Stellar Karaoke: deep blind separation of terrestrial atmospheric effects out of stellar spectra by velocity whitening

Abstract

We report a study exploring how the use of deep neural networks with astronomical Big Data may help us find and uncover new insights into underlying phenomena: through our experiments towards unsupervised knowledge extraction from astronomical Big Data we serendipitously found that deep convolutional autoencoders tend to reject telluric lines in stellar spectra. With further experiments we found that only when the spectra are in the barycentric frame does the network automatically identify the statistical independence between two components, stellar vs telluric, and rejects the latter. We exploit this finding and turn it into a proof-of-concept method for removal of the telluric lines from stellar spectra in a fully unsupervised fashion: we increase the inter-observation entropy of telluric absorption lines by imposing a random, virtual radial velocity to the observed spectrum. This technique results in a non-standard form of ``whitening'' in the atmospheric components of the spectrum, decorrelating them across multiple observations. We process more than 250,000 spectra from the High Accuracy Radial velocity Planetary Search (HARPS) and with qualitative and quantitative evaluations against a database of known telluric lines, show that most of the telluric lines are successfully rejected. Our approach, `Stellar Karaoke', has zero need for prior knowledge about parameters such as observation time, location, or the distribution of atmospheric molecules and processes each spectrum in milliseconds. We also train and test on Sloan Digital Sky Survey (SDSS) and see a significant performance drop due to the low resolution. We discuss directions for developing tools on top of the introduced method in the future.

References in corpus (29)

• The Seventh Data Release of the Sloan Digital Sky Survey
• The 2.5 m Telescope of the Sloan Digital Sky Survey
• SEGUE: A Spectroscopic Survey of 240,000 stars with g=14-20
• The Multi-Object, Fiber-Fed Spectrographs for SDSS and the Baryon Oscillation Spectroscopic Survey
• A Method of Correcting Near-Infrared Spectra for Telluric Absorption
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Molecfit: A general tool for telluric absorption correction. I. Method and application to ESO instruments
• Spectral Classification and Redshift Measurement for the SDSS-III Baryon Oscillation Spectroscopic Survey
• Molecfit: A general tool for telluric absorption correction II. Quantitative evaluation on ESO-VLT X-Shooter spectra
• Optimal whitening and decorrelation
• The IAU 2000 resolutions for astrometry, celestial mechanics and metrology in the relativistic framework: explanatory supplement
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• Spectral Classification of Galaxies: An Orthogonal Approach
• Photometric redshifts from SDSS images using a Convolutional Neural Network
• Correcting for Telluric Absorption: Methods, Case Studies, and Release of the TelFit Code
• Automated Classification of Stellar Spectra. II: Two-Dimensional Classification with Neural Networks and Principal Components Analysis
• He I $\lambda$ 10830 Å in the transmission spectrum of HD 209458 b
• Flux calibration of medium-resolution spectra from 300 nm to 2500 nm: Model reference spectra and telluric correction
• Magnetic fields in M dwarfs from the CARMENES survey
• Application of Convolutional Neural Networks for Stellar Spectral Classification
• Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
• Galaxy Morphology Network: A Convolutional Neural Network Used to Study Morphology and Quenching in $\sim 100,000$ SDSS and $\sim 20,000$ CANDELS Galaxies
• Wobble: A Data-driven Analysis Technique for Time-series Stellar Spectra
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Automatic model-based telluric correction for the ESPRESSO data reduction software. Model description and application to radial velocity computation
• Telluric correction in the near-infrared: Standard star or synthetic transmission?
• An autoencoder of stellar spectra and its application in automatically estimating atmospheric parameters
• Modelling telluric line spectra in the optical and infrared with an application to VLT/X-Shooter spectra
• Machines Learn to Infer Stellar Parameters Just by Looking at a Large Number of Spectra

Cited by in corpus (1)

• How to set up your first machine learning project in astronomy