Air quality prediction is highly important in view of the health impacts caused by exposure to air pollutants in urban air. This work has presented a model based on support vector machine (SVM) technique to predict daily average carbon monoxide (CO) concentrations in the atmosphere of Tehran. Two types of SVM regression models, i.e. -SVM and -SVM techniques, were used to predict average daily CO concentration as a function of 12 input variables. Then, forward selection (FS) technique was applied to reduce the number of input variables. After converting 12 input variables to 7 using the FS, they were fed to SVM models (FS-(-SVM) and FS-(-SVM)). Finally, a comparison among SVM models operation and previously developed techniques, i.e. classical regression model and artificial intelligent methods such as ANN and adaptive neuro-fuzzy inference system (ANFIS) was carried out. Determination of coefficient (R2) and mean absolute error (MAE) for -SVM (-SVM) were 0.87 (0.40) and 0.87 (0.41), respectively, while they were 0.90 (0.39) and 0.91 (0.35) for ANN and ANFIS, respectively. Results of developed SVM models indicated that both FS-(-SVM) and FS-(-SVM) regression techniques were superior. Furthermore, it was founded that the performance of FS-(-SVM) and FS-(-SVM) models were generally a bit better than the best FS-ANFIS and FS-ANN solutions for short term forecasting of CO concentrations.

The life cycle of diesel fuel in non-passenger vehicles was assessed for all registered vehicles in Qatar as of November 2017. The Greenhouse gases, Regulated Emissions, and Energy use in Transportation (GREET) model was used as a source of normalized data to evaluate diesel fuel emissions for all non-passenger vehicle categories. This work aims at estimating the emissions from all non-passenger diesel vehicles in Qatar and evaluating the impact of the fuel life cycle assessment. The emissions of CO2, NOx, CO, SO2, VOC, black carbon (BC), organic carbon, fine particulates PM2.5, and coarse particulates PM10 were evaluated. SO2 emissions were found to be dominant during the well to pump (WTP) stage of the life cycle assessment (LCA) process, while the pump to wheel (PTW) stage was found to be dominated by CO, VOC, PM10, PM2.5, and BC emissions. NOx and organic carbon emissions were virtually the same during both stages. Total greenhouse gas emissions amounted to 5367 kt of CO2 equivalent (CO2-eq) in 2017 as compared with that in 2014 (5277 kt), the only reported value in Qatar for transportation emissions. In addition, several mitigation strategies are proposed to ensure sustainability in the transport sector and to minimize the negative impact of diesel fuel emissions in the country.

Mitigation of atmospheric pollution has been a topic of concern over the past decades. In this study, tree rings have been used to reconstruct past climates as well as to assess the effects of recent climatic and environmental changes on tree growth. Vehicular emission is one of the major sources of pollutants in the atmosphere and this study focused on the Haatso-Atomic road which over the years has been a spot for heavy vehicular traffic. Swietenia mahagoni (Mahogany) tree was logged and the rings counted and age determined to be 61 years spanning from 1957 to 2018. X-ray fluorescence (XRF) was used to investigate the presence of the following heavy metals. Heavy metals (Cu, Mn, Zn, Pb, Cd and Ni) which ranged from (3.15—9.84mg/kg), (2.58 – 5.49 mg/kg), (8.18 – 15.78mg/kg), (0.12—0.60 mg/kg), (0.01—0.09 mg/kg) and (0.10 – 0.99 mg/kg) respectively, from vehicular emissions were determined for annual rings spanning from 1957 to 2018 and surprisingly an increasing trend was observed with some the heavy metals exceeding WHO guidelines. Tree growth rates were calculated through ring width measurements and related to annual precipitation data spanning over the sampling period. It was observed that wet seasons correlate with high growth rates of trees while low precipitations seasons related to low or no growth rate of trees.

Defined as any substance in the air that may harm humans, animals, vegetation, and materials, air pollution poses a great danger to human health. It has turned into a worldwide problem as well as a huge environmental risk. Recent years have witnessed the increase of air pollution in many cities around the world. Similarly, it has become a big problem in Iran. Although ground-level monitoring can provide accurate PM2.5 measurements, it has limited spatial coverage and resolution. As a result, Satellite Remote Sensing (RS) has emerged as an approach to estimate ground-level ambient air pollution, making it possible to monitor atmospheric particulate matters continuously and have a spatial coverage of them. Recent studies show a high correlation between ground level PM2.5, estimated by RS on the one hand, and measurements, collected at regulatory monitoring sites on the other. As such, the present study addresses the relation between air pollution and satellite images. For so doing, it derives RS estimates, using satellite measurements from Landsat satellite images. Monitoring data is the daily concentration of PM2.5 contaminants, obtained from air pollution stations. The relation between the concentration of pollutants and the values of various bands of Landsat satellite images is examined through 19 regression models. Among them, the Ensembles Bagged Trees has the lowest Root-Mean-Square Error (RMSE), equal to 21.88. Results show that this model can be used to estimate PM2.5 contaminants, based on Landsat satellite images.

The method of air pollution level evaluation of urban landscapes on the basis of D. melanogaster cohort analysis has been suggested. The method implies the binding to the landscape areas of the city. Within each landscape area traps and cultivators for D. melanogaster have been installed in sanitary-protective zones of various enterprises as well as on the background territory with the least level of anthropogenic load serving as the control. Based on specifically elaborated technique for field conditions, the amount of eggs, third instar larvae, pupae and imago has been calculated. Then, using the computer program ImageJ, the square under the curves of cohort survival has been determined which is considered overall cohort viability (OCVD.m). The previously mentioned indicator considers cohort survival at all stages of ontogenesis. In addition, the expressed in percentage indicator of oppression (IO OCVD.m) in relevance to the control OCVD. m affects the level of air pollution of urban landscapes by emissions of various enterprises. The relevance between these indicators is determined by a four-level scale elaborated specifically for the purpose. The method has been tested based on technogenic landscapes of Chernivtsi, Ukraine. The sensitivity of the suggested indicator for a wide range of pollutants has been proved and its ability to respond to different levels of greening of similar enterprises has been shown.