Galaxy morphoto-Z with neural Networks (GaZNets) - I. Optimized accuracy and outlier fraction from imaging and photometry

Open Access

Table 2.

Statistical properties of the predictions.

CNN model	Out. fr.	μ_δz	NMAD
Lower redshit galaxies

GaZNet-81pix	0.004	0.001	0.015
GaZNet-C9I4	0.004	−0.002	0.015

higher redshift galaxies

GaZNet-81pix	0.15	−0.039	0.045
GaZNet-C9I4	0.124	−0.033	0.033

Notes. Outlier fraction, mean bias and NMAD (see Sect. 3.2.1) from the further tools tested in Sect. 4.2.

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.