English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

This work proposes a Residual Recurrent Neural Network (RRNet) forsynthetically extracting spectral information, and estimating stellaratmospheric parameters together with 15 chemical element abundances formedium-resolution spectra from Large Sky Area Multi-Object Fiber SpectroscopicTelescope (LAMOST). The RRNet consists of two fundamental modules: a residualmodule and a recurrent module. The residual module extracts spectral featuresbased on the longitudinally driving power from parameters, while the recurrentmodule recovers spectral information and restrains the negative influences fromnoises based on Cross-band Belief Enhancement. RRNet is trained by the spectrafrom common stars between LAMOST DR7 and APOGEE-Payne catalog. The 17 stellarparameters and their uncertainties for 2.37 million medium-resolution spectrafrom LAMOST DR7 are predicted. For spectra with S/N >= 10, the precision ofestimations Teff and log g are 88 K and 0.13 dex respectively, elements C, Mg,Al, Si, Ca, Fe, Ni are 0.05 dex to 0.08 dex, and N, O, S, K, Ti, Cr, Mn are0.09 dex to 0.14 dex, while that of Cu is 0.19 dex. Compared with StarNet andSPCANet, RRNet shows higher accuracy and robustness. In comparison to ApachePoint Observatory Galactic Evolution Experiment and Galactic Archaeology withHERMES surveys, RRNet manifests good consistency within a reasonable range ofbias. Finally, this work releases a catalog for 2.37 million medium-resolutionspectra from the LAMOST DR7, the source code, the trained model and theexperimental data respectively for astronomical science exploration and dataprocessing algorithm research reference.

A Model RRNet for Spectral Information Exploitation and LAMOST Medium-resolution Spectrum Parameter Estimation