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

Open Access

Table 2

Comparison of CatBoost model performance on physical parameters with and without observational errors in input features but using the same dataset.

Parameter	Without errors					With errors
Parameter
	RMSE	NRMSE	MAE	Bias	η	RMSE	NRMSE	MAE	Bias	η
SFR	0.353	0.040	0.263	−0.010	0.011	0.336	0.038	0.250	0.001	0.011
SM	0.216	0.035	0.157	0.0003	0.011	0.206	0.033	0.148	0.001	0.012
Metallicity	0.104	0.068	0.079	−0.003	0.010	0.097	0.064	0.073	−0.0002	0.011

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).

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.