The advent of advanced features of soft computing can be used to solve complex problems which are more non-linear and messy. Many of the applications have been analysed and validated by the researchers through soft computing approach in the past.Neural Networks (NN) with appropriate selection of training parameters is implemented apart from conventional mathematical model. In this paper, analysis is made on the estimation of PM10 air quality in selected regions of Chennai district by wavelet approach with energy spectrograms. After analysing the results, NN of multilayer feed forward back propagation algorithm forecasts the air quality of selected regions. Discrepancies in selecting the training parameters of NN’s have been overcome by trial and error basis. This work will be helpful in proving the powerful tool of NN to forecast short term nonlinear parameters and the predicted results will give us the clear design of existing problem and thecontrol measures need to be implemented.

Today, indoor air pollution is a major concern. So far, many quantitative and qualitative studies have been conducted on particulate matter pollution in closed environments, but not much research has been done to measure air pollution in subway station. In this study, we have investigated the concentrations of PM10, PM2.5 and TSP particles in 12 underground stations on the oldest and main Tehran metro line, in two seasons, autumn and spring. For sampling suspended particles, we have used a portable direct reading device for monitoring suspended-particles (HAZDUST EPMA5000). We also used Pair T- test to compare the particle concentrations in different modes of the ventilation system (on, off, and inlet air) and Three-way variance analyze. According to the results, the mean concentrations of PM2.5-PM10 - TSP values in line-1 on the station platforms are significantly higher in spring than in autumn, off state of the ventilation system than on state of the ventilation system (P <0.001). Also, the concentration of particles measured in the air of subway stations is higher in the off state of ventilation systems, compared to Inlet air to stations (P<0.001). There is a correlation between concentration of particles measured in different sampling season, condition of the ventilation mode (on, off, inlet air) (P<0.001). Improving the efficiency of ventilation systems (equipped with a suitable filter) and fan in stations is suggested as one of the factors to reduce the concentration of particles, especially in spring.

Exposure to airborne particulates is a major occupational hazard especially for outdoor workers who spending time outdoors at ground level getting exposed to traffic fumes and roadside dust. Aim of this study was to assess respiratory health symptoms and determine the change of lung functions of the roadside vendors and its association with traffic-related exposures and their working experience. A cross-sectional study was conducted in key market places of Kolkata – Gariahat (GH), Esplanade-Park Street (EP), Shyambazar-Hatibagan (SH) and Behala (BE). Particulate (PM10 and PM2.5) levels and meteorological parameters (wind speed, temperature and relative humidity) were monitored in the morning, afternoon and night over the period of October 2019 to February 2020. Lung function status (FEV1, FVC, FEV1/FVC ratio and PEF) was measured for 111 purposively selected participants. PM concentration was observed higher in the morning and night peak hours for all sites. At SH area the average occupational exposure level for PM10 and PM2.5 were observed as 1502.22 μg/m3h and 684.01 μg/m3h. Percentage predicted FEV1 (%FEV1) of street vendors was found decreasing with their work experience and the worst-case scenario was observed in the EP area, with the corresponding value being 70.75%, 49.15% and 47.3% for less than 10 years, 10 to 20 years and more than 20 years participation respectively. The higher particulate burden was observed to have declining lung function status of the street vendors. A strong policy framework should be adopted to improve outdoor working environment for outdoor workers.

Ozone(O3), and its precursors, Benzene (C6H6), Nitrogen Dioxide(NO2), Carbon Monoxide (CO) and meteorological parameters Temperature, Relative Humidity and Wind Speed were measured in urban air of two sites of significant spatial variations, Delhi Milk Scheme (DMS), Sadipur and Netaji Subhash Chander Institute of Technology(NSIT) Dwarka, during 2017–2018. Samples collected by Central Pollution Control Board (CPCB) has been analysed. The concentrations of Benzene, Nitrogen dioxide and Carbon monoxide were found to be more at DMS than NSIT site in winter season (11.137±3.258, 5.540±1.441, 55.333±12.741, 44.667±10.066μg/m3, 1.433±0.058, 1.033±0.287mg/m3 respectively) and summer season (3.167±1.222, 2.233±0.929, 50.333±2.082, 31.333±6.658μg/m3, 0.743±0.151, 0.443±0.051mg/m3 respectively) while Ozone was found to be more at NSIT than DMS site (40.333±3.215, 34.433±2.503μg/m3 respectively). The maximum concentrations of Benzene for the DMS and NSIT sites, respectively, were 32.4μg/m3 and 17.7μg/m3 and was observed in the month of November while minimum were 1.0μg/m3 and 0.6μg/m3 and was observed in the month of June. For Ozone, the maximum concentrations for the DMS and NSIT sites, respectively, were 100μg/m3 and 101μg/m3 and was observed in the month of June while minimum were 33.0μg/m3 and 28.0μg/m3 and was observed in the month of February and December respectively. Regression analyses were performed to correlate O3 concentrations with C6H6, NO2 and CO in order to infer their possible sources. The study reveals that there is significant correlation of O3 with C6H6 (r2=0.475) and CO (r2=0.985) in summer at DMS and with C6H6 (r2=0.902) &amp; NO2(r2=0.728) in winter at NSIT. The correlation of O3, C6H6, NO2 and CO with Temperature, Relative Humidity and Wind Speed has also been investigated to understand their influence on these pollutants.

