Photometric redshift estimation with convolutional neural networks and galaxy images: Case study of resolving biases in data-driven methods

Open Access

Table 1

Data coverage in spectroscopic redshift and r-band magnitude.

	z_min(z′_min) ^(*)	z_max(z′_max) ^(*)	# Initial Bins (n)	Bin Size	# Appended Bins (left/right) ^(*)
SDSS	0.0 (−0.2)	0.4 (0.6)	180	2.2 × 10⁻³	90/90
CFHTLS	0.0 (−2.0)	4.0 (8.0)	1000	4.0 × 10⁻³	500/1,000

	r_min	r_max	# Input Rows (2m − 1)	Row Size	# Output Bins (m)

SDSS	12.5	18.0	11	0.5	6
CFHTLS	16.0	25.5	19	0.5	10

Notes. ^(*)The redshift range is extended in step 3 by appending additional bins with the original bin size to either side of the initial redshift output. z′_min and z′_max denote the new boundaries after extension.

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.