RESUMO
High-quality, standardized urban canopy layer observations are a worldwide necessity for urban climate and air quality research and monitoring. The Schools Weather and Air Quality (SWAQ) network was developed and distributed across the Greater Sydney region with a view to establish a citizen-centred network for investigation of the intra-urban heterogeneity and inter-parameter dependency of all major urban climate and air quality metrics. The network comprises a matrix of eleven automatic weather stations, nested with a web of six automatic air quality stations, stretched across 2779 km2, with average spacing of 10.2 km. Six meteorological parameters and six air pollutants are recorded. The network has a focus on Sydney's western suburbs of rapid urbanization, but also extends to many eastern coastal sites where there are gaps in existing regulatory networks. Observations and metadata are available from September 2019 and undergo routine quality control, quality assurance and publication. Metadata, original datasets and quality-controlled datasets are open-source and available for extended academic and non-academic use.
RESUMO
With the escalation of heat- and pollution-related threats in cities across the globe, timely counteractions and emergency procedures are vital, which calls for accurate co-prediction of urban heat and air quality under both standard conditions and under extreme events. In this study, we used historical hourly data recorded at 9 sites across the Sydney metropolitan area to test the performance of long short-term memory (LSTM) forecasting architectures in predicting 5 urban pollutants based on different combinations of meteorological inputs and considering standard, bushfire, and pandemic lockdown conditions. We demonstrate that, in most cases and even in a fast-growing city, there is no significant benefit achieved by including extra predictors to temperature and humidity, when adequate forecasting techniques capable of learning long-term dependencies are used. Further, in agreement with previous studies, we provide evidence of ozone's higher responsiveness to all weather parameters and thus enhanced predictability and PM10's lower predictability as compared to all other considered urban pollutants. The prediction accuracy tends to be comparable between standard conditions and bushfire events. However, the predictability significantly declines under anomalies in anthropogenic patterns and urban metabolic rates as those recorded during the pandemic. The inclusion of local emission sources and anthropogenic factors in the input dataset is considered necessary for NO and PM10 to properly predict urban air quality, especially under human-related extreme conditions.