The little information available on fuel consumption and emissions by high seas tuna fisheries indicates that the global tuna fleet may have consumed about 2.5 Mt of fuel in 2009, resulting in the production of about 9 Mt of CO2-equivalent greenhouse gases (GHGs), i.e., about 4.5–5% of the global fishing fleet emissions. We developed a model of annual fuel consumption for the large-scale purse seiners operating in the western Indian Ocean as a function of fishing effort, strategy, and vessel characteristics based on an original and unique data set of more than 4300 bunkering operations that spanned the period 2013–2019. We used the model to estimate the total fuel consumption and associated GHG and SO2 emissions of the Indian Ocean purse seine fishery between 1981 and 2019. Our results showed that the energetic performance of this fishery was characterized by strong interannual variability over the last four decades. This resulted from a combination of variations in tuna abundance but also changes in catchability and fishing strategy. In recent years, the increased targeting of schools associated with fish aggregating devices in response to market incentives combined with the IOTC management measure implemented to rebuild the stock of yellowfin tuna has strongly modified the productivity and spatio-temporal patterns of purse seine fishing. This had effects on fuel consumption and air pollutant emissions. Over the period 2015 to 2019, the purse seine fishery, including its support vessel component, annually consumed about 160,000 t of fuel and emitted 590,000 t of CO2-eq GHG. Furthermore, our results showed that air pollutant emissions can be significantly reduced when limits in fuel composition are imposed. In 2015, SO2 air pollution exceeded 1500 t, but successive implementation of sulphur limits in the Indian Ocean purse seine fishery in 2016 and 2018 have almost eliminated this pollution. Our findings highlight the need for a routine monitoring of fuel consumption with standardized methods to better assess the determinants of fuel consumption in fisheries and the air pollutants they emit in the atmosphere.

Studies have reported significant reductions in air pollutant levels due to the COVID-19 outbreak worldwide global lockdowns. Nevertheless, all of the reports are limited compared to data from the same period over the past few years, providing mainly an overview of past events, with no future predictions. Lockdown level can be directly related to the number of new COVID-19 cases, air pollution, and economic restriction. As lockdown status varies considerably across the globe, there is a window for mega-cities to determine the optimum lockdown flexibility. To that end, firstly, we employed four different Artificial Neural Networks (ANN) to examine the compatibility to the original levels of CO, O₃, NO₂, NO, PM₂.₅, and PM₁₀, for São Paulo City, the current Pandemic epicenter in South America. After checking compatibility, we simulated four hypothetical scenarios: 10%, 30%, 70%, and 90% lockdown to predict air pollution levels. To our knowledge, ANN have not been applied to air pollution prediction by lockdown level. Using a limited database, the Multilayer Perceptron neural network has proven to be robust (with Mean Absolute Percentage Error ∼ 30%), with acceptable predictive power to estimate air pollution changes. We illustrate that air pollutant levels can effectively be controlled and predicted when flexible lockdown measures are implemented. The models will be a useful tool for governments to manage the delicate balance among lockdown, number of COVID-19 cases, and air pollution.

It is widely recognized that green infrastructures in urban ecosystems provides important ecosystem services, including air purification. The potential absorption of nitrogen oxides (NOₓ) by urban trees has not been fully quantified, although it is important for air pollution mitigation and the well-being of urban residents. In this study, four common tree species (Sophora japonica L., Fraxinus chinensis Roxb., Populus tomentosa Carrière, Sabina chinensis (L.)) in Beijing, China, were studied. The dual stable isotopes (¹⁵N and ¹⁸O) and a Bayesian isotope mixing model were applied to estimate the sources contributions of potential nitrogen sources to the roadside trees based on leaf and soil sampling in urban regions. The following order of sources contributions was determined: soil > dry deposition > traffic-related NOₓ. The capacity of urban trees for NOₓ removal in the city was estimated using a remote sensing and GIS approach, and the removal capacity was found to range from 0.79 to 1.11 g m⁻² a⁻¹ across administrative regions, indicating that 1304 tons of NOₓ could be potentially removed by urban trees in 2019. Our finding qualified the potential NOₓ removal by urban trees in terms of atmospheric pollution mitigation, highlighting the role of green infrastructure in air purification, which should be taken into account by stakeholders to manage green infrastructure as the basis of a nature-based approach.

