Towards the prediction of molecular parameters from astronomical emission lines using Neural Networks
Artikel i vetenskaplig tidskrift, 2021
Molecular astronomy is a field that is blooming in the era of large observatories such as the Atacama Large Millimeter/Submillimeter Array (ALMA). With modern, sensitive, and high spectral resolution radio telescopes like ALMA and the Square Kilometer Array, the size of the data cubes is rapidly escalating, generating a need for powerful automatic analysis tools. This work introduces MolPred, a pilot study to perform predictions of molecular parameters such as excitation temperature (Tex) and column density (log(N)) from input spectra by the use of neural networks. We used as test cases the spectra of CO, HCO+, SiO and CH3CN between 80 and 400 GHz. Training spectra were generated with MADCUBA, a state-of-the-art spectral analysis tool. Our algorithm was designed to allow the generation of predictions for multiple molecules in parallel. Using neural networks, we can predict the column density and excitation temperature of these molecules with a mean absolute error of 8.5% for CO, 4.1% for HCO+, 1.5% for SiO and 1.6% for CH3CN. The prediction accuracy depends on the noise level, line saturation, and number of transitions. We performed predictions upon real ALMA data. The values predicted by our neural network for this real data differ by 13% from the MADCUBA values on average. Current limitations of our tool include not considering linewidth, source size, multiple velocity components, and line blending.
MADCUBA
Molecular parameters
Neural networks
Machine learning
Molecular astronomy
ALCHEMI
Författare
Alejandro Barrientos
Universidad Técnica Federico Santa María
Atacama Large Millimeter-submillimeter Array (ALMA)
Jonathan Holdship
Universiteit Leiden
University College London (UCL)
Mauricio Solar
Universidad Técnica Federico Santa María
S. Martin
Universidad Técnica Federico Santa María
European Southern Observatory Santiago
Víctor M. Rivilla
Centro de Astrobiologia (CAB)
Osservatorio Astrofisico di Arcetri
Serena Viti
University College London (UCL)
Universiteit Leiden
J. G. Mangum
National Radio Astronomy Observatory
N. Harada
National Astronomical Observatory of Japan
The Graduate University for Advanced Studies (SOKENDAI)
Academia Sinica
K. Sakamoto
Academia Sinica
Sebastien Muller
Chalmers, Rymd-, geo- och miljövetenskap, Onsala rymdobservatorium
Kunihiko Tanaka
Keio University
Yuki Yoshimura
University of Tokyo
Kouichiro Nakanishi
National Astronomical Observatory of Japan
The Graduate University for Advanced Studies (SOKENDAI)
R. Herrero-Illana
Consejo Superior de Investigaciones Científicas (CSIC)
European Southern Observatory Santiago
S. Muhle
Universität Bonn
Rebeca Aladro
Max-Planck-Gesellschaft
Susanne Aalto
Chalmers, Rymd-, geo- och miljövetenskap, Astronomi och plasmafysik
C. Henkel
Max-Planck-Gesellschaft
King Abdulaziz University
Pedro Humire
Max-Planck-Gesellschaft
Experimental Astronomy
0922-6435 (ISSN) 1572-9508 (eISSN)
Vol. 52 1-2 157-182Ämneskategorier (SSIF 2011)
Datorteknik
Bioinformatik (beräkningsbiologi)
Signalbehandling
DOI
10.1007/s10686-021-09786-w