Machine learning the gap between real and simulated nebulae - A domain-adaptation approach to classify ionised nebulae in nearby galaxies

Open Access

Fig. 6.

Same plots as in Fig. 4, but considering both the NN and the DANN trained over a noise-augmented dataset with S/N ∼ 40 on Hβ in the source domain (see text in Sec. 4.2). Noise augmentation leads to better performances on the target domain for both the NN and the DANN.

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.