Dataset Information

Prediction of daily mean and one-hour maximum PM_2.5 concentrations and applications in Central Mexico using satellite-based machine-learning models.

ABSTRACT:

Background

Machine-learning algorithms are becoming popular techniques to predict ambient air PM_2.5 concentrations at high spatial resolutions (1 × 1 km) using satellite-based aerosol optical depth (AOD). Most machine-learning models have aimed to predict 24 h-averaged PM_2.5 concentrations (mean PM_2.5) in high-income regions. Over Mexico, none have been developed to predict subdaily peak levels, such as the maximum daily 1-h concentration (max PM_2.5).

Objective

Our goal was to develop a machine-learning model to predict mean PM_2.5 and max PM_2.5 concentrations in the Mexico City Metropolitan Area from 2004 through 2019.

Methods

We present a new modeling approach based on extreme gradient boosting (XGBoost) and inverse-distance weighting that uses AOD, meteorology, and land-use variables. We also investigated applications of our mean PM_2.5 predictions that can aid local authorities in air-quality management and public-health surveillance, such as the co-occurrence of high PM_2.5 and heat, compliance with local air-quality standards, and the relationship of PM_2.5 exposure with social marginalization.

Results

Our models for mean and max PM_2.5 exhibited good performance, with overall cross-validated mean absolute errors (MAE) of 3.68 and 9.20 μg/m³, respectively, compared to mean absolute deviations from the median (MAD) of 8.55 and 15.64 μg/m³. In 2010, everybody in the study region was exposed to unhealthy levels of PM_2.5. Hotter days had greater PM_2.5 concentrations. Finally, we found similar exposure to PM_2.5 across levels of social marginalization.

Significance

Machine learning algorithms can be used to predict highly spatiotemporally resolved PM_2.5 concentrations even in regions with sparse monitoring.

Impact

Our PM_2.5 predictions can aid local authorities in air-quality management and public-health surveillance, and they can advance epidemiological research in Central Mexico with state-of-the-art exposure assessment methods.

SUBMITTER: Gutierrez-Avila I

PROVIDER: S-EPMC9731899 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prediction of daily mean and one-hour maximum PM<sub>2.5</sub> concentrations and applications in Central Mexico using satellite-based machine-learning models.

Gutiérrez-Avila Iván I Arfer Kodi B KB Carrión Daniel D Rush Johnathan J Kloog Itai I Naeger Aaron R AR Grutter Michel M Páramo-Figueroa Víctor Hugo VH Riojas-Rodríguez Horacio H Just Allan C AC

Journal of exposure science & environmental epidemiology 20220910 6

<h4>Background</h4>Machine-learning algorithms are becoming popular techniques to predict ambient air PM<sub>2.5</sub> concentrations at high spatial resolutions (1 × 1 km) using satellite-based aerosol optical depth (AOD). Most machine-learning models have aimed to predict 24 h-averaged PM<sub>2.5</sub> concentrations (mean PM<sub>2.5</sub>) in high-income regions. Over Mexico, none have been developed to predict subdaily peak levels, such as the maximum daily 1-h concentration (max PM<sub>2.5< ...[more]

