deep-REMAP: Parameterization of Stellar Spectra Using Regularized Multi-Task Learning

TL;DR

deep-REMAP is a novel multi-task learning framework that leverages synthetic and observational spectra to accurately predict stellar parameters, enhancing automated stellar characterization in large astronomical surveys.

Contribution

It introduces a regularized multi-task learning approach with an asymmetric loss function for probabilistic inference, improving stellar parameter predictions from spectral data.

Findings

Outperforms existing methods in predicting stellar parameters

Effectively extends to other stellar libraries and properties

Demonstrates superior predictive accuracy using synthetic and observational data

Abstract

Traditional spectral analysis methods are increasingly challenged by the exploding volumes of data produced by contemporary astronomical surveys. In response, we develop deep-Regularized Ensemble-based Multi-task Learning with Asymmetric Loss for Probabilistic Inference ($\rm{deep-REMAP}$), a novel framework that utilizes the rich synthetic spectra from the PHOENIX library and observational data from the MARVELS survey to accurately predict stellar atmospheric parameters. By harnessing advanced machine learning techniques, including multi-task learning and an innovative asymmetric loss function, $\rm{deep-REMAP}$ demonstrates superior predictive capabilities in determining effective temperature, surface gravity, and metallicity from observed spectra. Our results reveal the framework's effectiveness in extending to other stellar libraries and properties, paving the way for more sophisticated and automated techniques in stellar characterization.