Rate Coefficients for the Collisional Excitation of Molecules: Estimates from an Artificial Neural Network

Abstract

An artificial neural network (ANN) is investigated as a tool for estimating rate coefficients for the collisional excitation of molecules. The performance of such a tool can be evaluated by testing it on a dataset of collisionally-induced transitions for which rate coefficients are already known: the network is trained on a subset of that dataset and tested on the remainder. Results obtained by this method are typically accurate to within a factor ~ 2.1 (median value) for transitions with low excitation rates and ~ 1.7 for those with medium or high excitation rates, although 4% of the ANN outputs are discrepant by a factor of 10 more. The results suggest that ANNs will be valuable in extrapolating a dataset of collisional rate coefficients to include high-lying transitions that have not yet been calculated. For the asymmetric top molecules considered in this paper, the favored architecture is a cascade-correlation network that creates 16 hidden neurons during the course of training, with 3 input neurons to characterize the nature of the transition and one output neuron to provide the logarithm of the rate coefficient.

23 pages including 9 figures. Accepted for publication in ApJ

References in corpus (3)

• ANNz: estimating photometric redshifts using artificial neural networks
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• An Artificial Neural Network Approach to the Solution of Molecular Chemical Equilibrium

Cited by in corpus (11)

• Molecular excitation in the Interstellar Medium: recent advances in collisional, radiative and chemical processes
• Interstellar Hydrides
• Water in star-forming regions with Herschel: highly excited molecular emission from the NGC 1333 IRAS 4B outflow
• Deuterated molecules in Orion KL from Herschel/HIFI
• ALMA sub-mm maser and dust distribution of VY Canis Majoris
• C${}_2$H observations toward the Orion Bar
• Origin of warm and hot gas emission from low-mass protostars: Herschel-HIFI observations of CO J=16-15. I. Line profiles, physical conditions, and H2O abundance
• SOFIA/GREAT Discovery of Terahertz Water Masers
• The H${}_2$O Spectrum of the Massive Protostar AFGL 2136 IRS 1 from 2 to 13 $\mu$m at High Resolution: Probing the Circumstellar Disk
• Water Absorption from Gas Very Near the Massive Protostar AFGL 2136 IRS 1
• Herschel/HIFI observations of a new interstellar water maser: the 5(32)-4(41) transition at 620.701 GHz