National Empirical Models of Air Pollution Using Microscale Measures of the Urban Environment

Abstract

National-scale empirical models of air pollution (e.g., Land Use Regression) rely on predictor variables (e.g., population density, land cover) at different geographic scales. These models typically lack microscale variables (e.g., street level), which may improve prediction with fine-spatial gradients. We developed microscale variables of the urban environment including Point of Interest (POI) data, Google Street View (GSV) imagery, and satellite-based measures of urban form. We developed United States national models for six criteria pollutants (NO 2 , PM 2.5 , O 3 , CO, PM 10 , SO 2 ) using various modeling approaches: Stepwise Regression + kriging (SW-K), Partial Least Squares + kriging (PLS-K), and Machine Learning + kriging (ML-K). We compared predictor variables (e.g., traditional vs microscale) and emerging modeling approaches (ML-K) to well-established approaches (i.e., traditional variables in a PLS-K or SW-K framework). We found that combined predictor variables (traditional + microscale) in the ML-K models outperformed the well-established approaches (10fold spatial cross-validation (CV) R 2 increased 0.02−0.42 [average: 0.19] among six criteria pollutants). Comparing all model types using microscale variables to models with traditional variables, the performance is similar (average difference of 10-fold spatial CV R 2 = 0.05) suggesting microscale variables are a suitable substitute for traditional variables. ML-K and microscale variables show promise for improving national empirical models.

Leveraging Citizen Science and Low-Cost Sensors to Characterize Air Pollution Exposure of Disadvantaged Communities in Southern California

“…This finding suggests that the built environment can be targeted to reduce the exposure disparity. For example, a number of studies have found that air pollution exposure could be impacted by small-scale differences in the built environment, including traffic and road geometry [ 67 ], impervious surface [ 68 , 69 ], greenness [ 70 ], walkability [ 71 ], the fragmentation of urban patches [ 70 ], and other factors [ 19 , 72 , 73 , 74 ]. Oftentimes, disadvantaged communities are near highways, have much fewer green spaces, much greater auto dependence, poor quality pavement streets, and residential segregation patterns [ 14 , 46 , 48 ], which may be associated with adverse air pollution exposure [ 73 ] and disparities [ 75 ].…”

National Land Use Regression Model for NO2 Using Street View Imagery and Satellite Observations

“…In recent years, innovative image data sources (e.g., street view imagery, high-resolution satellite imagery) have emerged as possible tools to capture hyperlocal characteristics of the natural and built environment. Image-based data may be promising for replacing or augmenting traditional LUR predictors , when enabled by imagery processing techniques (i.e., computer vision) and advanced modeling (e.g., machine learning) . For example, information (e.g., traffic, land use, built environment features) provided by traditional LUR predictors are also encoded in high-resolution digital images and can be extracted and quantified via advanced computer vision techniques.…”

“…As an emerging research topic, a small number of studies have explored using these new data sources to build empirical air quality models. ,,− For example, Lu et al compared national empirical models of six criteria pollutants using traditional LUR variables versus microscale variables (e.g., street view imagery, point of interest, local climate zones) . Similar model performance was achieved using the various combinations of variables, suggesting that microscale variables could be a suitable substitute for traditional predictors.…”

A global map of local climate zones to support earth system modelling and urban-scale environmental science

“…However, the typology has been used for other purposes (see also Lehnert et al, 2021, for European applications), such as urban heat (risk) assessment studies (Verdonck et al, 2019b;Van de Walle et al, 2022), climate-sensitive design, land use/land cover change, urban planning (policies) (Perera and Emmanuel, 2018;Aminipouri et al, 2019;Vandamme et al, 2019;Maharoof et al, 2020;Chen et al, 2021b;Zhi et al, 2021), anthropogenic heat, building energy demand and consump-tion, carbon emissions (Wu et al, 2018;Santos et al, 2020;Yang et al, 2020;Benjamin et al, 2021;Kotharkar et al, 2022), quality of life (Sapena et al, 2021), urban ventilation (Z. Zhao et al, 2020), air quality (Steeneveld et al, 2018T. Lu et al, 2021), urban vegetation phenology and ecosystem patterns, functions, and dynamics (Kabano et al, 2021;Zhao et al, 2022), and epidemiological studies (Brousse et al, 2019(Brousse et al, , 2020a.…”

“…Vandamme et al, 2019;Wang et al, 2019;Demuzere et al, 2020b;C. Zhao et al, 2020;Y. Lu et al, 2021;Zhi et al, 2021), yet they reveal large potential in terms of characterizing the temporal transformations of urban morphologies across and within different cities, identify the main drivers of such changes, and bridge the gap between policy-making and urbanization patterns required to come up with informed, data-driven, and rational urban planning strategies toward sustainable city developments.…”