Search

Particulate matter is one of the most dangerous air pollutants, especially in urban areas, due to its significant adverse health effects. Traditionally, air quality monitoring relies on fixed reference stations, which often have a low temporal and spatial resolution. To address this limitation, a low-cost, portable air quality monitoring device with a rapid measurement response was used to assess particulate matter concentration levels in the afternoon hours in central Thessaloniki, Greece. This approach enabled the identification of local hotspots directly related to human activities. Statistical analysis and spatial mapping were employed, and data collected were categorized using k-means clustering. The findings of the study suggest that data acquired via portable low-cost sensors can describe the local variability of PM2.5 concentrations. The results indicate that local activities, such as increased human accumulation, traffic congestion at traffic lights, market working hours, together with meteorological parameters, can significantly impact air quality in specific urban locations. They also highlight the differences between data recorded in colder and warmer periods, with the concentrations of PM2.5 in the first period being 3.7 μg/m3 greater on average than in the second. These differences are also identified via the k-means clustering method, which suggest that higher concentrations appear mostly during the colder period of the study. [ABSTRACT FROM AUTHOR]

By deploying machine learning (ML) and deep learning (DL) algorithms, we address the problem of smell event modelling in the Pittsburgh metropolitan area. We use the Smell Pittsburgh dataset to develop a model that can reflect the relation between bad smell events and industrial pollutants in a specific urban territory. The initial dataset resulted from crowd-sourcing citizen reports using a mobile phone application, which we categorised in a binary matter (existence or absence of smell events). We investigate the mapping of smell data with air pollution levels that were recorded by a reference station located in the southeastern area of the city. The initial dataset is processed and evaluated to produce an updated dataset, which is used as an input to assess various ML and DL models for modelling smell events. The models utilise a set of air quality and climate data to associate them with a smell event to investigate to what extent these data correlate with unpleasant odours in the Pittsburgh metropolitan area. The model results are satisfactory, reaching an accuracy of 69.6, with ML models mostly outperforming DL models. This work also demonstrates the feasibility of combining environmental modelling with crowd-sourced information, which may be adopted in other cities when relevant data are available. [ABSTRACT FROM AUTHOR]