RATE COEFFICIENTS FOR THE COLLISIONAL EXCITATION OF MOLECULES: ESTIMATES FROM AN ARTIFICIAL NEURAL NETWORK
- Department of Physics and Astronomy, Johns Hopkins University, 3400 North Charles Street, Baltimore, MD 21218 (United States)
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 data set of collisionally induced transitions for which rate coefficients are already known: the network is trained on a subset of that data set and tested on the remainder. Results obtained by this method are typically accurate to within a factor of approx2.1 (median value) for transitions with low excitation rates and approx1.7 for those with medium or high excitation rates, although 4% of the ANN outputs are discrepant by a factor of 10 or more. The results suggest that ANNs will be valuable in extrapolating a data set 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 three input neurons to characterize the nature of the transition and one output neuron to provide the logarithm of the rate coefficient.
- OSTI ID:
- 21392463
- Journal Information:
- Astrophysical Journal, Vol. 708, Issue 1; Other Information: DOI: 10.1088/0004-637X/708/1/635; ISSN 0004-637X
- Country of Publication:
- United States
- Language:
- English
Similar Records
Prediction of Weld Penetration in FCAW of HSLA steel using Artificial Neural Networks
Predicting stream water quality using artificial neural networks (ANN)