Cargando…
An Ensemble Spatiotemporal Model for Predicting PM(2.5) Concentrations
Although fine particulate matter with a diameter of <2.5 μm (PM(2.5)) has a greater negative impact on human health than particulate matter with a diameter of <10 μm (PM(10)), measurements of PM(2.5) have only recently been performed, and the spatial coverage of these measurements is limited....
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5451999/ https://www.ncbi.nlm.nih.gov/pubmed/28531151 http://dx.doi.org/10.3390/ijerph14050549 |
_version_ | 1783240302230765568 |
---|---|
author | Li, Lianfa Zhang, Jiehao Qiu, Wenyang Wang, Jinfeng Fang, Ying |
author_facet | Li, Lianfa Zhang, Jiehao Qiu, Wenyang Wang, Jinfeng Fang, Ying |
author_sort | Li, Lianfa |
collection | PubMed |
description | Although fine particulate matter with a diameter of <2.5 μm (PM(2.5)) has a greater negative impact on human health than particulate matter with a diameter of <10 μm (PM(10)), measurements of PM(2.5) have only recently been performed, and the spatial coverage of these measurements is limited. Comprehensively assessing PM(2.5) pollution levels and the cumulative health effects is difficult because PM(2.5) monitoring data for prior time periods and certain regions are not available. In this paper, we propose a promising approach for robustly predicting PM(2.5) concentrations. In our approach, a generalized additive model is first used to quantify the non-linear associations between predictors and PM(2.5), the bagging method is used to sample the dataset and train different models to reduce the bias in prediction, and the variogram for the daily residuals of the ensemble predictions is then simulated to improve our predictions. Shandong Province, China, is the study region, and data from 96 monitoring stations were included. To train and validate the models, we used PM(2.5) measurement data from 2014 with other predictors, including PM(10) data, meteorological parameters, remote sensing data, and land-use data. The validation results revealed that the R(2) value was improved and reached 0.89 when PM(10) was used as a predictor and a kriging interpolation was performed for the residuals. However, when PM(10) was not used as a predictor, our method still achieved a CV R(2) value of up to 0.86. The ensemble of spatial characteristics of relevant factors explained approximately 32% of the variance and improved the PM(2.5) predictions. The spatiotemporal modeling approach to estimating PM(2.5) concentrations presented in this paper has important implications for assessing PM(2.5) exposure and its cumulative health effects. |
format | Online Article Text |
id | pubmed-5451999 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-54519992017-06-05 An Ensemble Spatiotemporal Model for Predicting PM(2.5) Concentrations Li, Lianfa Zhang, Jiehao Qiu, Wenyang Wang, Jinfeng Fang, Ying Int J Environ Res Public Health Article Although fine particulate matter with a diameter of <2.5 μm (PM(2.5)) has a greater negative impact on human health than particulate matter with a diameter of <10 μm (PM(10)), measurements of PM(2.5) have only recently been performed, and the spatial coverage of these measurements is limited. Comprehensively assessing PM(2.5) pollution levels and the cumulative health effects is difficult because PM(2.5) monitoring data for prior time periods and certain regions are not available. In this paper, we propose a promising approach for robustly predicting PM(2.5) concentrations. In our approach, a generalized additive model is first used to quantify the non-linear associations between predictors and PM(2.5), the bagging method is used to sample the dataset and train different models to reduce the bias in prediction, and the variogram for the daily residuals of the ensemble predictions is then simulated to improve our predictions. Shandong Province, China, is the study region, and data from 96 monitoring stations were included. To train and validate the models, we used PM(2.5) measurement data from 2014 with other predictors, including PM(10) data, meteorological parameters, remote sensing data, and land-use data. The validation results revealed that the R(2) value was improved and reached 0.89 when PM(10) was used as a predictor and a kriging interpolation was performed for the residuals. However, when PM(10) was not used as a predictor, our method still achieved a CV R(2) value of up to 0.86. The ensemble of spatial characteristics of relevant factors explained approximately 32% of the variance and improved the PM(2.5) predictions. The spatiotemporal modeling approach to estimating PM(2.5) concentrations presented in this paper has important implications for assessing PM(2.5) exposure and its cumulative health effects. MDPI 2017-05-22 2017-05 /pmc/articles/PMC5451999/ /pubmed/28531151 http://dx.doi.org/10.3390/ijerph14050549 Text en © 2017 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Li, Lianfa Zhang, Jiehao Qiu, Wenyang Wang, Jinfeng Fang, Ying An Ensemble Spatiotemporal Model for Predicting PM(2.5) Concentrations |
title | An Ensemble Spatiotemporal Model for Predicting PM(2.5) Concentrations |
title_full | An Ensemble Spatiotemporal Model for Predicting PM(2.5) Concentrations |
title_fullStr | An Ensemble Spatiotemporal Model for Predicting PM(2.5) Concentrations |
title_full_unstemmed | An Ensemble Spatiotemporal Model for Predicting PM(2.5) Concentrations |
title_short | An Ensemble Spatiotemporal Model for Predicting PM(2.5) Concentrations |
title_sort | ensemble spatiotemporal model for predicting pm(2.5) concentrations |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5451999/ https://www.ncbi.nlm.nih.gov/pubmed/28531151 http://dx.doi.org/10.3390/ijerph14050549 |
work_keys_str_mv | AT lilianfa anensemblespatiotemporalmodelforpredictingpm25concentrations AT zhangjiehao anensemblespatiotemporalmodelforpredictingpm25concentrations AT qiuwenyang anensemblespatiotemporalmodelforpredictingpm25concentrations AT wangjinfeng anensemblespatiotemporalmodelforpredictingpm25concentrations AT fangying anensemblespatiotemporalmodelforpredictingpm25concentrations AT lilianfa ensemblespatiotemporalmodelforpredictingpm25concentrations AT zhangjiehao ensemblespatiotemporalmodelforpredictingpm25concentrations AT qiuwenyang ensemblespatiotemporalmodelforpredictingpm25concentrations AT wangjinfeng ensemblespatiotemporalmodelforpredictingpm25concentrations AT fangying ensemblespatiotemporalmodelforpredictingpm25concentrations |