A Machine Learning Method to Infer Fundamental Stellar Parameters from Photometric Light Curves

Abstract

A fundamental challenge for wide-field imaging surveys is obtaining follow-up spectroscopic observations: there are > $10^9$ photometrically cataloged sources, yet modern spectroscopic surveys are limited to ~few x $10^6$ targets. As we approach the Large Synoptic Survey Telescope (LSST) era, new algorithmic solutions are required to cope with the data deluge. Here we report the development of a machine-learning framework capable of inferring fundamental stellar parameters (Teff, log g, and [Fe/H]) using photometric-brightness variations and color alone. A training set is constructed from a systematic spectroscopic survey of variables with Hectospec/MMT. In sum, the training set includes ~9000 spectra, for which stellar parameters are measured using the SEGUE Stellar Parameters Pipeline (SSPP). We employed the random forest algorithm to perform a non-parametric regression that predicts Teff, log g, and [Fe/H] from photometric time-domain observations. Our final, optimized model produces a cross-validated root-mean-square error (RMSE) of 165 K, 0.39 dex, and 0.33 dex for Teff, log g, and [Fe/H], respectively. Examining the subset of sources for which the SSPP measurements are most reliable, the RMSE reduces to 125 K, 0.37 dex, and 0.27 dex, respectively, comparable to what is achievable via low-resolution spectroscopy. For variable stars this represents a ~12-20% improvement in RMSE relative to models trained with single-epoch photometric colors. As an application of our method, we estimate stellar parameters for ~54,000 known variables. We argue that this method may convert photometric time-domain surveys into pseudo-spectrographic engines, enabling the construction of extremely detailed maps of the Milky Way, its structure, and history.

References in corpus (31)

• Maps of Dust IR Emission for Use in Estimation of Reddening and CMBR Foregrounds
• The Sloan Digital Sky Survey: Technical Summary
• The generalised Lomb-Scargle periodogram. A new formalism for the floating-mean and Keplerian periodograms
• The Palomar Transient Factory: System Overview, Performance and First Results
• The Sloan Digital Sky Survey Quasar Catalog V. Seventh Data Release
• Kepler Input Catalog: Photometric Calibration and Stellar Classification
• The Milky Way Tomography with SDSS: II. Stellar Metallicity
• SkyMapper and the Southern Sky Survey
• The SEGUE Stellar Parameter Pipeline. I. Description and Initial Validation Tests
• Hectospec, the MMT's 300 Optical Fiber-Fed Spectrograph
• SDSS Standard Star Catalog for Stripe 82: the Dawn of Industrial 1% Optical Photometry
• The SEGUE Stellar Parameter Pipeline. II. Validation with Galactic Globular and Open Clusters
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• The SEGUE Stellar Parameter Pipeline. III. Comparison with High-Resolution Spectroscopy of SDSS/SEGUE Field Stars
• The Sloan Digital Sky Survey quasar catalog: tenth data release
• Photometric Variability in Kepler Target Stars. II. An Overview of Amplitude, Periodicity, and Rotation in First Quarter Data
• Automated supervised classification of variable stars I. Methodology
• High-Resolution Spectroscopy of Extremely Metal-Poor Stars from SDSS/SEGUE: I. Atmospheric Parameters and Chemical Compositions
• Random forest automated supervised classification of Hipparcos periodic variable stars
• An Early Warning System for Asteroid Impact
• Optimal Time-Series Selection of Quasars
• The SEGUE Stellar Parameter Pipeline. V. Estimation of Alpha-Element Abundance Ratios From Low-Resolution SDSS/SEGUE Stellar Spectra
• An observational correlation between stellar brightness variations and surface gravity
• Using Machine Learning for Discovery in Synoptic Survey Imaging
• Quasar Selection Based on Photometric Variability
• A comparison of period finding algorithms
• Construction of a Calibrated Probabilistic Classification Catalog: Application to 50k Variable Sources in the All-Sky Automated Survey
• Variable stars across the observational HR diagram
• Fundamental stellar parameters and metallicities from Bayesian spectroscopy. Application to low- and high-resolution spectra
• Rapid, Machine-Learned Resource Allocation: Application to High-redshift GRB Follow-up
• Determination of the iron content of Cepheids from the shape of their light curves

Cited by in corpus (28)

• A recurrent neural network for classification of unevenly sampled variable stars
• Asteroid lightcurves from the Palomar Transient Factory survey: Rotation periods and phase functions from sparse photometry
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• J-PLUS: Stellar Parameters, C, N, Mg, Ca and [α/Fe] Abundances for Two Million Stars from DR1
• An investigation on the factors affecting machine learning classifications in $\gamma$-ray astronomy
• Stellar Parameter Determination from Photometry using Invertible Neural Networks
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Astraea: Predicting Long Rotation Periods with 27-Day Light Curves
• Machine Learning Based Real Bogus System for HSC-SSP Moving Object Detecting Pipeline
• A Wide Planetary Mass Companion Discovered Through the Citizen Science Project Backyard Worlds: Planet 9
• Near-ultraviolet to visible spectroscopy of the Themis and Polana-Eulalia complex families
• Preparing for advanced LIGO: A Star-Galaxy Separation Catalog for the Palomar Transient Factory
• Predicting the redshift of gamma-ray loud AGNs using supervised machine learning
• Variable star classification with a Multiple-Input Neural Network
• Stellar Spectral Interpolation using Machine Learning
• GRB Redshift Estimation using Machine Learning and the Associated Web-App
• Machine Learning Regression of extinction in the second $Gaia$ Data Release
• Metallicity estimation of MW, SMC and LMC classical Cepheids from the shape of the $V$- and $I$-band light curves
• The Most Predictive Physical Properties for the Stellar Population Radial Profiles of Nearby Galaxies
• Variable Star Classification Using Multi-View Metric Learning
• A Detection Metric Designed for O'Connell Effect Eclipsing Binaries
• The Synthetic-Oversampling Method: Using Photometric Colors to Discover Extremely Metal-Poor Stars
• Physical Parameters of Stars in NGC 6397 Using ANN-Based Interpolation and Full Spectrum Fitting
• Integrating Temporal and Spectral Features of Astronomical Data Using Wavelet Analysis for Source Classification
• J-PLUS: Searching for very metal-poor star candidates using the SPEEM pipeline
• Predicting Stellar Parameters of Massive Stars from Light Curves with Machine Learning
• Random Forests applied to High Precision Photometry Analysis with Spitzer IRAC