Performance comparison of LUR and OK in PM2.5 concentration mapping: a multidimensional perspective

Zou, Bin; Luo, Yanqing; Wan, Neng; Zheng, Zhong; Sternberg, Troy; Liao, Yilan

doi:10.1038/srep08698

Cited by 71 publications

(50 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, the accuracy of the PM 2.5 concentrations was computed using the self-adaptive LUR model and was higher than the typical LUR model. In addition, the accuracy of the typical LUR model evaluated using LOO cross validation (result before Kriging interpolation) was less than the final map accuracy, which verified that Kriging improves the accuracy of the LUR model [50].…”

Section: Comparison With the Typical Lur Methodsmentioning

confidence: 85%

See 1 more Smart Citation

Self-Adaptive Revised Land Use Regression Models for Estimating PM2.5 Concentrations in Beijing, China

Ji-ping

Zongyi

2016

Sustainability

View full text Add to dashboard Cite

Heavy air pollution, especially fine particulate matter (PM 2.5 ), poses serious challenges to environmental sustainability in Beijing. Epidemiological studies and the identification of measures for preventing serious air pollution both require accurate PM 2.5 spatial distribution data. Land use regression (LUR) models are promising for estimating the spatial distribution of PM 2.5 at a high spatial resolution. However, typical LUR models have a limited sampling point explanation rate (SPER, i.e., the rate of the sampling points with reasonable predicted concentrations to the total number of sampling points) and accuracy. Hence, self-adaptive revised LUR models are proposed in this paper for improving the SPER and accuracy of typical LUR models. The self-adaptive revised LUR model combines a typical LUR model with self-adaptive LUR model groups. The typical LUR model was used to estimate the PM 2.5 concentrations, and the self-adaptive LUR model groups were constructed for all of the sampling points removed from the typical LUR model because they were beyond the prediction data range, which was from 60% of the minimum observation to 120% of the maximum observation. The final results were analyzed using three methods, including an accuracy analysis, and were compared with typical LUR model results and the spatial variations in Beijing. The accuracy satisfied the demands of the analysis, and the accuracies at the different monitoring sites indicated spatial variations in the accuracy of the self-adaptive revised LUR model. The accuracy was high in the central area and low in suburban areas. The comparison analysis showed that the self-adaptive LUR model increased the SPER from 75% to 90% and increased the accuracy (based on the root-mean-square error) from 20.643 µg/m 3 to 17.443 µg/m 3 for the PM 2.5 concentrations during the winter of 2014 in Beijing. The spatial variation analysis for Beijing showed that the PM 2.5 concentrations were low in the north, especially in the northwest region, and high in the southern and central portions of Beijing. This spatial variation was consistent with the fact that the northern region is mountainous and has fewer people and less traffic, which results in lower air pollution, than in the central region, which has a high population density and heavy traffic. Moreover, the southern region is adjacent to Hebei province, which contains many polluting enterprises; thus, this area exhibits higher air pollution levels than Beijing. Therefore, the self-adaptive revised LUR model is effective and reliable.

show abstract

Section: Comparison With the Typical Lur Methodsmentioning

confidence: 85%

“…Finally, the choice of the spatial interpolation method is critical. Most studies have found that the final pollutant concentration distribution map is more accurate when combined with the Kriging interpolation method [50].…”

Section: Self-adaptive Revised Lur Modelmentioning

confidence: 99%

Self-Adaptive Revised Land Use Regression Models for Estimating PM2.5 Concentrations in Beijing, China

Ji-ping

Zongyi

2016

Sustainability

View full text Add to dashboard Cite

show abstract

“…In this process, the meteorological parameters with ground-based measurements were spatially interpolated to the fine grid of 10 km, which corresponds to the grid resolution of AOD datasets. For predictors with spatial scaling effects (e.g., land use/cover), the characteristic values were extracted at a 500-5000 m buffering radius based on previous findings [35,36]. Finally, PM 2.5 , fused AOD, meteorological parameters, pollution sources, road network, land use/cover, terrain, and population for all PM 2.5 monitoring sites were matched by PM 2.5 monitoring site IDs for model development.…”