The limited evidence available suggests that the interaction between chemical pollutants and biological particles may intensify respiratory diseases caused by air pollution in urban areas. Unlike air pollutants, which are routinely measured, records of biotic component are scarce. While pollen concentrations are daily surveyed in most cities, data related to airborne bacteria or fungi are not usually available. This work presents the first effort to understand atmospheric pollution integrating both biotic and abiotic agents, trying to identify relationships among the Proteobacteria, Actinobacteria and Ascomycota phyla with palynological, meteorological and air quality variables using all biological historical records available in the Madrid Greater Region. The tools employed involve statistical hypothesis contrast tests such as Kruskal-Wallis and machine learning algorithms. A cluster analysis was performed to analyse which abiotic variables were able to separate the biotic variables into groups. Significant relationships were found for temperature and relative humidity. In addition, the relative abundance of the biological phyla studied was affected by PM₁₀ and O₃ ambient concentration. Preliminary Generalized Additive Models (GAMs) to predict the biotic relative abundances based on these atmospheric variables were developed. The results (r = 0.70) were acceptable taking into account the scarcity of the available data. These models can be used as an indication of the biotic composition when no measurements are available. They are also a good starting point to continue working in the development of more accurate models and to investigate causal relationships.

The development of urbanised areas together with the growing transport infrastructure and traffic volume are the main cause of air quality deterioration due to the increasing concentrations of particulate matter. Dust pollution is a threat to human health. It can cause the development of lung, larynx or circulatory system cancer. Due to the ability to accumulate dust particles on the leaf surface, the contribution of trees in the process of phytoremediation of air pollution has started to be appreciated. An analysis of the elemental composition of particulate matter (PM) stored on the leaves surface was also carried out, which showed high average concentration of: C > O > Si > Fe (above 8wt.%). It was also observed single particles with a high concentration of heavy metals: Ti, Mn, Ba, Zn, Cr, Pb, Sn, Ni and REE (rare earth elements). The major origin of PM are vehicular emissions, soil and re-suspended road dust. This paper presents also a comparison of selected tree, shrub and vine species differing in their ability to accumulate particulate matter. It was experimentally determined the average leaf surface of individual plant species and established the amount of particulate matter with aerodynamic diameter between 10 and 100 μm, 2.5 and 10 μm, and 0.2 and 2.5 μm deposited on the leaf surface and in waxes.Some species of vines (Parthenocissus quinquefolia), shrubs (Forsythia x intermediata) and coniferous trees, such as Betula pendula ‘Youngii’, Quercus rubra, Cratageus monogyna, Acer pseduoplatanus, Tilia cordata Mill. or Platanus orientalis turned out to be the most efficient in the process of phylloremediation.

Evidence has shown associations between air pollution and traffic-related exposure with accelerated aging, but no study to date has linked the exposure with age at natural menopause, an important indicator of reproductive aging. In this study, we sought to examine the associations of residential exposure to ambient particulate matter (PM) and distance to major roadways with age at natural menopause in the Nurses’ Health Study II (NHS II), a large, prospective female cohort in US. A total of 105,996 premenopausal participants in NHS II were included at age 40 and followed through 2015. Time-varying residential exposures to PM₁₀, PM₂.₅₋₁₀, and PM₂.₅ and distance to roads was estimated. We calculated hazard ratios (HR) and 95% confidence intervals (CIs) for natural menopause using Cox proportional hazard models adjusting for potential confounders and predictors of age at menopause. We also examined effect modification by region, smoking, body mass, physical activity, menstrual cycle length, and population density. There were 64,340 reports of natural menopause throughout 1,059,229 person-years of follow-up. In fully adjusted models, a 10 μg/m³ increase in the cumulative average exposure to PM₁₀ (HR: 1.02, 95% CI: 1.00, 1.04), PM₂.₅₋₁₀ (HR: 1.03, 95% CI: 1.00, 1.05), and PM₂.₅ (HR: 1.03, 95% CI: 1.00, 1.06) and living within 50 m to a major road at age 40 (HR: 1.03, 95%CI: 1.00, 1.06) were associated with slightly earlier menopause. No statistically significant effect modification was found, although the associations of PM were slightly stronger for women who lived in the West and for never smokers. To conclude, we found exposure to ambient PM and traffic in midlife was associated with slightly earlier onset of natural menopause. Our results support previous evidence that exposure to air pollution and traffic may accelerate reproductive aging.