Estimating PM_2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g, wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use. Using ensemble-based deep learning with big data fused from multiple sources we developed a PM_2.5 prediction model with uncertainty estimates at a high spatial (1km × 1km) and temporal (weekly) resolution for a 10-year time span (2008–2017). We leveraged autoencoder-based full residual deep networks to model complex nonlinear interrelationships among PM_2.5 emission, transport and dispersion factors and other influential features. These included remote sensing data (MAIAC aerosol optical depth (AOD), normalized difference vegetation index, impervious surface), MERRA-2 GMI Replay Simulation (M2GMI) output, wildfire smoke plume dispersion, meteorology, land cover, traffic, elevation, and spatiotemporal trends (geo-coordinates, temporal basis functions, time index). As one of the primary predictors of interest with substantial missing data in California related to bright surfaces, cloud cover and other known interferences, missing MAIAC AOD observations were imputed and adjusted for relative humidity and vertical distribution. Wildfire smoke contribution to PM_2.5 was also calculated through HYSPLIT dispersion modeling of smoke emissions derived from MODIS fire radiative power using the Fire Energetics and Emissions Research version 1.0 model. Ensemble deep learning to predict PM_2.5 achieved an overall mean training RMSE of 1.54 μg/m³ (R²: 0.94) and test RMSE of 2.29 μg/m³ (R²: 0.87). The top predictors included M2GMI carbon monoxide mixing ratio in the bottom layer, temporal basis functions, spatial location, air temperature, MAIAC AOD, and PM_2.5 sea salt mass concentration. In an independent test using three long-term AQS sites and one short-term non-AQS site, our model achieved a high correlation (>0.8) and a low RMSE (<3 μg/m³). Statewide predictions indicated that our model can capture the spatial distribution and temporal peaks in wildfire-related PM_2.5. The coefficient of variation indicated highest uncertainty over deciduous and mixed forests and open water land covers. Our method can be generalized to other regions, including those having a mix of major urban areas, deserts, intensive smoke events, snow cover and complex terrains, where PM_2.5 has previously been challenging to predict. Prediction uncertainty estimates can also inform further model development and measurement error evaluations in exposure and health studies.

(1) Background: The developmental origins of health and disease (DOHaD) hypothesis links adverse fetal exposures with developmental mal-adaptations and morbidity later in life. Short- and long-term exposures to air pollutants are known contributors to health outcomes; however, the potential for developmental health effects of air pollution exposures during gestation or early-childhood have yet to be reviewed and synthesized from a DOHaD lens. The objective of this study is to summarize the literature on cardiovascular and metabolic, respiratory, allergic, and neuropsychological health outcomes, from prenatal development through early childhood, associated with early-life exposures to outdoor air pollutants, including traffic-related and wildfire-generated air pollutants. (2) Methods: We conducted a search using PubMed and the references of articles previously known to the authors. We selected papers that investigated health outcomes during fetal or childhood development in association with early-life ambient or source-specific air pollution exposure. (3) Results: The current literature reports that prenatal and early-childhood exposures to ambient and traffic-related air pollutants are associated with a range of adverse outcomes in early life, including cardiovascular and metabolic, respiratory and allergic, and neurodevelopmental outcomes. Very few studies have investigated associations between wildfire-related air pollution exposure and health outcomes during prenatal, postnatal, or childhood development. (4) Conclusion: Evidence from January 2000 to January 2022 supports a role for prenatal and early-childhood air pollution exposures adversely affecting health outcomes during development. Future studies are needed to identify both detrimental air pollutants from the exposure mixture and critical exposure time periods, investigate emerging exposure sources such as wildfire, and develop feasible interventional tools.

