Unmasking the physical information inherent to interstellar spectral line profiles with machine learning - I. Application of LTE to HCN and HNC transitions

Home

All issues

Volume 698 (May 2025)

A&A, 698 (2025) A286

Full HTML

Open Access

Table A.4

Performance metrics and ratios predictions of HNC/HCN for the cold source R CrA IRS 7B from the RF, XGB, and MLP models.

RF
Spectral lines	${\bar{R}}_{t r a i n}^{2}$ $\bar{R}_{train}^{2}$	${\bar{R}}_{t e s t}^{2}$ $\bar{R}_{test}^{2}$	HNC/HCN	Std _pred	depth
HNC 3–2	0.80	0.77	0.11	0.004	6
HCN 3–2 HNC 3–2	0.99	0.98	0.28	0.03	12
XGB
Spectral lines	${\bar{R}}_{t r a i n}^{2}$ $\bar{R}_{train}^{2}$	${\bar{R}}_{t e s t}^{2}$ $\bar{R}_{test}^{2}$	HNC/HCN	Std_pred	depth	learning rate
HNC 3–2	0.86	0.84	0.11	0.01	3	0.03
HCN 3–2 HNC 3–2	0.99	0.98	0.29	0.08	5	0.05
MLP
Spectral lines	${\bar{R}}_{t r a i n}^{2}$ $\bar{R}_{train}^{2}$	${\bar{R}}_{t e s t}^{2}$ $\bar{R}_{test}^{2}$	HNC/HCN	Std_pred
HNC 3–2	0.77	0.75	0.34	0.1
HCN 3–2 HNC 3–2	0.99	0.99	0.004	0.008

Notes. Likewise Table A.1, mean values of the coefficients of determination ( ${\bar{R}}_{t r a i n}^{2}$ $\bar{R}_{{train}}^{2}$ and ${\bar{R}}_{t e s t}^{2}$ $\bar{R}_{{test}}^{2}$ ) are provided for the three models.

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.