RESUMO
Ensuring environmental justice necessitates equitable access to air quality data, particularly for vulnerable communities. However, traditional air quality data from reference monitors can be costly and challenging to interpret without in-depth knowledge of local meteorology. Low-cost monitors present an opportunity to enhance data availability in developing countries and enable the establishment of local monitoring networks. While machine learning models have shown promise in atmospheric dispersion modelling, many existing approaches rely on complementary data sources that are inaccessible in low-income areas, such as smartphone tracking and real-time traffic monitoring. This study addresses these limitations by introducing deep learning-based models for particulate matter dispersion at the neighbourhood scale. The models utilize data from low-cost monitors and widely available free datasets, delivering root mean square errors (RMSE) below 2.9 µg m-3 for PM1, PM2.5, and PM10. The sensitivity analysis shows that the most important inputs to the models were the nearby monitors' PM concentrations, boundary layer dissipation and height, and precipitation variables. The models presented different sensitivities to each road type, and an RMSE below the regional differences, evidencing the learning of the spatial dependencies. This breakthrough paves the way for applications in various vulnerable localities, significantly improving air pollution data accessibility and contributing to environmental justice. Moreover, this work sets the stage for future research endeavours in refining the models and expanding data accessibility using alternative sources.
RESUMO
Background: The characterisation of individual exposure to air pollution in urban scenarios is a challenge in environmental epidemiological studies. We investigated if the city's pollution monitoring stations over or underestimate the exposure of individuals depending on their socioeconomic conditions and daily commuting times. Methods: The amount of black carbon accumulated in the lungs of 604 deceased who underwent autopsy in São Paulo was considered as a proxy for PM10. The concentrations of PM10 in the residence of the deceased were estimated by interpolating an ordinary kriging model. These two-exposure metrics allowed us to construct an environmental exposure misclassification index ranging from -1 to 1. The association between the index and daily commuting, socioeconomic context index (GeoSES), and street density as predictors was assessed by means of a multilevel linear regression model. Findings: With a decrease of 0.1 units in GeoSES, the index increases, on average, by 0.028 units and with an increase of 1 h in daily commuting, the index increases, on average, by 0.022 units indicating that individual exposure to air pollution is underestimated in the lower GeoSES and in people with many hours spent in daily commuting. Interpretation: Reduction of health consequences of air pollution demands not only alternative fuel and more efficient mobility strategies, but also should include profound rethink of cities. Funding: São Paulo Research Foundation (FAPESP-13/21728-2) and National Council for Scientific and Technological Development (CNPq-304126/2015-2, 401825/2020-5).
RESUMO
Vehicles are an important source of air pollutants and greenhouse gases. Their emissions have been controlled since the 1970s by laboratory tests but there are often found divergences to real-world emissions. Real driving emissions procedure is in implementation in many countries, for evaluating vehicles closer to actual operation. In order to reduce the dispersion of the results, some dynamic parameters, such as speed, acceleration, and CO2 emissions, are controlled; however, sometimes they are into the limits but divergences remain. This paper has the goal of applying VSP as an additional parameter for improving the evaluation of the vehicle dynamics, because it can better represent the engine power required for running as well as the road grade influence.