Single hidden layer artificial neural network models versus multiple linear regression model in forecasting the time series of total ozone

Abstract

Present paper endeavors to develop predictive artificial neural network model for forecasting the mean monthly total ozone concentration over Arosa, Switzerland. Single hidden layer neural network models with variable number of nodes have been developed and their performances have been evaluated using the method of least squares and error estimation. Their performances have been compared with multiple linear regression model. Ultimately, single-hidden-layer model with 8 hidden nodes have been identified as the best predictive model.

Authors and Affiliations

G. Bandyopadhyay, S. Chattopadhyay

Keywords

Related Articles

Comparative utilization of phosphorus from sedimentary and igneous phosphate rock by major biotic components of aquatic ecosystem

Two laboratory experiments were conducted to evaluate the amount of P utilization from two different types of sparingly soluble phosphate rock by aquatic biotic communities. The first type was Mussoorie Phosphate Rock or...

Environmental management of coastal regions in the Caspian Sea<br />

Considering rapid population growth and migration, higher accumulation of communities is noticed in coastal areas. This is especially true with the coastal areas of the Caspian Sea. In the present investigation coastal a...

Evaluation of advanced rice germplasm under water stress environment

Thirteen genotypes of rice comprising of approved varieties and elite candidate lines were studied at three different water regimes by supplying 12, 8 and 4 numbers of irrigations at different intervals/ stages. The expe...

Assessment of degradation of agricultural soils arising from brick burning in selected soil profiles

The study was conducted with the selected soil profile of burnt (soil around brick kilns) and unburnt (agricultural land) soils in the Dinajpur, Rangpur, Rajshahi, Khulna and Patuakhali districts to evaluate the effects...

Length-weight relationship of sucker head, Garra Gotyla Gotyla (Gray, 1830) in different rivers of Nepal and the influence of monsoon

Size structure data particularly that of length and weight is very important fisheries management tool, which is also applied to assess the health, habitat and integrity of the rivers. Nepal is tremendously rich in both...

Download PDF file
  • EP ID EP83971
  • DOI -
  • Views 112
  • Downloads 0

How To Cite

G. Bandyopadhyay, S. Chattopadhyay (2007). Single hidden layer artificial neural network models versus multiple linear regression model in forecasting the time series of total ozone. International Journal of Environmental Science and Technology, 4(1), 141-149. https://europub.co.uk/articles/-A-83971