Click for new scientific resources and news about Corona[COVID-19]

Paper Information

Journal:   JOURNAL OF RS AND GIS FOR NATURAL RESOURCES (JOURNAL OF APPLIED RS AND GIS TECHNIQUES IN NATURAL RESOURCE SCIENCE)   FALL 2012 , Volume 3 , Number 3; Page(s) 21 To 35.
 
Paper: 

PREDICTION AND MODELING OF CARBON MONOXIDE CONCENTRATION WITH THE COMBINATION OF AN ADAPTIVE NEURO-FUZZY NETWORK AND GIS

 
 
Author(s):  KHAZAEI E.*, ALE SHEYKH A.A., KARIMI M., VAHIDNIA H.
 
* COLLEGE OF GEODESY AND GEOMATICS ENGINEERING, KHAJEH NASIR AD-DIN TOOSI UNIVERSITY OF TECHNOLOGY
 
Abstract: 

Nowadays, air pollution is the main environmental challenge in metropolises. Therefore, it is essential to monitor and forecast air quality parameters in urban areas. It depends upon various factors, including topography, climate, population and transportation network. The relationship between these special factors has been considered as a dynamic, the nonlinear and ambiguous phenomenon. In this study, an adaptive Neuro –fuzzy system and GIS have been used to extract knowledge of environment from data, in terms of fuzzy rules. These rules were used to predict and model carbon monoxide (CO) pollutant concentration. Tehran has been selected as the case study. The data gathered from six meteorological stations, for four consecutive years in summer, in this city were used separately to train the neural network. Fuzzy rules (Sugeno and Mamdani) were extracted for each station and then, using these rules; pollutant concentration was estimated. Having concentration predictions at station points, log- Kriging was used to model the spatial concentration in the area selected as the case study. The results showed that average RMSE of all stations using Sugeno rules is 1.445 and using Mamdani rules is 1.374.

 
Keyword(s): AIR POLLUTION, ADAPTIVE NEURO-FUZZY NETWORK, FUZZY SYSTEM, KRIGING, GIS
 
References: 
  • ندارد
 
  Persian Abstract Yearly Visit 90
 
Latest on Blog
Enter SID Blog