Machine learning applications in studies of the physical properties of active galactic nuclei based on photometric observations

Open Access

Table 2

Target variables, their domain range and error estimate from the SPIDERS catalogue (Coffey et al. 2019).

Target parameter	Notes	Training range	Error on the estimate
z	Redshift	[0.008,2.5]	–
log L_X	X-ray luminosity	[40.8,45.9]	~0.05 dex
log L_bol	Bolometric luminosity	[42.9,47.6]	~0.02 dex
log M_BH/M_⊙	Black hole mass	[6.2,10.4]	~0.02 dex
log λ_Edd	Eddington ratio	[-3.2,0.54]	~0.01 dex

Notes. The variables are presented in the order of their sequential prediction by the ML algorithm, as executed by the chain regressor.

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.