Search

Satellite-based particulate matter (PM) models provide spatially and temporally resolved estimations, allowing greater spatial-temporal coverage compared to sparse ground monitoring stations. The spatio-temporal resolution of these models can be improved using aerosol optical depth (AOD) products from various satellite platforms with different overpass times which can capture possible changes in diurnal aerosol concentrations. Israel is characterized by diverse geo-climatic regions and it is subjected to frequent dust storms events. Our goal was to estimate PM10 and PM2.5 concentrations in Israel on daily and intra-daily (mean PM around the Aqua and Terra overpasses) temporal resolutions and to assess the differences between these time windows. A hybrid modeling approach that consists of three stages was used enabling spatially continuous PM estimations at 1 × 1 km spatial resolution. The model was calibrated on a daily basis applying a mixed modeling approach using MODIS-based MAIAC AOD and various spatial and temporal predictors. It was found that in certain urban areas the measured and estimated PM concentrations during the satellite overpass (Terra or Aqua) were higher than the mean daily PM. The models performed well showing cross-validated R2 that ranged between 0.82 and 0.92. Mean estimated PM for the study period (2005–2015) during days with no dust events showed different spatial patterns for the daily and intra-daily estimations and revealed areas in Israel that are affected by high PM concentrations (mainly industrial or dense urban areas). Estimations from these models are useful for epidemiological research and might contribute to environmental regulatory purposes by focusing the efforts of PM pollution reduction at the identified polluted areas.

This work examines the impact of different environmental attributes on the uncertainty in satellite-based Aerosol Optical Depth (AOD) retrieval against the benchmark Aerosol Robotic Network (AERONET) AOD measurements at 21 sites across North Africa, California and Germany, in the years 2007–2017. As a first step, we studied the effects of spatial averaging the Multi-Angle Implementation of Atmospheric Correction (MAIAC) AOD retrievals, and of temporal averaging the AERONET AOD around the satellite (Aqua) overpass, on the agreement between the two products. AERONET AOD averaging over a time-window of ±15 min around the satellite overpass and the 1 × 1 km2 spatial grid of MAIAC were found to provide the best AOD retrieval performance. Next, MAIAC AOD were stratified according to different co-measured environmental attributes (aerosol loading, dominant particle size, vegetation cover, and prevailing particle type) and analyzed against the AERONET AOD. The envelope of the expected retrieval error varied considerably among different environmental attributes categories, with more accurate AOD retrievals obtained over highly vegetated areas (i.e. less surface reflectance) than over arid areas. Moreover, the retrieval accuracy was found to be sensitive to the aerosol loading and particle size, with a large bias between the MAIAC and AERONET AOD during high aerosol loading of coarse particles. In addition, the retrieval accuracy of MAIAC AOD was found to depend on the aerosol type due to the aerosol model assumptions regarding their optical properties.

Reconstructing the distribution of fine particulate matter (PM(2.5)) in space and time, even far from ground monitoring sites, is an important exposure science contribution to epidemiologic analyses of PM(2.5) health impacts. Flexible statistical methods for prediction have demonstrated the integration of satellite observations with other predictors, yet these algorithms are susceptible to overfitting the spatiotemporal structure of the training datasets. We present a new approach for predicting PM(2.5) using machine-learning methods and evaluating prediction models for the goal of making predictions where they were not previously available. We apply extreme gradient boosting (XGBoost) modeling to predict daily PM(2.5) on a 1×1 km(2) resolution for a 13 state region in the Northeastern USA for the years 2000–2015 using satellite-derived aerosol optical depth and implement a recursive feature selection to develop a parsimonious model. We demonstrate excellent predictions of withheld observations but also contrast an RMSE of 3.11 μg/m(3) in our spatial cross-validation withholding nearby sites versus an overfit RMSE of 2.10 μg/m(3) using a more conventional random ten-fold splitting of the dataset. As the field of exposure science moves forward with the use of advanced machine-learning approaches for spatiotemporal modeling of air pollutants, our results show the importance of addressing data leakage in training, overfitting to spatiotemporal structure, and the impact of the predominance of ground monitoring sites in dense urban sub-networks on model evaluation. The strengths of our resultant modeling approach for exposure in epidemiologic studies of PM(2.5) include improved efficiency, parsimony, and interpretability with robust validation while still accommodating complex spatiotemporal relationships.

