Neural network-based emulation of interstellar medium models

Abstract

The interpretation of observations of atomic and molecular tracers in the galactic and extragalactic interstellar medium (ISM) requires comparisons with state-of-the-art astrophysical models to infer some physical conditions. Usually, ISM models are too time-consuming for such inference procedures, as they call for numerous model evaluations. As a result, they are often replaced by an interpolation of a grid of precomputed models. We propose a new general method to derive faster, lighter, and more accurate approximations of the model from a grid of precomputed models. These emulators are defined with artificial neural networks (ANNs) designed and trained to address the specificities inherent in ISM models. Indeed, such models often predict many observables (e.g., line intensities) from just a few input physical parameters and can yield outliers due to numerical instabilities or physical bistabilities. We propose applying five strategies to address these characteristics: 1) an outlier removal procedure; 2) a clustering method that yields homogeneous subsets of lines that are simpler to predict with different ANNs; 3) a dimension reduction technique that enables to adequately size the network architecture; 4) the physical inputs are augmented with a polynomial transform to ease the learning of nonlinearities; and 5) a dense architecture to ease the learning of simple relations. We compare the proposed ANNs with standard classes of interpolation methods to emulate the Meudon PDR code, a representative ISM numerical model. Combinations of the proposed strategies outperform all interpolation methods by a factor of 2 on the average error, reaching 4.5% on the Meudon PDR code. These networks are also 1000 times faster than accurate interpolation methods and require ten to forty times less memory. This work will enable efficient inferences on wide-field multiline observations of the ISM.

References in corpus (42)

• XGBoost: A Scalable Tree Boosting System
• A computer program for fast non-LTE analysis of interstellar line spectra
• The UMIST database for astrochemistry 2012
• An Analysis of the Shapes of Interstellar Extinction Curves. V. The IR-Through-UV Curve Morphology
• A KInetic Database for Astrochemistry (KIDA)
• A model for atomic and molecular interstellar gas: The Meudon PDR code
• Photodissociation and photoionisation of atoms and molecules of astrophysical interest
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• H3+ in Diffuse Interstellar Clouds: a Tracer for the Cosmic-Ray Ionization Rate
• LIME - a flexible, non-LTE line excitation and radiation transfer method for millimeter and far-infrared wavelengths
• HI-to-H2 Transitions and H I Column Densities in Galaxy Star-Forming Regions
• The anatomy of the Orion B Giant Molecular Cloud: A local template for studies of nearby galaxies
• Bayesian analysis of cosmic-ray propagation: evidence against homogeneous diffusion
• Compression and ablation of the photo-irradiated cloud the Orion Bar
• UCLCHEM: A Gas-Grain Chemical Code
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• A New Reference Chemical Composition for TMC-1
• SKYNET: an efficient and robust neural network training tool for machine learning in astronomy
• Structure of photodissociation fronts in star-forming regions revealed by observations of high-J CO emission lines with Herschel
• The penetration of FUV radiation into molecular clouds
• H_2 Pure Rotational Lines in the Orion Bar
• Models of irradiated molecular shocks
• PDR Model Mapping of Physical Conditions via Spitzer/IRS Spectroscopy of H2: Theoretical Success toward NGC 2023-South
• Tracing Interstellar Heating: An ALCHEMI Measurement of the HCN Isomers in NGC 253
• Constraining physical conditions for the PDR of Trumpler 14 in the Carina Nebula
• Reducing the complexity of chemical networks via interpretable autoencoders
• Inferring the HII region escape fraction of ionizing photons from infrared emission lines in metal-poor star-forming dwarf galaxies
• Chemulator: Fast, accurate thermochemistry for dynamical models through emulation
• Do Androids Dream of Magnetic Fields? Using Neural Networks to Interpret the Turbulent Interstellar Medium
• Tracers of the ionization fraction in dense and translucent gas: I. Automated exploitation of massive astrochemical model grids
• Incorporating Astrochemistry into Molecular Line Modelling via Emulation
• ROBO: a Model and a Code for the Study of the Interstellar Medium
• MOLPOP-CEP: An Exact, Fast Code for Multi-Level Systems
• The KOSMA-$\tau$ PDR Model -- I. Recent updates to the numerical model of photo-dissociated regions
• Bayesian Inference of Reaction Rates in Icy Mantles
• Deep learning denoising by dimension reduction: Application to the ORION-B line cubes
• PDR Model Mapping of Obscured H2 Emission and the Line-of-Sight Structure of M17-SW
• Machine learning-accelerated chemistry modeling of protoplanetary disks
• Understanding the Formation and Evolution of Interstellar Ices: A Bayesian Approach
• Astrochemical Kinetic Grid Models of Groups of Observed Molecular Abundances: Taurus Molecular Cloud 1 (TMC-1)
• UCLCHEMCMC: A MCMC Inference tool for Physical Parameters of Molecular Clouds

Cited by in corpus (5)

• Quantifying the informativity of emission lines to infer physical conditions in giant molecular clouds. I. Application to model predictions
• Mapping Synthetic Observations to Prestellar Core Models: An Interpretable Machine Learning Approach
• Beetroots: spatially-regularized Bayesian inference of physical parameter maps -- Application to Orion
• Neural-Network Chemical Emulator for First-Star Formation: Robust Iterative Predictions over a Wide Density Range
• Recovering the properties of the interstellar medium through integrated spectroscopy: application to the z~0 ECO volume-limited star-forming galaxy sample