Spatiotemporal representativeness of air pollution monitoring in Dublin, Ireland

Semi-supervised urban haze pollution prediction based on multi-source heterogeneous data

Particulate matter (PM) is defined by the Texas Commission on Environmental Quality (TCEQ) as "a mixture of solid particles and liquid droplets found in the air". These particles vary widely in size. Those particles that are less than 2.5 μm in aerodynamic diameter are known as Particulate Matter 2.5 or PM2.5. Urban haze pollution represented by PM2.5 is becoming serious, so air pollution monitoring is very important. However, due to high cost, the number of air monitoring stations is limited. Our work focuses on integrating multi-source heterogeneous data of Nanchang, China, which includes Taxi track, human mobility, Road networks, Points of Interest (POIs), Meteorology (e.g., temperature, dew point, humidity, wind speed, wind direction, atmospheric pressure, weather activity, weather conditions) and PM2.5 forecast data of air monitoring stations. This research presents an innovative approach to air quality prediction by integrating the above data sets from various sources and utilizing diverse architectures in Nanchang City, China. So for that, semi-supervised learning techniques will be used, namely collaborative training algorithm Co-Training (Co-T), who further adjusting algorithm Tri-Training (Tri-T). The objective is to accurately estimate haze pollution by integrating and using these multi-source heterogeneous data. We achieved this for the first time by employing a semi-supervised co-training strategy to accurately estimate pollution levels after applying the U-air system to environmental data. In particular, the algorithm of U-Air system is reproduced on these highly diverse heterogeneous data of Nanchang City, and the semi-supervised learning Co-T and Tri-T are used to conduct more detailed urban haze pollution prediction. Compared with Co-T, which train time classifier (TC) and subspace classifier (SC) respectively from the separated spatio-temporal perspective, the Tri-T is more accurate with a and faster because of its testing accuracy up to 85.62 %. The forecast results also present the potential of the city multi-source heterogeneous data and the effectiveness of the semi-supervised learning. We hope that this synthesis will motivate atmospheric environmental officials, scientists, and environmentalists in China to explore machine learning technology for controlling the discharge of pollutants and environmental management.

The impact of dynamic traffic and wind conditions on green infrastructure performance to improve local air quality

Road traffic represents the dominant source of air pollution in urban street canyons. Local wind conditions greatly impacts the dispersion of these pollutants, yet street trees complicate ventilation in such settings. This case study adopts a novel modelling framework to account for dynamic traffic and wind conditions to identify the optimal street tree configuration that prevents a deterioration in air quality. Measurement data from a shallow to moderately deep street canyon (average 0.5 H/W aspect ratio and four lanes of 1-way traffic) in Dublin, Ireland was used for model calibration. The computational fluid dynamics (CFD) models were used to examine scenarios of dynamic traffic flows within each traffic lane with respect to its impact on local PM2.5 concentrations on adjacent footpaths, segmenting air quality monitoring results based on different wind conditions for model calibration. The monitoring campaign identified higher PM2.5 concentrations on the leeward (north) footpath, with average differences of 14.1 % (2.15 μg/m3) for early evening peaks. The modelling results demonstrated how street trees negatively impacted air quality on the windward footpath in parallel wind conditions regardless of leaf area density (LAD) or tree spacing, with mixed results observed on the leeward footpath in varying traffic flows and wind speeds. Perpendicular wind direction models and high wind speed exacerbated poor air quality on the windward footpath for all tree spacing models, while improving the air quality on the leeward footpath. The findings advise against planting high-LAD trees in this type of street, with a minimum of 20 m spacing for low-LAD trees to balance reducing local air pollution and ventilation capacity in the street. This study highlights the complexities of those in key decision-marking roles and demonstrates the need to adopt a transparent framework to ensure adequate modelling evidence can inform tree planting in city streets.

Co-occurrence of urban heat and the COVID-19: Impacts, drivers, methods, and implications for the post-pandemic era

Cities, the main place of human settlements, are under various mega challenges such as climate change, population increase, economic growth, urbanization, and pandemic diseases, and such challenges are mostly interlinked. Urban heat, due to heatwaves and heat islands, is the combined effect of climate change and urbanization. The COVID-19 is found to be a critical intervention of urban heat. However, the interrelationship between COVID-19 and urban heat has not been fully understood, constraining urban planning and design actions for improving the resilience to the dual impacts of heat and the pandemic. To close this research gap, this paper conducted a review on the co-occurrence of urban heat and the COVID-19 pandemic for a better understanding of their synergies, conflicts or trade-offs. The research involves a systematic review of urban temperature anomalies, variations in air pollutant concentrations, unbalanced energy development, and thermal health risks during the pandemic lockdown. In addition, this paper further explored data sources and analytical methods adopted to screen and identify the interventions of COVID-19 to urban heat. Overall, this paper is of significance for understanding the impact of COVID-19 on urban heat and provides a reference for coping with urban heat and the pandemic simultaneously. The world is witnessing the co-existence of heat and the pandemic, even in the post-pandemic era. This study can enlighten city managers, planners, the public, and researchers to collaborate for constructing a robust and resilient urban system for dealing with more than one challenges.