Fig. 6.

Learning curve for the spectral emulator. The error on the training sample as well as the test sample is shown as a function of the number of models used in the training. The quoted errors are the mean of the individual errors, which in turn are the MFE for each spectrum. For each training size, we select five different realizations at random and average the resulting errors.
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.