“School of Astronomy”

Back to Papers Home
Back to Papers of School of Astronomy

Paper   IPM / Astronomy / 12896
School of Astronomy
  Title:   Estimating the continuum of quasars using the Multilayer Perceptron Artificial Neural Network
1.  F. Jafari
2.  S.M. Barakati
3.  A. Aghaee
  Status:   Published
  Year:  2012
  Supported by:  IPM
Quasar continuum in the Lyman-alpha forest is not obvious, especially when its redshift and spectral resolution are very high and very low, respectively. Therefore, predicting this part of the spectrum using the wavelengths larger than that of quasar Lyman-alpha emission line is very important. In this paper, the quasar continua of 50 quasars are estimated using a multilayer perceptron artificial neural network which is trained and based on a conjugate gradient back-propagation algorithm. The neural network is trained using the data correspond to the wavelengths larger than that of the quasar Lyman-alpha emission line and also 10 random data which are smaller than the Lyman- emission, then, the whole spectrum will be estimated for that quasar.

Download TeX format
back to top
scroll left or right