Prediction of Short-Term Ultrafine Particle Exposures Using Real-Time Street-Level Images Paired with Air Quality Measurements.

Within-city ultrafine particle (UFP) concentrations vary sharply since they are influenced by various factors. We developed prediction models for short-term UFP exposures using street-level images collected by a camera installed on a vehicle rooftop, paired with air quality measurements conducted during a large-scale mobile monitoring campaign in Toronto, Canada. Convolutional neural network models were trained to extract traffic and built environment features from images. These features, along with regional air quality and meteorology data were used to predict short-term UFP concentration as a continuous and categorical variable. A gradient boost model for UFP as a continuous variable achieved R2 = 0.66 and RMSE = 9391.8#/cm3 (mean values for 10-fold cross-validation). The model predicting categorical UFP achieved accuracies for "Low" and "High" UFP of 77 and 70%, respectively. The presence of trucks and other traffic parameters were associated with higher UFPs, and the spatial distribution of elevated short-term UFP followed the distribution of single-unit trucks. This study demonstrates that pictures captured on urban streets, associated with regional air quality and meteorology, can adequately predict short-term UFP exposure. Capturing the spatial distribution of high-frequency short-term UFP spikes in urban areas provides crucial information for the management of near-road air pollution hot spots.

Emerging canine leptospirosis in Sydney and the role of population demographics.

An outbreak of canine leptospirosis commenced in Sydney, Australia in 2017. The aim of this retrospective study was to determine if clusters of leptospirosis occurred during this outbreak, and if these were associated with host factors, to assist investigation of the drivers of emerging leptospirosis at this location. Within the City of Sydney local government area, 13 cases were reported during the outbreak. Administrative data on the canine population were collected and mapped. Clusters of leptospirosis cases were detected using a retrospective space-time analysis and a discrete Poisson probability statistical model. Sydney dog population registration [55.6%, 95% confidence interval (CI) 51.8-58.1%] was lower than the Australian national average (80%). The distribution of dog types, based on the United Kennel Club standards, was significantly (p < .0001) different to that of the national profile: there was a distinct preference in Sydney for companion dogs. The age distribution of dogs in Sydney did not reflect a typical right-skewed curve; instead, a relatively uniform distribution was observed between the age group of 1 to 8 years. A primary disease cluster (radius 1.1 km) in the eastern area of the Sydney City Council was identified (4 cases observed between 24 May and 9 August 2019 vs. 0.10 cases expected), p = .0450. When adjusted for the age, breed type and sex distribution of the population, similar clusters were identified; in the case of age-adjustment, the spatiotemporal cluster identified was larger and of longer duration (seven cases observed between 28 June and 11 November 2019 versus 0.34 cases expected), p = .0025. The presence of clusters of canine leptospirosis in the City of Sydney during this outbreak, which persisted after adjustment for demographics (age, sex, breed type), suggest that environmental factors - rather than host or pathogen factors - might be responsible for the emergence of leptospirosis. Environmental factors that potentially might be linked to this outbreak of canine leptospirosis and the clusters observed require investigation.