Towards the prediction of molecular parameters from astronomical emission lines using Neural Networks

Abstract

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 (T ex ) 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 CH 3 CN 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 CH 3 CN. 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.

Overview of Big Data Analytics in Modern Astronomy

“…In a different context, David et al applied a genetic algorithm-based ANN for classifying preprocessed light curves [58]. Alejandro et al employed a neural network in molecular astronomy to predict various molecule parameters from emission lines [59]. ANNs can also function as deep architecture models by increasing the number of hidden layers and neurons in each layer.…”

Volume Density Structure of the Central Molecular Zone NGC 253 through ALCHEMI Excitation Analysis

“…By exploiting large-scale molecular line survey data at millimeter-submillimeter wavelengths accessible with the Atacama Large Millimeter/submillimeter Array (ALMA), it is now possible to simultaneously delineate the spatial variation of n H 2 , T kin , and hydrogen column density (N H 2 ) even in relatively distant sources. In this paper, we apply the same analysis as T18 to the NGC 253 CMZ by utilizing the unprecedentedly rich spectral data from the ALMA Comprehensive High-resolution Extragalactic Molecular Inventory (ALCHEMI) program (Barrientos et al 2021;Harada et al 2021Harada et al , 2022Holdship et al 2021Holdship et al , 2022Martín et al 2021;Behrens et al 2022;Haasler et al 2022;Huang et al 2023;Humire et al 2022). The ALCHEMI survey (Martín et al 2021) covers the 84-373 GHz frequency range at a 1 6 (=27 pc) spatial and 10 km s −1 velocity resolution, including all tracers used in the T18 analysis.…”