Wildfires in the Western United States are a growing and significant source of air pollution that is eroding decades of progress in air pollution reduction. The effects on preterm birth during critical periods of pregnancy are unknown. We assessed associations between prenatal exposure to wildland fire smoke and risk of preterm birth (gestational age < 37 weeks). We assigned smoke exposure to geocoded residence at birth for all live singleton births in California conceived 2007-2018, using weekly average concentrations of particulate matter ≤ 2.5 µm (PM_2.5) attributable to wildland fires from United States Environmental Protection Agency's Community Multiscale Air Quality Model. Logistic regression yielded odds ratio (OR) for preterm birth in relation to increases in average exposure across the whole pregnancy, each trimester, and each week of pregnancy. Models adjusted for season, age, education, race/ethnicity, medical insurance, and smoking of the birthing parent. For the 5,155,026 births, higher wildland fire PM_2.5 exposure averaged across pregnancy, or any trimester, was associated with higher odds of preterm birth. The OR for an increase of 1 µg/m³ of average wildland fire PM_2.5 during pregnancy was 1.013 (95 % CI:1.008,1.017). Wildland fire PM_2.5 during most weeks of pregnancy was associated with higher odds. Strongest estimates were observed in weeks in the second and third trimesters. A 10 µg/m³ increase in average wildland fire PM_2·5 in gestational week 23 was associated with OR = 1.034; 95 % CI: 1.019, 1.049 for preterm birth. Preterm birth is sensitive to wildland fire PM_2.5; therefore, we must reduce exposure during pregnancy.

Low-cost sensors can provide insight on the spatio-temporal variability of air pollution, provided that sufficient efforts are made to ensure data quality. Here, 19 AirBeam particulate matter (PM) sensors were deployed from December 2016 to January 2017 to determine the spatial variability of PM_2.5 in Sacramento, California. Prior to, and after, the study, the 19 sensors were deployed and collocated at a regulatory air monitoring site. The sensors demonstrated a high degree of precision during all collocated measurement periods (Pearson R² = 0.98 − 0.99 across all sensors), with little drift. A sensor-specific correction factor was developed such that each sensor reported a comparable value. Sensors had a moderate degree of correlation with regulatory monitors during the study (R² = 0.60 − 0.68 at two sites). In a multi-linear regression model, the deviation between sensor and reference measurements of PM_2.5 had the highest correlation with dew point and relative humidity. Sensor measurements were used to estimate the PM_2.5 spatial variability, finding an average pairwise coefficient of divergence of 0.22 and a range of 0.14 to 0.33, indicating mostly homogeneous distributions. No significant difference in the average sensor PM concentrations between environmental justice (EJ) and non-EJ communities (p value = 0.24) was observed.

Air pollution has been associated with gestational diabetes mellitus (GDM). We aim to investigate susceptible windows of air pollution exposure and factors determining population vulnerability. We ascertained GDM status in the prospective Maternal and Developmental Risks from Environmental and Social Stressors (MADRES) pregnancy cohort from Los Angeles, California, USA. We calculated the relative risk of GDM by exposure to ambient particulate matter (PM₁₀; PM_2.5), nitrogen dioxide (NO₂), and ozone (O₃) in each week from 12 weeks before to 24 weeks after conception, adjusting for potential confounders, with distributed lag models to identify susceptible exposure windows. We examined effect modification by prenatal depression, median-split pre-pregnancy BMI (ppBMI) and age. Sixty (9.7%) participants were diagnosed with GDM among 617 participants (mean age: 28.2 years, SD: 5.9; 78.6% Hispanic, 11.8% non-Hispanic Black). GDM risk increased with exposure to PM_2.5, PM₁₀, and NO₂ in a periconceptional window ranging from 5 weeks before to 5 weeks after conception: interquartile-range increases in PM_2.5, PM₁₀, and NO₂ during this window were associated with increased GDM risk by 5.7% (95% CI: 4.6–6.8), 8.9% (8.1–9.6), and 15.0% (13.9–16.2), respectively. These sensitive windows generally widened, with greater effects, among those with prenatal depression, with age ≥28 years, or with ppBMI ≥27.5 kg/m², than their counterparts. Preconception and early-pregnancy are susceptible windows of air pollutants exposure that increased GDM risk. Prenatal depression, higher age, or higher ppBMI may increase one’s vulnerability to air pollution-associated GDM risk. 10.13039/100000002 National Institutes of Health , 10.13039/501100001589 Environmental Protection Agency .