
Download original image
Schematic overview of our neural network architecture. Four solar wind parameters form the input vector X (in this example B, log nO7+/nO6+, np, and Tp), the hidden layer contains a variable number of neurons nh, and the output yrec is the remaining solar wind parameter (in this example vp). Each layer is fully connected by weights that are represented by arrows.
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.