Estimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale

Estimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale

Directly establishing the relationship between satellite data and PM<sub>2.5</sub> concentration through deep learning methods for PM<sub>2.5</sub> concentration estimation is an important means for estimating regional PM<sub>2.5</sub> concentration. However, due...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Xingdi Chen, Peng Kong, Peng Jiang, Yanlan Wu
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
PM<sub>2.5</sub>
MODIS
deep Bayesian model
multiscale
Science
Q
Acceso en línea:https://doaj.org/article/897952685233496aaaf89e6fa4e8cde3
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:897952685233496aaaf89e6fa4e8cde3
record_format dspace
spelling oai:doaj.org-article:897952685233496aaaf89e6fa4e8cde32021-11-25T18:54:09ZEstimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale10.3390/rs132245452072-4292https://doaj.org/article/897952685233496aaaf89e6fa4e8cde32021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4545https://doaj.org/toc/2072-4292Directly establishing the relationship between satellite data and PM<sub>2.5</sub> concentration through deep learning methods for PM<sub>2.5</sub> concentration estimation is an important means for estimating regional PM<sub>2.5</sub> concentration. However, due to the lack of consideration of uncertainty in deep learning methods, methods based on deep learning have certain overfitting problems in the process of PM<sub>2.5</sub> estimation. In response to this problem, this paper designs a deep Bayesian PM<sub>2.5</sub> estimation model that takes into account multiple scales. The model uses a Bayesian neural network to describe key parameters a priori, provide regularization effects to the neural network, perform posterior inference through parameters, and take into account the characteristics of data uncertainty, which is used to alleviate the problem of model overfitting and to improve the generalization ability of the model. In addition, different-scale Moderate-Resolution Imaging Spectroradiometer (MODIS) satellite data and ERA5 reanalysis data were used as input to the model to strengthen the model’s perception of different-scale features of the atmosphere, as well as to further enhance the model’s PM<sub>2.5</sub> estimation accuracy and generalization ability. Experiments with Anhui Province as the research area showed that the <i>R</i><sup>2</sup> of this method on the independent test set was 0.78, which was higher than that of the DNN, random forest, and BNN models that do not consider the impact of the surrounding environment; moreover, the RMSE was 19.45 μg·m<sup>−3</sup>, which was also lower than the three compared models. In the experiment of different seasons in 2019, compared with the other three models, the estimation accuracy was significantly reduced; however, the <i>R</i><sup>2</sup> of the model in this paper could still reach 0.66 or more. Thus, the model in this paper has a higher accuracy and better generalization ability.Xingdi ChenPeng KongPeng JiangYanlan WuMDPI AGarticlePM<sub>2.5</sub>MODISdeep Bayesian modelmultiscaleScienceQENRemote Sensing, Vol 13, Iss 4545, p 4545 (2021)
institution DOAJ
collection DOAJ
language EN
topic PM<sub>2.5</sub>
MODIS
deep Bayesian model
multiscale
Science
Q
spellingShingle PM<sub>2.5</sub>
MODIS
deep Bayesian model
multiscale
Science
Q
Xingdi Chen
Peng Kong
Peng Jiang
Yanlan Wu
Estimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale
description Directly establishing the relationship between satellite data and PM<sub>2.5</sub> concentration through deep learning methods for PM<sub>2.5</sub> concentration estimation is an important means for estimating regional PM<sub>2.5</sub> concentration. However, due to the lack of consideration of uncertainty in deep learning methods, methods based on deep learning have certain overfitting problems in the process of PM<sub>2.5</sub> estimation. In response to this problem, this paper designs a deep Bayesian PM<sub>2.5</sub> estimation model that takes into account multiple scales. The model uses a Bayesian neural network to describe key parameters a priori, provide regularization effects to the neural network, perform posterior inference through parameters, and take into account the characteristics of data uncertainty, which is used to alleviate the problem of model overfitting and to improve the generalization ability of the model. In addition, different-scale Moderate-Resolution Imaging Spectroradiometer (MODIS) satellite data and ERA5 reanalysis data were used as input to the model to strengthen the model’s perception of different-scale features of the atmosphere, as well as to further enhance the model’s PM<sub>2.5</sub> estimation accuracy and generalization ability. Experiments with Anhui Province as the research area showed that the <i>R</i><sup>2</sup> of this method on the independent test set was 0.78, which was higher than that of the DNN, random forest, and BNN models that do not consider the impact of the surrounding environment; moreover, the RMSE was 19.45 μg·m<sup>−3</sup>, which was also lower than the three compared models. In the experiment of different seasons in 2019, compared with the other three models, the estimation accuracy was significantly reduced; however, the <i>R</i><sup>2</sup> of the model in this paper could still reach 0.66 or more. Thus, the model in this paper has a higher accuracy and better generalization ability.
format article
author Xingdi Chen
Peng Kong
Peng Jiang
Yanlan Wu
author_facet Xingdi Chen
Peng Kong
Peng Jiang
Yanlan Wu
author_sort Xingdi Chen
title Estimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale
title_short Estimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale
title_full Estimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale
title_fullStr Estimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale
title_full_unstemmed Estimation of PM<sub>2.5</sub> Concentration Using Deep Bayesian Model Considering Spatial Multiscale
title_sort estimation of pm<sub>2.5</sub> concentration using deep bayesian model considering spatial multiscale
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/897952685233496aaaf89e6fa4e8cde3
work_keys_str_mv AT xingdichen estimationofpmsub25subconcentrationusingdeepbayesianmodelconsideringspatialmultiscale
AT pengkong estimationofpmsub25subconcentrationusingdeepbayesianmodelconsideringspatialmultiscale
AT pengjiang estimationofpmsub25subconcentrationusingdeepbayesianmodelconsideringspatialmultiscale
AT yanlanwu estimationofpmsub25subconcentrationusingdeepbayesianmodelconsideringspatialmultiscale
_version_ 1718410600753659904

Ejemplares similares