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

Open Access

Table 1

Comparative evaluation metrics of ML models (CatBoost and WDNN) for the physical parameters SFR, SM, and metallicity.

Parameter	CatBoost					WDNN
Parameter
	RMSE	NRMSE	MAE	Bias	η	RMSE	NRMSE	MAE	Bias	η
SFR	0.349	0.040	0.259	0.002	0.011	0.351	0.040	0.260	0.001	0.011
SM	0.209	0.034	0.146	0.001	0.013	0.210	0.034	0.147	0.001	0.013
Metallicity	0.109	0.064	0.082	5.354e-05	0.011	0.110	0.065	0.083	0.002	0.010

Notes. The SFR is measured in units of log(SFR [M_⊙yr⁻¹]); SM is also measured in units of log(M* [M_⊙]), and metallicity is represented as 12 + log(O/H). All numerical values presented in the tables have been rounded to the third decimal place for clarity.

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.