Denoising Diffusion Probabilistic Models to Predict the Density of Molecular Clouds
arXiv:2304.01670 · doi:10.3847/1538-4357/accae5
Abstract
We introduce the state-of-the-art deep learning Denoising Diffusion Probabilistic Model (DDPM) as a method to infer the volume or number density of giant molecular clouds (GMCs) from projected mass surface density maps. We adopt magnetohydrodynamic simulations with different global magnetic field strengths and large-scale dynamics, i.e., noncolliding and colliding GMCs. We train a diffusion model on both mass surface density maps and their corresponding mass-weighted number density maps from different viewing angles for all the simulations. We compare the diffusion model performance with a more traditional empirical two-component and three-component power-law fitting method and with a more traditional neural network machine learning approach (CASI-2D). We conclude that the diffusion model achieves an order of magnitude improvement on the accuracy of predicting number density compared to that by other methods. We apply the diffusion method to some example astronomical column density maps of Taurus and the Infrared Dark Clouds (IRDCs) G28.37+0.07 and G35.39-0.33 to produce maps of their mean volume densities.
arXiv commentApJ accepted
References in corpus (41)
- Theory of Star Formation
- The Star Formation Efficiency in Nearby Galaxies: Measuring Where Gas Forms Stars Effectively
- Enzo: An Adaptive Mesh Refinement Code for Astrophysics
- Star Clusters Across Cosmic Time
- Herschel view of the Taurus B211/3 filament and striations: Evidence of filamentary growth?
- Magnetic Fields in Spiral Galaxies
- The Evolution of the Star-forming Interstellar Medium across Cosmic Time
- Planck intermediate results. XXXV. Probing the role of the magnetic field in the formation of structure in molecular clouds
- Improving galaxy morphologies for SDSS with Deep Learning
- Astrochemistry During the Formation of Stars
- Reaction Networks For Interstellar Chemical Modelling: Improvements and Challenges
- From Filamentary Networks to Dense Cores in Molecular Clouds: Toward a New Paradigm for Star Formation
- The cold interstellar medium of galaxies in the Local Universe
- Mid-Infrared Extinction Mapping of Infrared Dark Clouds II. The Structure of Massive Starless Cores and Clumps
- High-dynamic-range extinction mapping of infrared dark clouds: Dependence of density variance with sonic Mach number in molecular clouds
- Magnetohydrodynamic Simulations of Disk Galaxy Formation: the Magnetization of The Cold and Warm Medium
- High Resolution Millimeter-Wave Mapping of Linearly Polarized Dust Emission: Magnetic Field Structure in Orion
- A Simple and Accurate Network for Hydrogen and Carbon Chemistry in the ISM
- Gas Kinematics and Excitation in the Filamentary IRDC G035.39-00.33
- GMC Collisions as Triggers of Star Formation. II. 3D Turbulent, Magnetized Simulations
- A Stable, Accurate Methodology for High Mach Number, Strong Magnetic Field MHD Turbulence with Adaptive Mesh Refinement: Resolution and Refinement Studies
- Photodissociation Region Diagnostics Across Galactic Environments
- CNN Architecture Comparison for Radio Galaxy Classification
- Is the Taurus B213 Region a True Filament?: Observations of Multiple Cyanoacetylene Transitions
- GMC Collisions as Triggers of Star Formation. I. Parameter Space Exploration with 2D Simulations
- Deep Learning-Based Super-Resolution and De-Noising for XMM-Newton Images
- CASI: A Convolutional Neural Network Approach for Shell Identification
- PDFchem: A new fast method to determine ISM properties and infer environmental parameters using probability distributions
- Inferring Vector Magnetic Fields from Stokes Profiles of GST/NIRIS Using a Convolutional Neural Network
- Application of Convolutional Neural Networks to Identify Stellar Feedback Bubbles in CO Emission
- GMC Collisions as Triggers of Star Formation. VII. The Effect of Magnetic Field Strength on Star Formation
- Prospects for future studies using deep imaging: Analysis of individual Galactic cirrus filaments
- Application of Convolutional Neural Networks to Identify Protostellar Outflows in CO Emission
- PGNets: Planet mass prediction using convolutional neural networks for radio continuum observations of protoplanetary disks
- Astrochemical modelling of infrared dark clouds
- Deblending Galaxies with Generative Adversarial Networks
- A Census of Outflow to Magnetic Field Orientations in Nearby Molecular Clouds
- A Census of Protostellar Outflows in Nearby Molecular Clouds
- Application of Convolutional Neural Networks to Predict Magnetic Fields Directions in Turbulent Clouds
- Noise reduction on single-shot images using an autoencoder
- GMC Collisions As Triggers of Star Formation. VIII. The Core Mass Function