Traffic-related air pollution backcasting using convolutional neural network and long short-term memory approach.

Air pollution backcasting, especially nitrogen dioxide (NO), is crucial in epidemiological studies, thus enabling the reconstruction of historical exposure levels for assessing long-term health effects. Changes in NO concentrations in urban areas are typically influenced by vehicle composition, technology, and traffic volumes. However, the observed NO levels at a monitoring site also reflect contributions from other sources, such as industrial and regional backgrounds. This study proposes a model that captures the spatial variability of NO concentrations, incorporating temporal trends through traffic-related predictors like nitrogen oxides (NOx) emissions and Annual Average Daily Traffic (AADT). Our approach integrates a Convolutional Neural Network (CNN) for spatial variation and Long Short-Term Memory (LSTM) for long-term temporal dynamics, yielding optimal spatiotemporal predictions for NO levels across the City of Toronto, Canada. The model, trained with NO measurements collected via the Urban Scanner mobile platform in 2020 and 2021, utilizes a Traffic Emission Prediction scheme (TEPs) to develop NO and AADT inventories, serving as input to the LSTM model. Our proposed approach successfully estimates traffic-related NO levels across Toronto from 2006 to 2020. By intersecting the backcasted levels with census data, we noted that despite an overall decrease in NO levels between 2006 and 2020, disparities in exposure grew as more marginalized communities faced environmental injustice.