Predicting Traffic-Related Air Pollution Using Feature Extraction from Built Environment Images

Abstract

This study develops a set of algorithms to extract built environment features from Google aerial and street view images, reflecting the microcharacteristics of an urban location as well as the different functions of buildings. These features were used to train a Bayesian regularized artificial neural network (BRANN) model to predict near-road air quality based on measurements of ultrafine particles (UFPs) and black carbon (BC) in Toronto, Canada. The resulting models [adjusted R 2 of 75.87 and 79.10% for UFP and BC and root mean squared error (RMSE) of 21,800 part/cm 3 and 1300 ng/m 3 for UFP and BC] were compared with similar ANN models developed using the same predictors, but extracted from traditional geographic information system (GIS) databases [adjusted R 2 of 58.74 and 64.21% for UFP and BC and RMSE values of 23,000 part/ cm 3 and 1600 ng/m 3 for UFP and BC]. The models based on feature extraction exhibited higher predictive power, thus highlighting the greater accuracy of the proposed methods compared to GIS layers that are solely based on aerial images. A comparison with other neural network approaches as well as with a traditional land-use regression model demonstrates the strength of the BRANN model for spatial interpolation of air quality.

Predicting Within-City Spatial Variations in Outdoor Ultrafine Particle and Black Carbon Concentrations in Bucaramanga, Colombia: A Hybrid Approach Using Open-Source Geographic Data and Digital Images

“…In some areas of the 10-fold sensitivity analysis, the LUR model explained little (if any) of the variation in UFP and BC concentrations, and this would certainly contribute to reduced statistical power and considerable bias in effect estimates in epidemiological analyses. , This research adds to the growing body of literature demonstrating the utility of images as an additional source of information on associations between the urban physical environment and outcomes of interest. In our case, the outcome was air pollution, but other researchers have investigated the application of image-based analyses to predict other meaningful outcomes, including perceived neighborhood safety, health inequalities, land use, and elements of the urban environment. − While we cannot identify the specific image characteristics used to make predictions, the slopes for CNN predictions in linear models and GAM decreased when specific land use parameters were included in the models. Additionally, recall that overall model performance improved only modestly when combining CNN and LUR predictions.…”

Using an Exposome-Wide Approach to Explore the Impact of Urban Environments on Blood Pressure among Adults in Beijing–Tianjin–Hebei and Surrounding Areas of China

“…In the DAG (Figure S1), built environment, surrounding natural spaces and road traffic take up part of the urban design and are likely to determine the levels of air pollution in the city. , Hence, air pollution may be on the causal pathway between the urban design indicators and BP, that is, the mediator. While, the urban design indicators (i.e., built environment, surrounding natural spaces and road traffic) can be considered mutual confounders between each other, and are considered confounders between air pollution and BP.…”

What You See Is What You Breathe? Estimating Air Pollution Spatial Variation Using Street-Level Imagery

“…High quality air pollution measurements from ground measurement campaigns are required for development and calibration of city-wide air pollution models, yet they are very costly to implement and therefore not available to most cities around the world. Advances in deep learning methods and their success in computer vision applications has led to a growing interest in using images for estimating air pollution levels [8][9][10][11][12][13][14][15][16]. The rationale behind this interest is that information on pollution sources and common predictor variables used in traditional approaches (for example, land use, traffic, and built and natural environment features [17]) is, at least partially, visible from street-level and satellite images.…”