The negative health impacts of air pollution are well documented. Not as well-documented, however, is how particulate matter varies at the hyper-local scale, and the role that proximal sources play in influencing neighborhood-scale patterns. We examined PM_2.5 variations in one airshed within Indianapolis (Indianapolis, IN, USA) by utilizing data from 25 active PurpleAir (PA) sensors involving citizen scientists who hosted all but one unit (the control), as well as one EPA monitor. PA sensors report live measurements of PM_2.5 on a crowd sourced map. After calibrating the data utilizing relative humidity and testing it against a mobile air-quality unit and an EPA monitor, we analyzed PM_2.5 with meteorological data, tree canopy coverage, land use, and various census variables. Greater proximal tree canopy coverage was related to lower PM_2.5 concentrations, which translates to greater health benefits. A 1% increase in tree canopy at the census tract level, a boundary delineated by the US Census Bureau, results in a ~0.12 µg/m³ decrease in PM_2.5, and a 1% increase in “heavy industry” results in a 0.07 µg/m³ increase in PM_2.5 concentrations. Although the overall results from these 25 sites are within the annual ranges established by the EPA, they reveal substantial variations that reinforce the value of hyper-local sensing technologies as a powerful surveillance tool.

This study introduces a novel hybrid model combining Bayesian Stochastic Partial Differential Equations (SPDE) with deep learning, specifically Convolutional Neural Networks (CNN) and Deep Feedforward Neural Networks (DFFNN), to predict PM_2.5 concentrations. Traditional models often fail to account for non-linear relationships and complex spatial dependencies, critical in urban settings. By integrating SPDE’s spatial-temporal structure with neural networks’ capacity for non-linearity, our model significantly outperforms standalone methods. Accurately predicting air pollution supports sustainable public health strategies and targeted interventions, which are critical for mitigating the adverse health effects of PM_2.5, particularly in urban areas heavily impacted by climate change. The hybrid model was applied to the Pleasant Run Airshed in Indianapolis, Indiana, utilizing a comprehensive dataset that included PM_2.5 sensor data, meteorological variables, and land-use information. By combining SPDE’s ability to model spatial-temporal structures with the adaptive power of neural networks, the model achieved a high level of predictive accuracy, significantly outperforming standalone methods. Additionally, the model’s interpretability was enhanced through the use of SHAP (Shapley Additive Explanations) values, which provided insights into the contribution of each variable to the model’s predictions. This framework holds the potential for improving air quality monitoring and supports more targeted public health interventions and policy-making efforts.

A substantial reduction in global transport and industrial processes stemming from the novel SARS-CoV-2 coronavirus and subsequent pandemic resulted in sharp declines in emissions, including for NO₂. This has implications for human health, given the role that this gas plays in pulmonary disease and the findings that past exposure to air pollutants has been linked to the most adverse outcomes from COVID-19 disease, likely via various co-morbidities. To explore how much COVID-19 shutdown policies impacted urban air quality, we examined ground-based NO₂ sensor data from 11 U.S. cities from a two-month window (March–April) during shutdown in 2020, controlling for natural seasonal variability by using average changes in NO₂ over the previous five years for these cities. Levels of NO₂ and VMT reduction in March and April compared to January 2020 ranged between 11–65% and 11–89%, consistent with a sharp drop in vehicular traffic from shutdown-related travel restrictions. To explore this link closely, we gathered detailed traffic count data in one city—Indianapolis, Indiana—and found a strong correlation (0.90) between traffic counts/classification and vehicle miles travelled, a moderate correlation (0.54) between NO₂ and traffic related data, and an average reduction of 1.11 ppb of NO₂ linked to vehicular data. This finding indicates that targeted reduction in pollutants like NO₂ can be made by manipulating traffic patterns, thus potentially leading to more population-level health resilience in the future.

Fine particulate matter (PM_2.5) poses substantial urban health risks that vary across space, time, and population vulnerability. We integrate a spatio-temporal INLA–SPDE PM_2.5 field with an agent-based model (ABM) of 10,000 daily home–work commuters in Indianapolis’s Pleasant Run airshed (50 weeks; 250 m grid). The PM_2.5 surface fuses 23 corrected PurpleAir PA-II-SD sensors with meteorology, land use, road proximity, and MODIS AOD. Validation indicated strong agreement (leave-one-out R² = 0.79, RMSE = 3.5 μg/m³; EPA monitor comparison R² = 0.81, RMSE = 3.1 μg/m³). We model a spatial-equity counterfactual by assigning susceptibility independently of residence and workplace, isolating vulnerability from residential segregation. Under this design, annual PM_2.5 exposure was statistically indistinguishable across groups (16.22–16.29 μg/m³; max difference 0.07 μg/m³, 20 μg/m³) near industrial zones and arterials that increase within-group variability without creating between-group exposure gaps. These findings quantify a policy-relevant “floor effect” in environmental justice: even with perfect spatial equity, substantial health disparities remain driven by susceptibility. Effective mitigation, therefore, requires dual strategies—place-based emissions and mobility interventions to reduce exposure for all, paired with vulnerability-targeted health supports (screening, access to care, indoor air quality) to address irreducible risk. The data and code framework provides a reproducible baseline against which real-world segregation and mobility constraints can be assessed in future, stratified scenarios.