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

¹ IRAM, 300 rue de la Piscine, 38406 Saint Martin d’Hères, France
e-mail: einig@iram.fr
² Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, GIPSA-Lab, Grenoble, 38000, France
³ LERMA, Observatoire de Paris, PSL Research University, CNRS, Sorbonne Universités, 75014 Paris, France
⁴ Université de Toulon, Aix Marseille Univ., CNRS, IM2NP, Toulon, France
⁵ Instituto de Física Fundamental (CSIC). Calle Serrano 121, 28006, Madrid, Spain
⁶ Chalmers University of Technology, Department of Space, Earth and Environment, 412 93 Gothenburg, Sweden
⁷ Univ. Lille, CNRS, Centrale Lille, UMR 9189 – CRIStAL, 59651 Villeneuve d’Ascq, France
⁸ LERMA, Observatoire de Paris, PSL Research University, CNRS, Sorbonne Universités, 92190 Meudon, France
⁹ Laboratoire d’Astrophysique de Bordeaux, Univ. Bordeaux, CNRS, B18N, Allee Geoffroy Saint-Hilaire, 33615 Pessac, France
¹⁰ Instituto de Astrofísica, Pontificia Universidad Católica de Chile, Av. Vicuña Mackenna 4860, 7820436 Macul, Santiago, Chile
¹¹ Institut de Recherche en Astrophysique et Planétologie (IRAP), Université Paul Sabatier, Toulouse Cedex 4, France
¹² GEPI, Observatoire de Paris, PSL University, CNRS, 5 place Jules Janssen, 92190 Meudon, France
¹³ Laboratoire de Physique de l'Ecole normale supérieure, ENS, Université PSL, CNRS, Sorbonne Université, Université de Paris, Sorbonne Paris Cité, 75005 Paris, France
¹⁴ Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Drive, Pasadena, CA 91109, USA
¹⁵ National Radio Astronomy Observatory, 520 Edgemont Road, Charlottesville, VA, 22903, USA
¹⁶ Harvard-Smithsonian Center for Astrophysics, 60 Garden Street, Cambridge, MA 02138, USA
¹⁷ School of Physics and Astronomy, Cardiff University, Queen’s buildings, Cardiff CF24 3AA, UK
¹⁸ AIM, CEA, CNRS, Université Paris-Saclay, Université Paris Diderot, Sorbonne Paris Cité, 91191 Gif-sur-Yvette, France

Received: 2 February 2023
Accepted: 18 July 2023

Abstract

Context. The availability of large bandwidth receivers for millimeter radio telescopes allows for the acquisition of position-position-frequency data cubes over a wide field of view and a broad frequency coverage. These cubes contain a lot of information on the physical, chemical, and kinematical properties of the emitting gas. However, their large size coupled with an inhomogenous signal-to-noise ratio (S/N) are major challenges for consistent analysis and interpretation.

Aims. We searched for a denoising method of the low S/N regions of the studied data cubes that would allow the low S/N emission to be recovered without distorting the signals with a high S/N.

Methods. We performed an in-depth data analysis of the ¹³CO and C¹⁷O (1–0) data cubes obtained as part of the ORION-B large program performed at the IRAM 30 m telescope. We analyzed 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 has allowed us to propose significant improvements of typical autoassociative neural networks, often used to denoise hyperspectral Earth remote sensing data. Applying this method to the ¹³CO (1–0) cube, we were able to 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 in the S/N in voxels with a weak signal, while preserving the spectral shape of the data in high S/N 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 to be a promising avenue. In addition, dealing with the multiplicative noise associated with the calibration uncertainty at high S/N would also be beneficial for such large data cubes.