Harvesting the Lyα forest with convolutional neural networks

Abstract

We develop a machine learning based algorithm using a convolutional neural network (CNN) to identify low HI column density Ly$\alpha$ absorption systems ($\log N_{\mathrm{HI}}/{\mathrm{cm}}^{-2}<17$) in the Ly$\alpha$ forest, and predict their physical properties, such as their HI column density ($\log N_{\mathrm{HI}}/{\mathrm{cm}}^{-2}$), redshift ($z_{\mathrm{HI}}$), and Doppler width ($b_{\mathrm{HI}}$). Our CNN models are trained using simulated spectra (S/N $\simeq 10$), and we test their performance on high quality spectra of quasars at redshift $z\sim 2.5-2.9$ observed with the High Resolution Echelle Spectrometer on the Keck I telescope. We find that $\sim 78\%$ of the systems identified by our algorithm are listed in the manual Voigt profile fitting catalogue. We demonstrate that the performance of our CNN is stable and consistent for all simulated and observed spectra with S/N $\gtrsim 10$. Our model can therefore be consistently used to analyse the enormous number of both low and high S/N data available with current and future facilities. Our CNN provides state-of-the-art predictions within the range $12.5\le \log N_{\mathrm{HI}}/\mathrm{c}{\mathrm{m}}^{-2}<15.5$ with a mean absolute error of $\Delta (\log N_{\mathrm{HI}}/{\mathrm{cm}}^{-2})=0.13$, $\Delta (z_{\mathrm{HI}})=2.7\times {10}^{-5}$, and $\Delta (b_{\mathrm{HI}})=4.1\mathrm{km}{\mathrm{s}}^{-1}$. The CNN prediction costs $<3$ minutes per model per spectrum with a size of 120\,000 pixels using a laptop computer. We demonstrate that CNNs can significantly increase the efficiency of analysing Ly$\alpha$ forest spectra, and thereby greatly increase the statistics of Ly$\alpha$ absorbers.

arXiv comment22 pages including 2-pages Appendices, 14 figures plus 4 figures in Appendices. This paper is submitted to MNRAS and has addressed the first referee report

References in corpus (65)

• Deep Learning using Rectified Linear Units (ReLU)
• An Overview of Multi-Task Learning in Deep Neural Networks
• Warm Dark Matter as a solution to the small scale crisis: new constraints from high redshift Lyman-alpha forest data
• Equation of State of the Photoionized Intergalactic Medium
• The Lyman Alpha Forest in the Spectra of QSOs
• First constraints on fuzzy dark matter from Lyman-$\alpha$ forest data and hydrodynamical simulations
• The SDSS Damped Lya Survey: Data Release 3
• The thermal history of the intergalactic medium
• The Physics of the Intergalactic Medium
• The Gaseous Environment of High-z Galaxies: Precision Measurements of Neutral Hydrogen in the Circumgalactic Medium of z ~ 2-3 Galaxies in the Keck Baryonic Structure Survey
• Model-independent insights into the nature of the Lyman-alpha forest and the distribution of matter in the universe
• On the (Non)Evolution of HI Disks over Cosmic Time
• Strong bound on canonical ultra-light axion dark matter from the Lyman-alpha forest
• 4MOST: Project overview and information for the First Call for Proposals
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• The Evolution of the Effective Equation of State of the IGM
• The Evolution of Optical Depth in the Ly-alpha Forest: Evidence Against Reionization at z~6
• Cosmological simulations of the circumgalactic medium with 1 kpc resolution: enhanced HI column densities
• Lyman-alpha Forests cool Warm Dark Matter
• The Impact of Enhanced Halo Resolution on the Simulated Circumgalactic Medium
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• The Strong Gravitational Lens Finding Challenge
• Possible evidence for an inverted temperature-density relation in the intergalactic medium from the flux distribution of the Lyman-alpha forest
• Radiative Transfer Effects during Photoheating of the Intergalactic Medium
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Revealing reionization with the thermal history of the intergalactic medium: new constraints from the Lyman-$\alpha$ flux power spectrum
• Measuring the equation of state of the intergalactic medium
• The physical properties of the Ly-Alpha forest at z > 1.5
• Physical Properties, Baryon Content, and Evolution of the LyαForest: New Insights from High Resolution Observations at z < 0.4
• The intergalactic medium over the last 10 billion years I: Lyman alpha absorption and physical conditions
• Automated Classification of Stellar Spectra. II: Two-Dimensional Classification with Neural Networks and Principal Components Analysis
• Optimising Automatic Morphological Classification of Galaxies with Machine Learning and Deep Learning using Dark Energy Survey Imaging
• Deep learning predictions of galaxy merger stage and the importance of observational realism
• Voigt-Profile Analysis of the Lyman-alpha Forest in a Cold Dark Matter Universe
• The Column Density, Kinematics, and Thermal State of Metal-Bearing Gas within the Virial Radius of z~2 Star-Forming Galaxies in the Keck Baryonic Structure Survey
• The photoheating of the intergalactic medium in synthesis models of the UV background
• The Temperature-Density Relation in the Intergalactic Medium at Redshift <z>=2.4
• Cutoff in the Lyman-$\alpha$ forest power spectrum: warm IGM or warm dark matter?
• Cosmological parameters sigma_8, the baryon density, and the UV background intensity from a calibrated measurement of H I Lyman-alpha absorption at z = 1.9
• Galaxy Merger Rates up to z $\sim$ 3 using a Bayesian Deep Learning Model $-$ A Major-Merger classifier using IllustrisTNG Simulation data
• Deep Learning of Quasar Spectra to Discover and Characterize Damped Lya Systems
• Identifying Strong Lenses with Unsupervised Machine Learning using Convolutional Autoencoder
• Detection of He II reionization in the SDSS quasar sample
• Low-redshift evolution of the Lyman-alpha Forest
• The Second Data Release of the KODIAQ Survey
• Bayesian emulator optimisation for cosmology: application to the Lyman-alpha forest
• Towards a Unified Description of the Intergalactic Medium at Redshift z~2.5
• Probing the thermal history of the Intergalactic Medium with Lyman-alpha absorption lines
• The Space Distribution of the Lyman Alpha Clouds in the Line of Sight to the Z=3.66 QSO 0055-269
• Photo-heating and the fate of hard photons during the reionisation of HeII by quasars
• Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks
• An Emulator for the Lyman-alpha Forest
• VoIgt profile Parameter Estimation Routine (VIPER): H I photoionization rate at z<0.5
• Artificial intelligence applied to the automatic analysis of absorption spectra. Objective measurement of the fine structure constant
• The b Distribution and the Velocity Structure of Absorption Peaks in the Lyman-Alpha Forest
• The evolution of HI and CIV quasar absorption line systems at 1.9 < z < 3.2
• Dependencies of QSO Lyman-alpha absorption line statistics on cosmological parameters
• The Size and Nature of Lyman alpha Forest Clouds Probed by QSO Pairs and Groups
• Learning the Relationship between Galaxies Spectra and their Star Formation Histories using Convolutional Neural Networks and Cosmological Simulations
• WEAVE-QSO: A Massive Intergalactic Medium Survey for the William Herschel Telescope
• Strong lens modelling: comparing and combining Bayesian neural networks and parametric profile fitting
• Detecting Damped Lyman-$\alpha$ Absorbers with Gaussian Processes
• The evolution of the low-density HI intergalactic medium from z=3.6 to 0: Data, transmitted flux and HI column density
• The Third Data Release of the KODIAQ Survey
• Deep Learning of DESI Mock Spectra to Find Damped Lyα Systems