Sharif Digital Repository

A model to predict air pollutants' concentrations was developed by implementing spectral decomposition of time series data, obtained by Kolmogorov-Zurbenko filter, in Artificial Neural Networks (ANN). This model was utilized to separate and individually predict three spectral components of air pollutants' time series of short, seasonal, and long-term. The best set of input variable was selected by evaluating the significance of different input variables while modeling different time series components. Moreover, different possible approaches for constructing such models were examined. Performance of the constructed model to predict air pollutants' level at a central location in Tehran, Iran,... 

Frequent air pollution episodes have been reported for Tehran, Iran, mainly because of critically high levels of fine particulate matter (PM2.5). The composition and sources of these particles are poorly known, so this study aims to identify the major components and heavy metals in PM2.5along with their seasonal trends and associated sources. 24-hour PM2.5samples were collected at a main residential station every 6 days for a full year from February 2014 to February 2015. The samples were analyzed for ions, organic carbon (including water-soluble and insoluble portions), elemental carbon (EC), and all detectable elements. The dominant mass components, which were determined by means of... 

Missing or incomplete data in short or long intervals is a common problem in measuring air pollution. Severe issues may arise when dealing with missing data for time-series prediction schemes or mean analysis. This study aimed to develop a new regression imputation framework to impute missing values in the hourly air quality data set of Tehran and enhance the applicability of Tehran Air Pollution Forecasting System (TAPFS). The proposed framework was designed based on three types of features including measurements of other stations, WRF and CAMx physical models. In this framework, elastic net and neuro-fuzzy networks were efficiently combined in a two-layer structure. The framework was... 

The spatiotemporal variability of ambient volatile organic compounds (VOCs) in Tehran, Iran, is not well understood. Here we present the design, methods, and results of the Tehran Study of Exposure Prediction for Environmental Health Research (Tehran SEPEHR) on ambient concentrations of benzene, toluene, ethylbenzene, p-xylene, m-xylene, o-xylene (BTEX), and total BTEX. To date, this is the largest study of its kind in a low- and middle-income country and one of the largest globally. We measured BTEX concentrations at five reference sites and 174 distributed sites identified by a cluster analytic method. Samples were taken over 25 consecutive 2-weeks at five reference sites (to be used for...