[Home ] [Archive]   [ فارسی ]  
:: Main :: About :: Current Issue :: Archive :: Search :: Submit :: Contact ::
:: ::
Back to the articles list Back to browse issues page
Estimation of PM10 concentration and generating pollution map with neural network and remote sensing images
Arsalan Ghorbanian Mr , Ali Mohammadzadeh Dr.
Abstract:   (35 Views)
obtaining reliable information about concentration and spatial pattern of particulate matter with the diameter smaller than 10 micron is a vital need. PM10 has been a popular subject for researchers because of its serious harmful effects on human health and the environment. for this purpose, pollution stations that have the ability to measure different pollutant concentration are located in various part of the cities. although these stations measure the number of pollutants with the high precision they are not spatially connected and only provide point observations. to overcome this problem, we can use remote sensing images in addition to ground measurements to estimate pollutant concentration and generate pollution maps with spatial continuity. in this study, ground measurements of 13 stations with MODIS images are used to estimate PM10 concentration. instead of using aerosol optical depth data, which is mostly used by researchers, we used aerosol's contribution to apparent reflectance images. limited researches have been carried out by ACR images therefore further investigations are required for performance evaluation. Artificial neural network with one, two and three hidden layers are used for modeling and estimation of PM10. The results of this study on 12 different days with the highest correlation coefficient of 0.9805 proved the high capability of the neural network in this field of study. Besides, a general model was trained for all days with the highest correlation coefficient of 0.503 using neural network regression.
Keywords: ACR, PM10, neural network, spatial distribution, MODIS
Type of Study: Research | Subject: Photo&RS
Send email to the article author

Add your comments about this article
Your username or Email:


XML   Persian Abstract   Print

Back to the articles list Back to browse issues page
نشریه علمی پژوهشی علوم و فنون نقشه برداری Journal of Geomatics Science and Technology