Dataset Information

Constrained Mixed-Effect Models with Ensemble Learning for Prediction of Nitrogen Oxides Concentrations at High Spatiotemporal Resolution.

ABSTRACT: Spatiotemporal models to estimate ambient exposures at high spatiotemporal resolutions are crucial in large-scale air pollution epidemiological studies that follow participants over extended periods. Previous models typically rely on central-site monitoring data and/or covered short periods, limiting their applications to long-term cohort studies. Here we developed a spatiotemporal model that can reliably predict nitrogen oxide concentrations with a high spatiotemporal resolution over a long time span (>20 years). Leveraging the spatially extensive highly clustered exposure data from short-term measurement campaigns across 1-2 years and long-term central site monitoring in 1992-2013, we developed an integrated mixed-effect model with uncertainty estimates. Our statistical model incorporated nonlinear and spatial effects to reduce bias. Identified important predictors included temporal basis predictors, traffic indicators, population density, and subcounty-level mean pollutant concentrations. Substantial spatial autocorrelation (11-13%) was observed between neighboring communities. Ensemble learning and constrained optimization were used to enhance reliability of estimation over a large metropolitan area and a long period. The ensemble predictions of biweekly concentrations resulted in an R2 of 0.85 (RMSE: 4.7 ppb) for NO2 and 0.86 (RMSE: 13.4 ppb) for NOx. Ensemble learning and constrained optimization generated stable time series, which notably improved the results compared with those from initial mixed-effects models.

SUBMITTER: Li L

PROVIDER: S-EPMC5609852 | biostudies-literature | 2017 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Constrained Mixed-Effect Models with Ensemble Learning for Prediction of Nitrogen Oxides Concentrations at High Spatiotemporal Resolution.

Li Lianfa L Lurmann Fred F Habre Rima R Urman Robert R Rappaport Edward E Ritz Beate B Chen Jiu-Chiuan JC Gilliland Frank D FD Wu Jun J

Environmental science & technology 20170811 17

Spatiotemporal models to estimate ambient exposures at high spatiotemporal resolutions are crucial in large-scale air pollution epidemiological studies that follow participants over extended periods. Previous models typically rely on central-site monitoring data and/or covered short periods, limiting their applications to long-term cohort studies. Here we developed a spatiotemporal model that can reliably predict nitrogen oxide concentrations with a high spatiotemporal resolution over a long tim ...[more]

PMID: 28727456

Similar Datasets

Project description:BACKGROUND:Accurate estimation of nitrogen dioxide (NO2) and nitrogen oxide (NOx) concentrations at high spatiotemporal resolutions is crucial for improving evaluation of their health effects, particularly with respect to short-term exposures and acute health outcomes. For estimation over large regions like California, high spatial density field campaign measurements can be combined with more sparse routine monitoring network measurements to capture spatiotemporal variability of NO2 and NOx concentrations. However, monitors in spatially dense field sampling are often highly clustered and their uneven distribution creates a challenge for such combined use. Furthermore, heterogeneities due to seasonal patterns of meteorology and source mixtures between sub-regions (e.g. southern vs. northern California) need to be addressed. OBJECTIVES:In this study, we aim to develop highly accurate and adaptive machine learning models to predict high-resolution NO2 and NOx concentrations over large geographic regions using measurements from different sources that contain samples with heterogeneous spatiotemporal distributions and clustering patterns. METHODS:We used a comprehensive Kruskal-K-means method to cluster the measurement samples from multiple heterogeneous sources. Spatiotemporal cluster-based bootstrap aggregating (bagging) of the base mixed-effects models was then applied, leveraging the clusters to obtain balanced and less correlated training samples for less bias and improvement in generalization. Further, we used the machine learning technique of grid search to find the optimal interaction of temporal basis functions and the scale of spatial effects, which, together with spatiotemporal covariates, adequately captured spatiotemporal variability in NO2 and NOx at the state and local levels. RESULTS:We found an optimal combination of four temporal basis functions and 200?m scale spatial effects for the base mixed-effects models. With the cluster-based bagging of the base models, we obtained robust predictions with an ensemble cross validation R2 of 0.88 for both NO2 and NOx [RMSE (RMSEIQR): 3.62?ppb (0.28) and 9.63?ppb (0.37) respectively]. In independent tests of random sampling, our models achieved similarly strong performance (R2 of 0.87-0.90; RMSE of 3.97-9.69?ppb; RMSEIQR of 0.21-0.27), illustrating minimal over-fitting. CONCLUSIONS:Our approach has important implications for fusing data from highly clustered and heterogeneous measurement samples from multiple data sources to produce highly accurate concentration estimates of air pollutants such as NO2 and NOx at high resolution over a large region.

