Figure 1.
The parameter estimation performance of RRNet: the performance obviously decreased on spectra with low temperature, high temperature, or low metallicity. Since RRNet is proposed for the problem of the parameter estimation for the medium-resolution spectra from LAMOST DR7, this experiment is carried out on 110 500 LAMOST DR7 spectra which have observations in the APOGEE DR17/ASPCAP catalogue from common sources. The performance of the parameter estimation is measured by the difference (mean of absolute error, MAE) between the RRNet estimation and the reference result in the APOGEE DR17/ASPCAP catalogue. As the trained model and the complete model prediction results are not published by SPCANet, only the performance characteristics of RRNet are analysed in this experiment.

The parameter estimation performance of RRNet: the performance obviously decreased on spectra with low temperature, high temperature, or low metallicity. Since RRNet is proposed for the problem of the parameter estimation for the medium-resolution spectra from LAMOST DR7, this experiment is carried out on 110 500 LAMOST DR7 spectra which have observations in the APOGEE DR17/ASPCAP catalogue from common sources. The performance of the parameter estimation is measured by the difference (mean of absolute error, MAE) between the RRNet estimation and the reference result in the APOGEE DR17/ASPCAP catalogue. As the trained model and the complete model prediction results are not published by SPCANet, only the performance characteristics of RRNet are analysed in this experiment.

Close
This Feature Is Available To Subscribers Only

Sign In or Create an Account

Close

This PDF is available to Subscribers Only

View Article Abstract & Purchase Options

For full access to this pdf, sign in to an existing account, or purchase an annual subscription.

Close