Elevated levels of ambient air pollution has been implicated as a major risk factor for morbidities and premature mortality in India, with particularly high concentrations of particulate matter in the Indo-Gangetic plain. High resolution spatiotemporal estimates of such exposures are critical to assess health effects at an individual level. This article retrospectively assesses daily average PM2.5 exposure at 1 km × 1 km grids in Delhi, India from 2010 to 2016, using multiple data sources and ensemble averaging approaches. We used a multi-stage modeling exercise involving satellite data, land use variables, reanalysis based meteorological variables and population density. A calibration regression was used to model PM2.5: PM10 to counter the sparsity of ground monitoring data. The relationship between PM2.5 and its spatiotemporal predictors was modeled using six learners; generalized additive models, elastic net, support vector regressions, random forests, neural networks and extreme gradient boosting. Subsequently, these predictions were combined under a generalized additive model framework using a tensor product based spatial smoothing. Overall cross-validated prediction accuracy of the model was 80% over the study period with high spatial model accuracy and predicted annual average concentrations ranging from 87 to 138 μg/m3. Annual average root mean squared errors for the ensemble averaged predictions were in the range 39.7–62.7 μg/m3 with prediction bias ranging between 4.6 and 11.2 μg/m3. In addition, tree based learners such as random forests and extreme gradient boosting outperformed other algorithms. Our findings indicate important seasonal and geographical differences in particulate matter concentrations within Delhi over a significant period of time, with meteorological and land use features that discriminate most and least polluted regions. This exposure assessment can be used to estimate dose response relationships more accurately over a wide range of particulate matter concentrations.

The use of satellite-based aerosol optical depth (AOD) to estimate fine particulate matter PM(sub 2.5) for epidemiology studies has increased substantially over the past few years. These recent studies often report moderate predictive power, which can generate downward bias in effect estimates. In addition, AOD measurements have only moderate spatial resolution, and have substantial missing data. We make use of recent advances in MODIS satellite data processing algorithms (Multi-Angle Implementation of Atmospheric Correction (MAIAC), which allow us to use 1 km (versus currently available 10 km) resolution AOD data.We developed and cross validated models to predict daily PM(sub 2.5) at a 1X 1 km resolution across the northeastern USA (New England, New York and New Jersey) for the years 2003-2011, allowing us to better differentiate daily and long term exposure between urban, suburban, and rural areas. Additionally, we developed an approach that allows us to generate daily high-resolution 200 m localized predictions representing deviations from the area 1 X 1 km grid predictions. We used mixed models regressing PM(sub 2.5) measurements against day-specific random intercepts, and fixed and random AOD and temperature slopes. We then use generalized additive mixed models with spatial smoothing to generate grid cell predictions when AOD was missing. Finally, to get 200 m localized predictions, we regressed the residuals from the final model for each monitor against the local spatial and temporal variables at each monitoring site. Our model performance was excellent (mean out-of-sample R(sup 2) = 0.88). The spatial and temporal components of the out-of-sample results also presented very good fits to the withheld data (R(sup 2) = 0.87, R(sup)2 = 0.87). In addition, our results revealed very little bias in the predicted concentrations (Slope of predictions versus withheld observations = 0.99). Our daily model results show high predictive accuracy at high spatial resolutions and will be useful in reconstructing exposure histories for epidemiological studies across this region.