Section: Data Integrationmentioning

confidence: 99%

Satellite Based Mapping of Ground PM2.5 Concentration Using Generalized Additive Modeling

et al. 2016

Self Cite

View full text Add to dashboard Cite

Satellite-based PM 2.5 concentration estimation is growing as a popular solution to map the PM 2.5 spatial distribution due to the insufficiency of ground-based monitoring stations. However, those applications usually suffer from the simple hypothesis that the influencing factors are linearly correlated with PM 2.5 concentrations, though non-linear mechanisms indeed exist in their interactions. Taking the Beijing-Tianjin-Hebei (BTH) region in China as a case, this study developed a generalized additive modeling (GAM) method for satellite-based PM 2.5 concentration mapping. In this process, the linear and non-linear relationships between PM 2.5 variation and associated contributing factors, such as the aerosol optical depth (AOD), industrial sources, land use type, road network, and meteorological variables, were comprehensively considered. The reliability of the GAM models was validated by comparison with typical linear land use regression (LUR) models. Results show that GAM modeling outperforms LUR modeling at both the annual and seasonal scale, with obvious higher model fitting-based adjusted R 2 and lower RMSEs. This is confirmed by the cross-validation-based adjusted R 2 with values of GAM-based spring, summer, autumn, winter, and annual models, which are 0.92, 0.78, 0.87, 0.85, and 0.90, respectively, while those of LUR models are 0.87, 0.71, 0.84, 0.84, and 0.85, respectively. Different to the LUR-based hypothesis of the "straight line" relations, the "smoothed curves" from GAM-based apportionment analysis reveals that factors contributing to PM 2.5 variation are unstable with the alternate linear and non-linear relations. The GAM model-based PM 2.5 concentration surfaces clearly demonstrate their superiority in disclosing the heterogeneous PM 2.5 concentrations to the discrete observations. It can be concluded that satellite-based PM 2.5 concentration mapping could be greatly improved by GAM modeling given its simultaneous considerations of the linear and non-linear influencing mechanisms of PM 2.5 .

show abstract

“…In one method, the particle concentrations of the stations are obtained based on the constructed model, and the simulation of the spatial distribution of the PM 2.5 concentration is achieved through spatial interpolation [18,19]. In the other method, the raster data of variables are incorporated into the model for regression analysis mapping to obtain the spatial distribution of the PM 2.5 concentration [20].…”

Section: Introductionmentioning

confidence: 99%

Optimization of PM2.5 Estimation Using Landscape Pattern Information and Land Use Regression Model in Zhejiang, China

Yang

Chen

et al. 2018

Atmosphere

View full text Add to dashboard Cite

Abstract:The motivation of this paper is that the effect of landscape pattern information on the accuracy of particulate matter estimation is seldom reported. The landscape pattern indexes were incorporated in a land use regression (LUR) model to investigate the performance of PM 2.5 simulation over Zhejiang Province. The study results show that the prediction accuracy of the model has been improved significantly after the incorporation of the landscape pattern indexes. At class-level, waters and residential areas were clearly landscape components influencing decreasing or increasing PM 2.5 concentration. At landscape-level, CONTAG (contagion index) played a huge negative role in pollutant concentrations. Latitude and relative humidity are key factors affecting the PM 2.5 concentration at province level. If the land use regression model incorporating landscape pattern indexes was used to simulate distribution of PM 2.5 , the accuracy of ordinary kriging for the LUR-based data mining was higher than the accuracy of LUR-based ordinary kriging, especially in the area of low pollution concentration.

show abstract

Performance comparison of LUR and OK in PM2.5 concentration mapping: a multidimensional perspective

Cited by 71 publications

References 41 publications

Self-Adaptive Revised Land Use Regression Models for Estimating PM2.5 Concentrations in Beijing, China

Self-Adaptive Revised Land Use Regression Models for Estimating PM2.5 Concentrations in Beijing, China

Satellite Based Mapping of Ground PM2.5 Concentration Using Generalized Additive Modeling

Optimization of PM2.5 Estimation Using Landscape Pattern Information and Land Use Regression Model in Zhejiang, China

Contact Info

Product

Resources

About