Single hidden layer artificial neural network models versus multiple linear regression model in forecasting the time series of total ozone
Journal Title: International Journal of Environmental Science and Technology - Year 2007, Vol 4, Issue 1
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
- EP ID EP83971
- DOI -
- Views 94
- Downloads 0
Cadmium absorption and accumulation in different parts of kidney beans, radishes and pumpkins
This study is done to measure the absorption and distribution of cadmium in different parts of kidney beans, radishes and pumpkins. Three parts of a field was chosen. In one part 65 ppm of cadmium nitrate was added to wa...
Flow and high sediment yield from the Huangfuchuan watershed
This study deals with general features of sediment transport in the Huangfuchuan river, an important branch river of the Yellow river, draining the Loess Plateau in China. The long-term precipitation records at 3 climate...
Impacts of soil acidity on qualitative and quantitative conditions of broadleaf and coniferous trees<br />
To recognize the impacts of soil acidity on quantitative and qualitative conditions of broadleaf and coniferous trees in Syyahkal watershed region of northern Iran, hand-cultivated adjacent stands of different species of...
Application of Chitin and Zeolite Adsorbents for Treatment of Low Level Radioactive Liquid Wastes<br />
Two types of Shrimp Chitin derivatives and two types of Iranian natural Zeolite derivatives (Firuzkooh Clinoptiliolite) were studied for adsorption and treatment of low-level radioactive liquid waste (LLW). Chitin with l...
Use of horizontal flow roughing filtration in drinking water treatment
In order to evaluate the feasibility of implementation of horizontal-flow roughing filtration for drinking water treatment a pilot was designed and run at the bank of Zayandehroud river near the village of Chamkhalifeh....