To date, spatial-temporal patterns of particulate matter (PM) within urban areas have primarily been examined using models. On the other hand, satellites extend spatial coverage but their spatial resolution is too coarse. In order to address this issue, here we report on spatial variability in PM levels derived from high 1 km resolution AOD product of Multi-Angle Implementation of Atmospheric Correction (MAIAC) algorithm developed for MODIS satellite. We apply day-specific calibrations of AOD data to predict PM(sub 2.5) concentrations within the New England area of the United States. To improve the accuracy of our model, land use and meteorological variables were incorporated. We used inverse probability weighting (IPW) to account for nonrandom missingness of AOD and nested regions within days to capture spatial variation. With this approach we can control for the inherent day-to-day variability in the AOD-PM(sub 2.5) relationship, which depends on time-varying parameters such as particle optical properties, vertical and diurnal concentration profiles and ground surface reflectance among others. Out-of-sample "ten-fold" cross-validation was used to quantify the accuracy of model predictions. Our results show that the model-predicted PM(sub 2.5) mass concentrations are highly correlated with the actual observations, with out-of- sample R(sub 2) of 0.89. Furthermore, our study shows that the model captures the pollution levels along highways and many urban locations thereby extending our ability to investigate the spatial patterns of urban air quality, such as examining exposures in areas with high traffic. Our results also show high accuracy within the cities of Boston and New Haven thereby indicating that MAIAC data can be used to examine intra-urban exposure contrasts in PM(sub 2.5) levels.

Traditional air pollution epidemiology studies being conducted in large cities can be limited by the availability of monitoring. Satellite Aerosol Optical Depth (AOD) measurements offer the possibility of exposure estimates for the entire population. We previously demonstrated that daily calibration substantially increased the predictive power of satellite AOD measurements for fine particles (PM 2.5 ) in New England, allowing estimation of exposure in locations without monitors. Similar results have not been reported for larger particles (PM 10 ), which are often the only measures that can be used in locations worldwide that do not have comprehensive PM 2.5 monitoring; this also applies to PM estimation of historical exposures. Here we extend this methodology by applying it to 2000–2009 PM 10 data from Lombardy, Northern Italy a region with high altitude differences, frequent temperature inversions and stationary fronts. Specifically, by 1) incorporating a model for missing AOD data to deal with non-randomness in the missing data; and 2) modeling interactions between land use and meteorological parameters to better capture space–time interactions. We calibrated AOD data through mixed-effect models regressing PM 10 measurements using day-specific random intercepts, and fixed and random AOD and temperature slopes. We used inverse-probability weighting to account for nonrandom AOD missingness, while reducing the dimensionality of spatial and temporal predictors and avoiding selecting different predictors in different locations, as common in land-use regression. We take advantage of associations of grid-cell AOD values with PM 10 monitoring located elsewhere and with AOD values in neighboring grid cells to develop grid-cell predictions when AOD is missing. By using ten-fold cross-validation to test the accuracy of our predictions, we found high out-of-sample R 2 ( R 2 = 0.787, year to year variation 0.738–0.818) for days with available AOD data. Even in days with no available AOD, our model performance was comparable ( R 2 = 0.787, year to year variation 0.736–0.841). Our results demonstrate that PM 10 can be reliably predicted using this AOD-based prediction model, even in a geographical area with complex geographic and weather patterns.

Land use regression (LUR) models provide good estimates of spatially resolved long-term exposures, but are poor at capturing short term exposures. Satellite-derived Aerosol Optical Depth (AOD) measurements have the potential to provide spatio-temporally resolved predictions of both long and short term exposures, but previous studies have generally showed relatively low predictive power. Our objective was to extend our previous work on day-specific calibrations of AOD data using ground PM2.5 measurements by incorporating commonly used LUR variables and meteorological variables, thus benefiting from both the spatial resolution from the LUR models and the spatio-temporal resolution from the satellite models. Later we use spatial smoothing to predict PM2.5 concentrations for day/locations with missing AOD measures. We used mixed models with random slopes for day to calibrate AOD data for 2000–2008 across New-England with monitored PM2.5 measurements. We then used a generalized additive mixed model with spatial smoothing to estimate PM2.5 in location–day pairs with missing AOD, using regional measured PM2.5, AOD values in neighboring cells, and land use. Finally, local (100 m) land use terms were used to model the difference between grid cell prediction and monitored value to capture very local traffic particles. Out-of-sample ten-fold cross-validation was used to quantify the accuracy of our predictions. For days with available AOD data we found high out-of-sample R2 (mean out-of-sample R2 = 0.830, year to year variation 0.725–0.904). For days without AOD values, our model performance was also excellent (mean out-of-sample R2 = 0.810, year to year variation 0.692–0.887). Importantly, these R2 are for daily, rather than monthly or yearly, values. Our model allows one to assess short term and long-term human exposures in order to investigate both the acute and chronic effects of ambient particles, respectively.