Exploring galactic properties with machine learning - Predicting star formation, stellar mass, and metallicity from photometric data

Open Access

Table 3

Performance of CatBoost model for different kinds of galaxies.

Class	Parameter	RMSE	NRMSE	MAE	Bias	η
	SFR	0.297	0.045	0.220	0.017	0.010
Passive	SM	0.149	0.025	0.099	−0.018	0.009

AGN	SFR	0.379	0.092	0.287	0.041	0.011
	SM	0.184	0.037	0.134	0.012	0.012

	SFR	0.391	0.065	0.288	0.049	0.013
Composite	SM	0.217	0.052	0.162	0.009	0.010

	SFR	0.327	0.040	0.244	−0.023	0.011
Star forming	SM	0.225	0.036	0.167	0.003	0.011

Notes. The SFR is measured in units of log(SFR [M_⊙ yr⁻¹]), and SM is also measured in units of log(M* [M_⊙]).

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.