Dataset Information

Multivariate Air Pollution Prediction Modeling with partial Missingness.

ABSTRACT: Missing observations from air pollution monitoring networks have posed a longstanding problem for health investigators of air pollution. Growing interest in mixtures of air pollutants has further complicated this problem, as many new challenges have arisen that require development of novel methods. The objective of this study is to develop a methodology for multivariate prediction of air pollution. We focus specifically on tackling different forms of missing data, such as: spatial (sparse sites), outcome (pollutants not measured at some sites), and temporal (varieties of interrupted time series). To address these challenges, we develop a novel multivariate fusion framework, which leverages the observed inter-pollutant correlation structure to reduce error in the simultaneous prediction of multiple air pollutants. Our joint fusion model employs predictions from the Environmental Protection Agency's Community Multiscale Air Quality (CMAQ) model along with spatio-temporal error terms. We have implemented our models on both simulated data and a case study in South Carolina for 8 pollutants over a 28-day period in June 2006. We found that our model, which uses a multivariate correlated error in a Bayesian framework, showed promising predictive accuracy particularly for gaseous pollutants.

SUBMITTER: Boaz RM

PROVIDER: S-EPMC6980235 | biostudies-literature | 2019 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multivariate Air Pollution Prediction Modeling with partial Missingness.

Boaz R M RM Lawson A B AB Pearce J L JL

Environmetrics 20190703 7

Missing observations from air pollution monitoring networks have posed a longstanding problem for health investigators of air pollution. Growing interest in mixtures of air pollutants has further complicated this problem, as many new challenges have arisen that require development of novel methods. The objective of this study is to develop a methodology for multivariate prediction of air pollution. We focus specifically on tackling different forms of missing data, such as: spatial (sparse sites) ...[more]

PMID: 31983873

Similar Datasets

Project description:BackgroundThe era of big data has enabled sophisticated models to predict air pollution concentrations over space and time. Historically these models have been evaluated using overall metrics that measure how close predictions are to monitoring data. However, overall methods are not designed to distinguish error at timescales most relevant for epidemiologic studies, such as day-to-day errors that impact studies of short-term health associations.MethodsWe introduce frequency band model performance, which quantifies health estimation capacity of air quality prediction models for time series studies of air pollution and health. Frequency band model performance uses a discrete Fourier transform to evaluate prediction models at timescales of interest. We simulated fine particulate matter (PM2.5), with errors at timescales varying from acute to seasonal, and health time series data. To compare evaluation approaches, we use correlations and root mean squared error (RMSE). Additionally, we assess health estimation capacity through bias and RMSE in estimated health associations. We apply frequency band model performance to PM2.5 predictions at 17 monitors in 8 US cities.ResultsIn simulations, frequency band model performance rates predictions better (lower RMSE, higher correlation) when there is no error at a particular timescale (e.g., acute) and worse when error is added to that timescale, compared to overall approaches. Further, frequency band model performance is more strongly associated (R2 = 0.95) with health association bias compared to overall approaches (R2 = 0.57). For PM2.5 predictions in Salt Lake City, UT, frequency band model performance better identifies acute error that may impact estimated short-term health associations.ConclusionsFor epidemiologic studies, frequency band model performance provides an improvement over existing approaches because it evaluates models at the timescale of interest and is more strongly associated with bias in estimated health associations. Evaluating prediction models at timescales relevant for health studies is critical to determining whether model error will impact estimated health associations.

Project description:Air pollution is a matter of concern among the public, especially for those living in urban and industrial areas. Markov chain modeling is often used to model the underlying dynamics of air pollution, which involves describing the transition probability of going from one air pollution state to another. Thus, estimating the transition probability matrix for the data of the air pollution index (API) is an essential process in the modeling. However, one may observe many zero probabilities in the transition probability matrix, especially when faced with a small sample, interpreting the results with respect to the climate condition less realistic. This study proposes a robust empirical Bayes method, which incorporates a method of smoothing the zero frequencies in the count matrix, contributing to an improved estimation of the transition probability matrix. The robustness of the empirical Bayesian estimation is investigated based on Bayes risk. The transition probability matrices estimated based on the robust empirical Bayes method for the hourly API data collected from seven monitoring stations in Malaysia for the period 2012 to 2014 are used for determining the air pollution characteristics such as the mean residence time, the steady-state probability and the mean recurrence time. Furthermore, the proposed method has been evaluated by Monte Carlo simulations. Results suggest that it is quite effective in producing non-zero transition probability estimates, and superior to the maximum likelihood method in terms of minimizing the mean squared error for individual and entire transition probabilities. Therefore, the robust empirical Bayes method proves to be an improved approach to the estimation of the Markov chain. When applied to API data, it could provide important information on air pollution dynamics that may help guiding the development of proper strategies for managing the impact of air quality.Supplementary informationThe online version contains supplementary material available at 10.1007/s40201-020-00607-4.

Project description:Recent cohort studies have relied on exposure prediction models to estimate individuallevel air pollution concentrations because individual air pollution measurements are not available for cohort locations. For such prediction models, geographic variables related to pollution sources are important inputs. We demonstrated the computation process of geographic variables mostly recorded in 2010 at regulatory air pollution monitoring sites in South Korea. On the basis of previous studies, we finalized a list of 313 geographic variables related to air pollution sources in eight categories including traffic, demographic characteristics, land use, transportation facilities, physical geography, emissions, vegetation, and altitude. We then obtained data from different sources such as the Statistics Geographic Information Service and Korean Transport Database. After integrating all available data to a single database by matching coordinate systems and converting non-spatial data to spatial data, we computed geographic variables at 294 regulatory monitoring sites in South Korea. The data integration and variable computation were performed by using ArcGIS version 10.2 (ESRI Inc., Redlands, CA, USA). For traffic, we computed the distances to the nearest roads and the sums of road lengths within different sizes of circular buffers. In addition, we calculated the numbers of residents, households, housing buildings, companies, and employees within the buffers. The percentages of areas for different types of land use compared to total areas were calculated within the buffers. For transportation facilities and physical geography, we computed the distances to the closest public transportation depots and the boundary lines. The vegetation index and altitude were estimated at a given location by using satellite data. The summary statistics of geographic variables in Seoul across monitoring sites showed different patterns between urban background and urban roadside sites. This study provided practical knowledge on the computation process of geographic variables in South Korea, which will improve air pollution prediction models and contribute to subsequent health analyses.

Dataset Information

Multivariate Air Pollution Prediction Modeling with partial Missingness.

Publications

Multivariate Air Pollution Prediction Modeling with partial Missingness.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets