Abstract
We present a Deep Learning pipeline for the detection of astronomical sources within radiointerferometric simulated data cubes. Our pipeline is constituted by two Deep Learning models: a Convolutional Autoencoder for the detection of sources within the spatial domain of the cube, and a RNN for the denoising and detection of emission peaks in the frequency domain. The combination of spatial and frequency information allows for higher completeness and helps to remove false positives. The pipeline has been tested on simulated ALMA observations achieving better performances and faster execution times with respect to traditional methods. The pipeline can detect \(92\%\) of sources up to a flux of 1.31 Jy/beam with no false positives thus providing a reliable source detection solution for future astronomical radio surveys.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akhazhanov, A., et al.: Finding quadruply imaged quasars with machine learning - I. Methods. Mon. Not. R. Astron. Soc. 513(2), pp. 2407–2421 (2022). https://doi.org/10.1093/mnras/stac925
Collaboration, A., et al.: “The astropy project: building an openscience project and status of the v2.0 core package. Astron. J. 156(3), 123 (2018). https://doi.org/10.3847/1538-3881/aabc4f. arXiv: 1801.02634 [astro-ph.IM]
Baron, D.: Machine learning in astronomy: a practical overview (2019). https://doi.org/10.48550/ARXIV.1904.07248
Bowles, M., et al.: Attention-gating for improved radio galaxy classification. Mon. Not. R. Astron. Soc. 501(3), 4579–4595 (2020). https://doi.org/10.1093/mnras/staa3946
Carpenter, J., et al.: The ALMA development program: roadmap to 2030 (2020). https://doi.org/10.48550/ARXIV.2001.11076. https://arxiv.org/abs/2001.11076
Chung, J., et al.: Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR abs/1412.3555 (2014). arXiv:1412.3555
Connor, L., et al.: Deep radio-interferometric imaging with POLISH: DSA-2000 and weak lensing. Mon. Not. R. Astron. Soc. 514(2), pp. 2614–2626 (2022). https://doi.org/10.1093/mnras/stac1329
Cornwell, T.J.: Multiscale CLEAN deconvolution of radio synthesis images. IEEE J. Sel. Top. Sig. Process. 2(5), 793–801 (2008). https://doi.org/10.1109/JSTSP.2008.2006388
Duarte, R., Nemmen, R., Navarro, J.P.: Black hole weather forecasting with deep learning: a pilot study. Mon. Not. R. Astron. Soc. 512(4), 5848–5861 (2022). https://doi.org/10.1093/mnras/stac665
Goode, S., et al.: Machine learning for fast transients for the deeper, wider, faster programme with the removal Of BOgus transients (ROBOT) pipeline. Mon. Not. R. Astron. Soc. 513(2), 1742–1754 (2022). https://doi.org/10.1093/mnras/stac983
Hales, C.A., et al.: BLOBCAT: software to catalogue flood-filled blobs in radio images of total intensity and linear polarization. Mon. Not. R. Astron. Soc. 425(2), 979–996 (2012). https://doi.org/10.1111/j.1365-2966.2012.21373.x
Hogbom, J.A.: Aperture synthesis with a non-regular distribution of interferometer baselines. Astron. Astrophys. 15, 417 (1974)
Lin, S.-C., et al.: Estimating cluster masses from SDSS multiband images with transfer learning. Mon. Not. R. Astron. Soc. 512(3), 3885–3894 (2022). https://doi.org/10.1093/mnras/stac725
Longo, G., Merényi, E., Tiňo, P.: Foreword to the focus issue on machine intelligence in astronomy and astrophysics. Publ. Astron. Soc. Pac. 131(1004), 1–6 (2019). ISSN: 00046280, 15383873. https://www.jstor.org/stable/26874447. Visited 24 June 2022
McMullin, J.P., et al.: CASA architecture and applications. In: Shaw, R.A., Hill, F., Bell, D.J. (eds.) Astronomical Data Analysis Software and Systems XVI ASP Conference Series, vol. 376, Proceedings of the Conference Held 15–18 October 2006 in Tucson, Arizona, USA, p. 127 376, October 2007
Nousi, P., et al.: Autoencoder-driven spiral representation learning for gravitational wave surrogate modelling. Neurocomputing 491, 67–77 (2022). https://doi.org/10.1016/j.neucom.2022.03.052
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Pesenson, M.Z., Pesenson, I.Z., McCollum, B.: The data big bang and the expanding digital universe: high-dimensional, complex and massive data sets in an in ationary epoch. Adv. Astron. 2010 (2010), pp. 1–16. https://doi.org/10.1155/2010/350891
Rezaei, S., et al.: DECORAS: detection and characterization of radio-astronomical sources using deep learning. Mon. Not. R. Astron. Soc. 510(4), 5891–5907 (2021). https://doi.org/10.1093/mnras/stab3519
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., Mcclelland, J.L. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume 1: Foundations, pp. 318–362. MIT Press, Cambridge (1986)
Schmidt, K., et al.: Deep learning-based imaging in radio interferometry. Astron. Astrophys. (2022). https://doi.org/10.1051/0004-6361/202142113
Sweere, S.F., et al.: Deep learning-based super-resolution and de-noising for XMM-Newton images (2022). https://doi.org/10.48550/ARXIV.2205.01152
Virtanen, P., et al.: SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Methods 17, 261–272 (2020). https://doi.org/10.1038/s41592-019-0686-2
Westmeier, T., et al.: sofia2 an automated, parallel H source finding pipeline for the WALLABY survey. Mon. Not. R. Astron. Soc. 506(3), 3962–3976 (2021). https://doi.org/10.1093/mnras/stab1881
Yi, Z., et al.: Automatic detection of low surface brightness galaxies from Sloan Digital Sky Survey images. Mon. Not. R. Astron. Soc. 513(3), 3972–3981 (2022). https://doi.org/10.1093/mnras/stac775
Zelinka, I., Brescia, M., Baron, D. (eds.): Intelligent Astrophysics. ECC, vol. 39. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-65867-0
Zeng, Q., Li, X., Lin, H.: Concat convolutional neural network for pulsar candidate selection. Mon. Not. R. Astron. Soc. 494(3), 3110–3119 (2020). https://doi.org/10.1007/978-3-030-65867-0
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Veneri, M.D., Tychoniec, L., Guglielmetti, F., Villard, E., Longo, G. (2023). 3D Detection of ALMA Sources Through Deep Learning. In: Koprinska, I., et al. Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2022. Communications in Computer and Information Science, vol 1752. Springer, Cham. https://doi.org/10.1007/978-3-031-23618-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-23618-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23617-4
Online ISBN: 978-3-031-23618-1
eBook Packages: Computer ScienceComputer Science (R0)