PMID: 36088418

Similar Datasets

Project description:Epidemiologic studies have found associations between fine particulate matter (PM2.5) exposure and adverse health effects using exposure models that incorporate monitoring data and other relevant information. Here, we use nine PM2.5 concentration models (i.e., exposure models) that span a wide range of methods to investigate i) PM2.5 concentrations in 2011, ii) potential changes in PM2.5 concentrations between 2011 and 2028 due to on-the-books regulations, and iii) PM2.5 exposure for the U.S. population and four racial/ethnic groups. The exposure models included two geophysical chemical transport models (CTMs), two interpolation methods, a satellite-derived aerosol optical depth-based method, a Bayesian statistical regression model, and three data-rich machine learning methods. We focused on annual predictions that were regridded to 12-km resolution over the conterminous U.S., but also considered 1-km predictions in sensitivity analyses. The exposure models predicted broadly consistent PM2.5 concentrations, with relatively high concentrations on average over the eastern U.S. and greater variability in the western U.S. However, differences in national concentration distributions (median standard deviation: 1.00 μg m-3) and spatial distributions over urban areas were evident. Further exploration of these differences and their implications for specific applications would be valuable. PM2.5 concentrations were estimated to decrease by about 1 μg m-3 on average due to modeled emission changes between 2011 and 2028, with decreases of more than 3 μg m-3 in areas with relatively high 2011 concentrations that were projected to experience relatively large emission reductions. Agreement among models was closer for population-weighted than uniformly weighted averages across the domain. About 50% of the population was estimated to experience PM2.5 concentrations less than 10 μg m-3 in 2011 and PM2.5 improvements of about 2 μg m-3 due to modeled emission changes between 2011 and 2028. Two inequality metrics were used to characterize differences in exposure among the four racial/ethnic groups. The metrics generally yielded consistent information and suggest that the modeled emission reductions between 2011 and 2028 would reduce absolute exposure inequality on average.

Project description:High concentrations of particulate matter (PM2.5) and frequent air pollution episodes in Beijing have attracted widespread attention. This paper utilizes data from the new air pollution network in China to examine the current spatial and temporal variability of PM2.5 at 12 monitoring sites in Beijing over a recent 2-year period (April 2013) to March 2015). The long term (2-year) average concentration was 83 µg·m-3, well above Chinese and international standards. Across the region, annual average concentrations varied by 20 µg·m-3 (25% of the average level), with lower levels in suburban areas compared to periurban and urban areas, which had similar concentrations. The spatial variation in PM2.5 concentrations was associated with several land use and economic variables, including the fraction of vegetated land and building construction activity, which together explained 71% of the spatial variation. Daily air quality was characterized as "polluted" (above 75 µg·m-3) on 36 to 47% of days, depending on site. There were 77 pollution episodes during the study period (defined as two or more consecutive days with Beijing-wide 24-hour average concentrations over 75 µg·m-3), and 2 to 5 episodes occurred each month, including summer months. The longest episode lasted 9 days and daily concentrations exceeded 450 µg·m-3. Daily PM2.5 levels were autocorrelated (rlag1 = 0.516) and associated with many meteorological variables, including barometric pressure, relative humidity, hours of sunshine, surface and ambient temperature, precipitation and scavenging coefficient, and wind direction. Parsimonious models with meteorological and autoregressive terms explained over 60% of the variation in daily PM2.5 levels. The first autoregressive term and hours of sunshine were the most important variables in these models, however, the latter variable is PM2.5-dependent and thus not an explanatory variable. The present study can serve as a baseline to compare the improved air quality in Beijing expected in future years.

Project description:Long-term PM2.5 exposure has been associated with various adverse health outcomes. However, most ground monitors are located in urban areas, leading to a potentially biased representation of true regional PM2.5 levels. To facilitate epidemiological studies, accurate estimates of the spatiotemporally continuous distribution of PM2.5 concentrations are important. Satellite-retrieved aerosol optical depth (AOD) has been increasingly used for PM2.5 concentration estimation due to its comprehensive spatial coverage. Nevertheless, previous studies indicated that an inherent disadvantage of many AOD products is their coarse spatial resolution. For instance, the available spatial resolutions of the Moderate Resolution Imaging Spectroradiometer (MODIS) and the Multiangle Imaging SpectroRadiometer (MISR) AOD products are 10 and 17.6 km, respectively. In this paper, a new AOD product with 1 km spatial resolution retrieved by the multi-angle implementation of atmospheric correction (MAIAC) algorithm based on MODIS measurements was used. A two-stage model was developed to account for both spatial and temporal variability in the PM2.5-AOD relationship by incorporating the MAIAC AOD, meteorological fields, and land use variables as predictors. Our study area is in the southeastern US centered at the Atlanta metro area, and data from 2001 to 2010 were collected from various sources. The model was fitted annually, and we obtained model fitting R2 ranging from 0.71 to 0.85, mean prediction error (MPE) from 1.73 to 2.50 μg m-3, and root mean squared prediction error (RMSPE) from 2.75 to 4.10 μg m-3. In addition, we found cross-validation R2 ranging from 0.62 to 0.78, MPE from 2.00 to 3.01 μgm-3, and RMSPE from 3.12 to 5.00 μgm-3, indicating a good agreement between the estimated and observed values. Spatial trends showed that high PM2.5 levels occurred in urban areas and along major highways, while low concentrations appeared in rural or mountainous areas. Our time-series analysis showed that, for the 10-year study period, the PM2.5 levels in the southeastern US have decreased by ∼20 %. The annual decrease has been relatively steady from 2001 to 2007 and from 2008 to 2010 while a significant drop occurred between 2007 and 2008. An observed increase in PM2.5 levels in year 2005 is attributed to elevated sulfate concentrations in the study area in warm months of 2005.

Project description:BackgroundChildhood exposure to air pollution has been linked with maladaptive cognitive development; however, less is known about the association between prenatal fine particulate matter (PM2.5) exposure and childhood behavior.ObjectivesOur aim was to assess the association between prenatal PM2.5 exposure and behavioral development in 4-6 year old children residing in Mexico City.MethodsWe used data from 539 mother-child pairs enrolled in a prospective birth cohort in Mexico City. We estimated daily PM2.5 exposure using a 1 km2 satellite-based exposure model and averaged over each trimester of pregnancy. We assessed childhood behavior at 4-6 years of age using the parent-completed Behavioral Assessment Scale for Children (BASC-2) composite scores and subscales. We used linear regression models to estimate change in BASC-2 T-scores with trimester specific 5-μg/m3 increases in PM2.5. All models were mutually adjusted for PM2.5 exposures during the other trimesters, maternal factors including age, education, socioeconomic status, depression, and IQ, child's age at study visit, and season. We additionally assessed sex-specific effects by including an interaction term between PM2.5 and sex.ResultsHigher first trimester PM2.5 exposure was associated with reduced Adaptive Skills scores (β: -1.45, 95% CI: -2.60, -0.30). Lower scores on the Adaptive Skills composite score and subscales indicate poorer functioning. For PM2.5 exposure during the first trimester, decrements were consistent across adaptive subscale scores including Adaptability (β: -1.51, 95% CI: -2.72, -0.30), Social Skills (β: -1.63, 95% CI: -2.90, -0.36), and Functional Communication (β: -1.21, 95% CI: -2.21, -0.21). The association between 1st trimester PM2.5 and depression was stronger in males than females (β for males: 1.52, 95% CI: -0.41, 3.45; β for females: -0.13, 95% CI: -1.99, 1.72; p-int: 0.07).ConclusionsExposure to PM2.5 during early pregnancy may be associated with impaired behavioral development in children, particularly for measures of adaptive skills. These results suggest that air pollution impacts behavioral domains as well as cognition, and that the timing of exposure may be critical.

Dataset Information

Prediction of daily mean and one-hour maximum PM_2.5 concentrations and applications in Central Mexico using satellite-based machine-learning models.

Background

Objective

Methods

Results

Significance

Impact

Publications

Prediction of daily mean and one-hour maximum PM<sub>2.5</sub> concentrations and applications in Central Mexico using satellite-based machine-learning models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

Prediction of daily mean and one-hour maximum PM2.5 concentrations and applications in Central Mexico using satellite-based machine-learning models.

Background

Objective

Methods

Results

Significance

Impact

Publications

Prediction of daily mean and one-hour maximum PM<sub>2.5</sub> concentrations and applications in Central Mexico using satellite-based machine-learning models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Prediction of daily mean and one-hour maximum PM_2.5 concentrations and applications in Central Mexico using satellite-based machine-learning models.