Project description:Drought is a natural hazard, which is a result of a prolonged shortage of precipitation, high temperature and change in the weather pattern. Drought harms society, the economy and the natural environment, but it is difficult to identify and characterize. Many areas of Pakistan have suffered severe droughts during the last three decades due to changes in the weather pattern. A drought analysis with the incorporation of climate information has not yet been undertaken in this study region. Here, we propose an ensemble approach for monthly drought prediction and to define and examine wet/dry events. Initially, the drought events were identified by the short term Standardized Precipitation Index (SPI-3). Drought is predicted based on three ensemble models i.e., Equal Ensemble Drought Prediction (EEDP), Weighted Ensemble Drought Prediction (WEDP) and the Conditional Ensemble Drought Prediction (CEDP) model. Besides, two weighting procedures are used for distributing weights in the WEDP model, such as Traditional Weighting (TW) and the Weighted Bootstrap Resampling (WBR) procedure. Four copula families (i.e., Frank, Clayton, Gumbel and Joe) are used to explain the dependency relation between climate indices and precipitation in the CEDP model. Among all four copula families, the Joe copula has been found suitable for most of the times. The CEDP model provides better results in terms of accuracy and uncertainty as compared to other ensemble models for all meteorological stations. The performance of the CEDP model indicates that the climate indices are correlated with a weather pattern of four meteorological stations. Moreover, the percentage occurrence of extreme drought events that have appeared in the Multan, Bahawalpur, Barkhan and Khanpur are 1.44%, 0.57%, 2.59% and 1.71%, respectively, whereas the percentage occurrence of extremely wet events are 2.3%, 1.72%, 0.86% and 2.86%, respectively. The understanding of drought pattern by including climate information can contribute to the knowledge of future agriculture and water resource management.

Project description:Various approaches have been proposed to model PM2.5 in the recent decade, with satellite-derived aerosol optical depth, land-use variables, chemical transport model predictions, and several meteorological variables as major predictor variables. Our study used an ensemble model that integrated multiple machine learning algorithms and predictor variables to estimate daily PM2.5 at a resolution of 1?km?×?1?km across the contiguous United States. We used a generalized additive model that accounted for geographic difference to combine PM2.5 estimates from neural network, random forest, and gradient boosting. The three machine learning algorithms were based on multiple predictor variables, including satellite data, meteorological variables, land-use variables, elevation, chemical transport model predictions, several reanalysis datasets, and others. The model training results from 2000 to 2015 indicated good model performance with a 10-fold cross-validated R2 of 0.86 for daily PM2.5 predictions. For annual PM2.5 estimates, the cross-validated R2 was 0.89. Our model demonstrated good performance up to 60??g/m3. Using trained PM2.5 model and predictor variables, we predicted daily PM2.5 from 2000 to 2015 at every 1?km?×?1?km grid cell in the contiguous United States. We also used localized land-use variables within 1?km?×?1?km grids to downscale PM2.5 predictions to 100?m?×?100?m grid cells. To characterize uncertainty, we used meteorological variables, land-use variables, and elevation to model the monthly standard deviation of the difference between daily monitored and predicted PM2.5 for every 1?km?×?1?km grid cell. This PM2.5 prediction dataset, including the downscaled and uncertainty predictions, allows epidemiologists to accurately estimate the adverse health effect of PM2.5. Compared with model performance of individual base learners, an ensemble model would achieve a better overall estimation. It is worth exploring other ensemble model formats to synthesize estimations from different models or from different groups to improve overall performance.

Dataset Information

Constrained Mixed-Effect Models with Ensemble Learning for Prediction of Nitrogen Oxides Concentrations at High Spatiotemporal Resolution.

Publications

Constrained Mixed-Effect Models with Ensemble Learning for Prediction of Nitrogen Oxides Concentrations at High Spatiotemporal Resolution.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets