Published November 20, 2023 | Published
Journal Article Open

Predicting the Radiation Field of Molecular Clouds Using Denoising Diffusion Probabilistic Models

  • 1. ROR icon University of Virginia
  • 2. ROR icon The University of Texas at Austin
  • 3. ROR icon University of Massachusetts System
  • 4. ROR icon Carnegie Observatories
  • 5. ROR icon Harvard-Smithsonian Center for Astrophysics
  • 6. ROR icon California Institute of Technology

Abstract

Accurately quantifying the impact of radiation feedback in star formation is challenging. To address this complex problem, we employ deep-learning techniques known as denoising diffusion probabilistic models (DDPMs) to predict the interstellar radiation field (ISRF) strength based on three-band dust emission at 4.5, 24, and 250 μm. We adopt magnetohydrodynamic simulations from the STARFORGE project that model star formation and giant molecular cloud (GMC) evolution. We generate synthetic dust emission maps matching observed spectral energy distributions in the Monoceros R2 (MonR2) GMC. We train DDPMs to estimate the ISRF using synthetic three-band dust emission. The dispersion between the predictions and true values is within a factor of 0.1 for the test set. We extended our assessment of the diffusion model to include new simulations with varying physical parameters. While there is a consistent offset observed in these out-of-distribution simulations, the model effectively constrains the relative intensity to within a factor of 2. Meanwhile, our analysis reveals a weak correlation between the ISRF solely derived from dust temperature and the actual ISRF. We apply our trained model to predict the ISRF in MonR2, revealing a correspondence between intense ISRF, bright sources, and high dust emission, confirming the model's ability to capture ISRF variations. Our model robustly predicts radiation feedback distribution, even in complex, poorly constrained ISRF environments like those influenced by nearby star clusters. However, precise ISRF predictions require an accurate training data set mirroring the target molecular cloud's unique physical conditions.

Copyright and License

© 2023. The Author(s). Published by the American Astronomical Society.

Original content from this work may be used under the terms of the Creative Commons Attribution 4.0 licence. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

Acknowledgement

We would like to express our gratitude to the anonymous referee for the invaluable suggestions, particularly those pertaining to the assessment of out-of-distribution data. D.X. acknowledges support from the Virginia Initiative on Cosmic Origins (VICO). S.S.R.O. and R.G. acknowledge funding support for this work from NSF AAG grants 2107340 and 2107705. S.S.R.O. acknowledges support by NSF through CAREER award 1748571, AST-2107340, and AST-2107942; NASA through grants 80NSSC20K0507 and 80NSSC23K0476; and the Oden Institute through a Moncrief Grand Challenge award. The authors acknowledge Research Computing at the University of Virginia for providing computational resources and technical support that have contributed to the results reported within this publication.

Funding

D.X. acknowledges support from the Virginia Initiative on Cosmic Origins (VICO). S.S.R.O. and R.G. acknowledge funding support for this work from NSF AAG grants 2107340 and 2107705. S.S.R.O. acknowledges support by NSF through CAREER award 1748571, AST-2107340, and AST-2107942; NASA through grants 80NSSC20K0507 and 80NSSC23K0476; and the Oden Institute through a Moncrief Grand Challenge award.

Files

Xu_2023_ApJ_958_97.pdf
Files (24.2 MB)
Name Size Download all
md5:5a7eb78c588e17f3e81b2bc97a9bfbb3
24.2 MB Preview Download

Additional details

Created:
November 22, 2024
Modified:
November 22, 2024