Surveillance-image-based outdoor air quality monitoring

Air pollution threatens human health,necessitating effective and convenient air quality monitoring.Recently,there has been a growing interest in using camera images for air quality estimation.However,a major challenge has been nighttime detection due to the limited visibility of nighttime images.Here we present a hybrid deep learning model,capitalizing on the temporal continuity of air quality changes for estimating outdoor air quality from surveillance images.Our model,which integrates a convolutional neural network(CNN)and long short-term memory(LSTM),adeptly captures spatial-temporal image features,enabling air quality estimation at any time of day,including PM_(2.5) and PM10 concentrations,as well as the air quality index(AQI).Compared to independent CNN networks that solely extract spatial features,our model demonstrates superior accuracy on self-constructed datasets with R^(2)?0.94 and RMSE=5.11 mg m^(-3) for PM_(2.5),R^(2)=0.92 and RMSE=7.30 mg m^(-3) for PM10,and R^(2)=0.94 and RMSE?5.38 for AQI.Furthermore,our model excels in daytime air quality estimation and enhances nighttime predictions,elevating overall accuracy.Validation across diverse image datasets and comparative analyses underscore the applicability and superiority of our model,reaffirming its applicability and superiority for air quality monitoring.

Improving outdoor air quality based on building morphology:Numerical investigation

Due to rapid urbanization around the world,high concentrations of vehicular pollutants have deteriorated the outdoor air quality,which can affect the physical and psychological well-being of humans.Numerous strategies have been proposed to overcome these harmful impacts by improving the dispersion of air pollutants.Consequently,a question arises regarding the potential effects of building morphology on the dispersion of pollutants.Subsequently,transient three-dimensional Computational Fluid Dynamics(CFD)simulations are performed to examine the effect of building morphology on PM10 dispersion.Eleven cases with various prototypes and morphological methods are compared with a simple building form to identify the patterns of PM10 dispersion within a given time sequence under a prevailing inflow condition.The results indicate that the different designs of building morphology with varying Relative compactness(RC)indicator highlight the importance of considering morphological factors to improve outdoor air quality.In addition,the proposed prototypes can reduce PM10 concentrations by approximately 30%e90%at specific points in the studied time sequence.In particular,the vertical,horizontal,and grid folded prototypes can be considered more effective as an approximate decrease between 70%and 90%in PM10 concentrations is observed,which reflects the influence of building morphology on improving outdoor air quality.

Assessment of Air Pollution,by the Urban Traffic,in University Campus of Bucharest

This study aims to measure traffic-related air pollution of vehicles with internal combustion, the main source of emissions of BTEX, organic compounds and NOx, NO2, NO, O3, CO, SO2, PM10 and PM2.5, inorganic compounds, in three sites of the University campus, surrounded by residential areas. According to the University data, around 8000 students are being exposed daily to the measured level of pollution, in all 3 studied places of campus. A mobile laboratory was used, which continuously measures above mentioned pollutants and mete-orological parameters. The diurnal variation of BTEX, in a sunny and rainy day showed two peaks of BTEX concentration in the morning and evening. In the rainy days, the non-polar (hydrophobic) compounds as BTEX are mechanically trained by rain into the ground, where either they enter into the groundwater, or volatilized and re-enter in the air. Particulate matter such as PM10 and PM2.5 is, in a large part, carried by the rain into the soil. The polar compounds (hydrophilic, NOx, SO2) dissolves in the rainwater and are absorbed in the soil (increasing soil acidity) and evaporated towards the clouds (leading to acid rain). In our study, BTEX compounds removed by the rain varied between 62% - 75%, NOx and SO2, 80% and 77% respectively. Particulate matters were washed out up to 68% for PM10, and 42% for PM2.5. In the sunny days the air pollution with measured concentrations of O3 (121.66 ± 7.02, 123.56 ± 4.89 μg/m3) remained for 7 hours close to the limit value (120 μg/m3). The maximum of solar radiation, with corresponding low concentrations in NOx and xylene, corresponds to photochemical reactions in the atmosphere, generating photochemical smog. In a sunny day and high traffic, we found the maximum value 5.4 μg/m3 for benzene, for 30 min., a known human carcinogen, exceeding the annual limit value de 5 μg/m3. The average background, from benzene, in three University campuses daily visited by around 8000 students was 0.97 μg/m3, exposed to 1.46 μg/m3 and the cancer risk is 1/100,000.