Deep learning denoising by dimension reduction: Application to the ORION-B line cubes

Abstract

Context. The availability of large bandwidth receivers for millimeter radio telescopes allows the acquisition of position-position-frequency data cubes over a wide field of view and a broad frequency coverage. These cubes contain much information on the physical, chemical, and kinematical properties of the emitting gas. However, their large size coupled with inhomogenous signal-to-noise ratio (SNR) are major challenges for consistent analysis and interpretation.Aims. We search for a denoising method of the low SNR regions of the studied data cubes that would allow to recover the low SNR emission without distorting the signals with high SNR.Methods. We perform an in-depth data analysis of the 13 CO and C 17 O (1 -- 0) data cubes obtained as part of the ORION-B large program performed at the IRAM 30m telescope. We analyse the statistical properties of the noise and the evolution of the correlation of the signal in a given frequency channel with that of the adjacent channels. This allows us to propose significant improvements of typical autoassociative neural networks, often used to denoise hyperspectral Earth remote sensing data. Applying this method to the 13 CO (1 -- 0) cube, we compare the denoised data with those derived with the multiple Gaussian fitting algorithm ROHSA, considered as the state of the art procedure for data line cubes.Results. The nature of astronomical spectral data cubes is distinct from that of the hyperspectral data usually studied in the Earth remote sensing literature because the observed intensities become statistically independent beyond a short channel separation. This lack of redundancy in data has led us to adapt the method, notably by taking into account the sparsity of the signal along the spectral axis. The application of the proposed algorithm leads to an increase of the SNR in voxels with weak signal, while preserving the spectral shape of the data in high SNR voxels.Conclusions. The proposed algorithm that combines a detailed analysis of the noise statistics with an innovative autoencoder architecture is a promising path to denoise radio-astronomy line data cubes. In the future, exploring whether a better use of the spatial correlations of the noise may further improve the denoising performances seems a promising avenue. In addition,

References in corpus (20)

• Estimating Mutual Information
• Herschel Space Observatory - An ESA facility for far-infrared and submillimetre astronomy
• Bias-free Measurement of Giant Molecular Cloud Properties
• High-resolution wide-band Fast Fourier Transform spectrometers
• The anatomy of the Orion B Giant Molecular Cloud: A local template for studies of nearby galaxies
• PHANGS-ALMA Data Processing and Pipeline
• The IRAM-30m line survey of the Horsehead PDR: II. First detection of the l-C3H+ hydrocarbon cation
• The On The Fly Imaging Technique
• Turbulence and star formation efficiency in molecular clouds: solenoidal versus compressive motions in Orion B
• The IRAM-30m line survey of the Horsehead PDR: III. High abundance of complex (iso-)nitrile molecules in UV-illuminated gas
• GaussPy+: A fully automated Gaussian decomposition package for emission line spectra
• The IRAM-30m line survey of the Horsehead PDR: IV. Comparative chemistry of H2CO and CH3OH
• ROHSA: Regularized Optimization for Hyper-Spectral Analysis - Application to phase separation of 21 cm data
• The RWST, a comprehensive statistical description of the non-Gaussian structures in the ISM
• Dissecting the molecular structure of the Orion B cloud: Insight from Principal Component Analysis
• The IRAM-30m line survey of the Horsehead PDR: I. CF+ as a tracer of C+ and a measure of the Fluorine abundance
• Statistical description of dust polarized emission from the diffuse interstellar medium -- A RWST approach
• A dynamically young, gravitationally stable network of filaments in Orion B
• Non-Gaussian velocity shears in the environment of low mass dense cores
• Gas kinematics around filamentary structures in the Orion B cloud

Cited by in corpus (6)

• Surveying the Whirlpool at Arcseconds with NOEMA (SWAN)- I. Mapping the HCN and N${}_2$H${}^{+}$ 3mm lines
• Neural network-based emulation of interstellar medium models
• Quantifying the informativity of emission lines to infer physical conditions in giant molecular clouds. I. Application to model predictions
• Toward a robust physical and chemical characterization of heterogeneous lines of sight: The case of the Horsehead nebula
• Unmasking the physical information inherent to interstellar spectral line profiles with Machine Learning. I. Application of LTE to HCN and HNC transitions
• Surveying the Whirlpool at Arcseconds with NOEMA (SWAN) II: Survey design and observations