A deep-learning approach to the 3D reconstruction of dust density and temperature in star-forming regions

Abstract

Aims: We introduce a new deep-learning approach for the reconstruction of 3D dust density and temperature distributions from multi-wavelength dust emission observations on the scale of individual star-forming cloud cores (<0.2pc). Methods: We construct a training data set by processing cloud cores from the Cloud Factory simulations with the POLARIS radiative transfer code to produce synthetic dust emission observations at 23 wavelengths between 12 and 1300 $\mu$m. We simplify the task by reconstructing the cloud structure along individual lines of sight and train a conditional invertible neural network (cINN) for this purpose. The cINN belongs to the group of normalising flow methods and is able to predict full posterior distributions for the target dust properties. We test different cINN setups, ranging from a scenario that includes all 23 wavelengths down to a more realistically limited case with observations at only seven wavelengths. We evaluate the predictive performance of these models on synthetic test data. Results: We report an excellent reconstruction performance for the 23-wavelengths cINN model, achieving median absolute relative errors of about 1.8% in $\log (n/m^{-3})$ and 1% in $\log (T_{dust}/K)$, respectively. We identify trends towards overestimation at the low end of the density range and towards underestimation at the high end of both the density and temperature values, which may be related to a bias in the training data. Limiting our coverage to a combination of only seven wavelengths, we still find a satisfactory performance with average absolute relative errors of about 3.3% and 2.5% in $\log (n/m^{-3})$ and $\log (T_{dust}/K)$. Conclusions: This proof-of-concept study shows that the cINN-based approach for 3D reconstruction of dust density and temperature is very promising and even compatible with a more realistically constrained wavelength coverage.

38 pages, 25 figures, accepted for publication in Astronomy & Astrophysics on 26.01.2024

References in corpus (20)

• CASA, the Common Astronomy Software Applications for Radio Astronomy
• Gaia-2MASS 3D maps of Galactic interstellar dust within 3 kpc
• Simulating the formation of molecular clouds. I. Slow formation by gravitational collapse from static initial conditions
• Star formation near the Sun is driven by expansion of the Local Bubble
• CO-dark gas and molecular filaments in Milky Way type galaxies
• Updated Gaia-2MASS 3D maps of Galactic interstellar dust
• Parameters of 220 million stars from Gaia BP/RP spectra
• The Cloud Factory I: Generating resolved filamentary molecular clouds from galactic-scale forces
• Simulations of the star-forming molecular gas in an interacting M51-like galaxy
• On the Three-Dimensional Structure of Local Molecular Clouds
• ERGO-ML I: Inferring the assembly histories of IllustrisTNG galaxies from integral observable properties via invertible neural networks
• Inferring the three-dimensional distribution of dust in the Galaxy with a non-parametric method: Preparing for Gaia
• Inference of cosmic-ray source properties by conditional invertible neural networks
• The essential elements of dust evolution: A viable solution to the interstellar oxygen depletion problem?
• 3D shape explains star formation mystery of California and Orion A
• Emission-line diagnostics of HII regions using conditional Invertible Neural Networks
• The Cloud Factory II: Gravoturbulent Kinematics of Resolved Molecular Clouds in a Galactic Potential
• The Mechanical Alignment of Dust (MAD) I: On the spin-up process of fractal grains by a gas-dust drift
• Noise-Net: Determining physical properties of HII regions reflecting observational uncertainties
• Spectral classification of young stars using conditional invertible neural networks I. Introducing and validating the method

Cited by in corpus (3)

• Spectral classification of young stars using conditional invertible neural networks II. Application to Trumpler 14 in Carina
• A normalizing flow approach for the inference of star cluster properties from unresolved broadband photometry I: Comparison to spectral energy distribution fitting
• A method to derive self-consistent NLTE astrophysical parameters for 4 million high-resolution 4MOST stellar spectra in half a day with invertible neural networks