Measuring the spectral index of turbulent gas with deep learning from projected density maps
arXiv:2008.11287 · doi:10.1093/mnras/staa2663
Abstract
Turbulence plays a key role in star formation in molecular clouds, affecting star cluster primordial properties. As modelling present-day objects hinges on our understanding of their initial conditions, better constraints on turbulence can result in windfalls in Galactic archaeology, star cluster dynamics and star formation. Observationally, constraining the spectral index of turbulent gas usually involves computing spectra from velocity maps. Here we suggest that information on the spectral index might be directly inferred from column density maps (possibly obtained by dust emission/absorption) through deep learning. We generate mock density maps from a large set of adaptive mesh refinement turbulent gas simulations using the hydro-simulation code RAMSES. We train a convolutional neural network (CNN) on the resulting images to predict the turbulence index, optimize hyper-parameters in validation and test on a holdout set. Our adopted CNN model achieves a mean squared error of 0.024 in its predictions on our holdout set, over underlying spectral indexes ranging from 3 to 4.5. We also perform robustness tests by applying our model to altered holdout set images, and to images obtained by running simulations at different resolutions. This preliminary result on simulated density maps encourages further developments on real data, where observational biases and other issues need to be taken into account.
arXiv comment7 pages, 7 figures, 1 table
References in corpus (39)
- Cosmological Hydrodynamics with Adaptive Mesh Refinement: a new high resolution code called RAMSES
- Control of star formation by supersonic turbulence
- Interstellar Turbulence I: Observations and Processes
- A General Theory of Turbulence-Regulated Star Formation, From Spirals to ULIRGs
- Density, Velocity, and Magnetic Field Structure in Turbulent Molecular Cloud Models
- The Star Formation Rate of Turbulent Magnetized Clouds: Comparing Theory, Simulations, and Observations
- The Density Probability Distribution in Compressible Isothermal Turbulence: Solenoidal versus Compressive Forcing
- Velocity Modification of HI Power Spectrum
- Interstellar Turbulence II: Implications and Effects
- Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
- Density Studies of MHD Interstellar Turbulence: Statistical Moments, Correlations and Bispectrum
- Bayesian analysis of cosmic-ray propagation: evidence against homogeneous diffusion
- A General Theory of Turbulent Fragmentation
- Oscillation frequencies for 35 \Kepler solar-type planet-hosting stars using Bayesian techniques and machine learning
- Velocity Modification of Power Spectrum from Absorbing Medium
- Velocity centroids as tracers of the turbulent velocity statistics
- The Star Formation Rate in the Gravoturbulent Interstellar Medium
- A Search for Larson-Type Relations in Numerical Simulations of the ISM. Evidence for Non-Constant Column Densities
- Studying Turbulence using Doppler-broadened lines: Velocity Coordinate Spectrum
- Non-universal star formation efficiency in turbulent ISM
- The Power Spectrum of Supersonic Turbulence in Perseus
- K2 Variable Catalogue II: Machine Learning Classification of Variable Stars and Eclipsing Binaries in K2 Fields 0-4
- Interstellar Turbulence: II. Energy Spectra of Molecular Regions in the Outer Galaxy
- Velocity Spectrum for HI at High Latitudes
- The Turbulence Spectrum of Molecular Clouds in the Galactic Ring Survey: A Density-Dependent PCA Calibration
- Probing the evolution of molecular cloud structure II: From chaos to confinement
- Understanding star formation in molecular clouds II. Signatures of gravitational collapse of IRDCs
- Turbulence production and turbulent pressure support in the intergalactic medium
- Distribution of velocity gradient orientations: Mapping magnetization with the Velocity Gradient Technique
- Structure analysis of interstellar clouds: I. Improving the Delta-variance method
- Studying Turbulence from Doppler-broadened Absorption Lines: Statistics of Logarithms of Intensity
- The Turbulence Power Spectrum in Optically Thick Interstellar Clouds
- The structure of self-gravitating clouds
- Different Fates of Young Star Clusters After Gas Expulsion
- Exponential Tails in the Centroid Velocity Distributions of Star-Forming Regions
- TurbuStat: Turbulence Statistics in Python
- Turbulence in the Intergalactic Medium
- Finding Black Holes with Black Boxes -- Using Machine Learning to Identify Globular Clusters with Black Hole Subsystems
- Merged or monolithic? Using machine-learning to reconstruct the dynamical history of simulated star clusters