2018
DOI: 10.1021/acs.est.7b05669
|View full text |Cite
|
Sign up to set email alerts
|

Satellite-Based Estimates of Daily NO2 Exposure in China Using Hybrid Random Forest and Spatiotemporal Kriging Model

Abstract: A novel model named random-forest-spatiotemporal-kriging (RF-STK) was developed to estimate the daily ambient NO concentrations across China during 2013-2016 based on the satellite retrievals and geographic covariates. The RF-STK model showed good prediction performance, with cross-validation R = 0.62 (RMSE = 13.3 μg/m) for daily and R = 0.73 (RMSE = 6.5 μg/m) for spatial predictions. The nationwide population-weighted multiyear average of NO was predicted to be 30.9 ± 11.7 μg/m (mean ± standard deviation), wi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

3
104
2

Year Published

2019
2019
2022
2022

Publication Types

Select...
3
2
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 200 publications
(109 citation statements)
references
References 44 publications
3
104
2
Order By: Relevance
“…The NO x emission decreased rapidly after upgrading oil product quality standards and import denitrification facilities and the implementing low-NO 2 burner technologies . However, the NO − 3 concentration in the precipitation over China only displayed a slight decrease during this period, which was in good agreement with the slight decrease in national NO 2 concentration in the atmosphere (Zhan et al, 2018). It suggested that stricter controls on NO x emissions from power plants might be counteracted by the increase in power plants and energy consumption (F. Wang et al, 2018).…”
Section: Inter-annual Variation In the Water-soluble Ionssupporting
confidence: 62%
“…The NO x emission decreased rapidly after upgrading oil product quality standards and import denitrification facilities and the implementing low-NO 2 burner technologies . However, the NO − 3 concentration in the precipitation over China only displayed a slight decrease during this period, which was in good agreement with the slight decrease in national NO 2 concentration in the atmosphere (Zhan et al, 2018). It suggested that stricter controls on NO x emissions from power plants might be counteracted by the increase in power plants and energy consumption (F. Wang et al, 2018).…”
Section: Inter-annual Variation In the Water-soluble Ionssupporting
confidence: 62%
“…We used a random forest (RF) model. RF models have successfully been used in previous studies aiming to predict NO2 concentrations using land use (Araki et al, 2018;Chen et al, 2019;Hu et al, 2017;Zhan et al, 2018). This approach was chosen to minimise the risk of overfitting given that there are relatively few monitoring sites and also to capture non-linear relationships observed between air pollutant concentrations and predictor variables (Araki et al, 2018;Chen et al, 2019;Vizcaino and Lavalle, 2018).…”
Section: Model Building and Validationmentioning
confidence: 99%
“…Machine learning models are applied to predict the spatiotemporal distributions of atmospheric pollutants, such as fine particulate matter (PM2.5) and nitrogen dioxide (NO2), based on the associated satellite retrievals and 20 ground measurements (Zhan et al, 2018;Reid et al, 2015). Complex structures are built to capture nonlinear and high-order interactions between the response and predictor variables.…”
mentioning
confidence: 99%
“…In the comparisons of models predicting PM2.5 concentrations, random forests and gradient boosting machine, which incorporate the satellite-retrieved aerosol optical depth (AOD), presented conspicuously good prediction performance (Reid et al, 25 2015). In addition, the random forest and spatiotemporal kriging (RF-STK) model is proposed to predict the ground-level nitrogen dioxide (NO2) concentrations across China based on the satellite-retrieved NO2 density (Zhan et al, 2018). To the authors' knowledge, machine learning models have never been employed to estimate nationwide ground-level CO concentrations in China based on the satellite retrievals.…”
mentioning
confidence: 99%
See 1 more Smart Citation