Analysing the SEDs of protoplanetary disks with machine learning

Abstract

ABRIDGED. The analysis of spectral energy distributions (SEDs) of protoplanetary disks to determine their physical properties is known to be highly degenerate. Hence, a Bayesian analysis is required to obtain parameter uncertainties and degeneracies. The challenge here is computational speed, as one radiative transfer model requires a couple of minutes to compute. We performed a Bayesian analysis for 30 well-known protoplanetary disks to determine their physical disk properties, including uncertainties and degeneracies. To circumvent the computational cost problem, we created neural networks (NNs) to emulate the SED generation process. We created two sets of radiative transfer disk models to train and test two NNs that predict SEDs for continuous and discontinuous disks. A Bayesian analysis was then performed on 30 protoplanetary disks with SED data collected by the DIANA project to determine the posterior distributions of all parameters. We ran this analysis twice, (i) with old distances and additional parameter constraints as used in a previous study, to compare results, and (ii) with updated distances and free choice of parameters to obtain homogeneous and unbiased model parameters. We evaluated the uncertainties in the determination of physical disk parameters from SED analysis, and detected and quantified the strongest degeneracies. The NNs are able to predict SEDs within 1ms with uncertainties of about 5% compared to the true SEDs obtained by the radiative transfer code. We find parameter values and uncertainties that are significantly different from previous values obtained by ${\chi }^2$ fitting. Comparing the global evidence for continuous and discontinuous disks, we find that 26 out of 30 objects are better described by disks that have two distinct radial zones. Also, we created an interactive tool that instantly returns the SED predicted by our NNs for any parameter combination.

40 pages, 22 figures, the online tool is available at https://tillkaeufer.github.io/sedpredictor

References in corpus (12)

• Bayes in the sky: Bayesian inference and model selection in cosmology
• Monte Carlo radiative transfer in protoplanetary disks
• The shape and composition of interstellar silicate grains
• Evolution of emission line activity in intermediate mass young stars
• A Tale of Two Herbig Ae stars -MWC275 and AB Aurigae: Comprehensive Models for SED and Interferometry
• Disks around CQ Tau and MWC 758: dense PDR or gas dispersal?
• Circumstellar disks around Herbig Be stars
• Modeling protoplanetary disk SEDs with artificial neural networks: Revisiting the viscous disk model and updated disk masses
• A dust and gas cavity in the disc around CQ Tau revealed by ALMA
• Protoplanetary Disk Masses from Radiative Transfer Modeling: A Case Study in Taurus
• On the underestimation of dust mass in protoplanetary disks: Effects of disk structure and dust properties
• Consistent dust and gas models for protoplanetary disks IV. A panchromatic view of protoplanetary disks

Cited by in corpus (9)

• Porous Dust Particles in Protoplanetary Disks: Application to the HL Tau Disk
• Bayesian Analysis of Molecular Emission and Dust Continuum of Protoplanetary Disks
• The edge-on protoplanetary disk HH 48 NE I. Modeling the geometry and stellar parameters
• DBNets: A publicly available deep learning tool to measure the masses of young planets in dusty protoplanetary discs
• MINDS. Strong oxygen depletion in the inner regions of a very low-mass star disk?
• Constraints on the gas-phase C/O ratio of DR Tau's outer disk from CS, SO, and C${}_2$H observations
• The grazing angle icy protoplanetary disk PDS 453
• J-PAS: A Neural Network Approach to Single Stellar Population Characterization
• Fundamental properties of protoplanetary discs determined from simultaneous fits to thermal dust images and spectral energy distributions