Geographically Weighted Principal Components Analysis to assess diffuse pollution sources of soil heavy metal: Application to rough mountain areas in Northwest Spain

Fernández, Susana; Cotos-Yáñez, Tomás R.; Roca‐Pardiñas, Javier; Ordóñez, Celestino

doi:10.1016/j.geoderma.2016.10.012

Cited by 77 publications

(32 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different from the traditional PCA‐GWR, the GWPCA‐GWR model used GWPCA to extract the local information of auxiliary variables. Previous studies suggested that GWPCA is more effective than PCA in geographic data processing (Fernández, Cotos‐Yáñez, Roca‐Pardiñas, & Ordóñez, 2018 ; Granger et al., 2017 ; Kumar, Lal, & Lloyd, 2012b). In this study, in the northeast of Shayang County (close to Han River), soil pH and CEC had higher loadings, while in the west of Shayang County (the paddy field area), AFe had higher loadings (Figure 5).…”

Section: Resultsmentioning

confidence: 99%

Improving the spatial prediction accuracy of soil alkaline hydrolyzable nitrogen using GWPCA‐GWRK

Jian

Zhang

et al. 2021

Soil Science Soc of Amer J

View full text Add to dashboard Cite

Principal component analysis-multiple linear regression (PCA-MLR) is usually used to weaken the multi-collinearity effects among auxiliary variables in a regression prediction. However, both PCA and MLR in this model are only built on variable space rather than geographical space. When used in the spatial prediction of soil properties, PCA-MLR usually cannot effectively capture the spatially non-stationary structures among auxiliary variables and spatially non-stationary relationships between the target variable and principal component scores. Moreover, PCA-MLR may ignore the potentially valuable regression residual. To address these limitations, this study first proposed geographically weighted principal component analysis-geographically weighted regression kriging (GWPCA-GWRK) for the spatial prediction of soil alkaline hydrolyzable nitrogen (AN) in Shayang County, China. Then, the spatial prediction accuracy of GWPCA-GWRK was compared with those of the following five models: ordinary kriging (OK), co-kriging (CoK), PCA-MLR, PCAgraphically weighted regression (PCA-GWR), and GWPCA-GWR. Results showed that (i) eight variables were determined as auxiliary data by a geodetector; (ii) the spatially non-stationary relationships among the eight auxiliary variables were revealed by the results of the local correlation analysis, Monte Carlo test, and GWPCA; (iii) GWPCA-GWRK provided the lowest prediction error (RMSE = 18.80 mg kg −1 , MAE = 12.79 mg kg −1 ) and highest Lin's concordance correlation coefficient (LCCC; 0.75); (iv) relative improvement accuracies over the traditionallyused OK were 19.74% for GWPCA-GWRK, 16.42% for GWPCA-GWR,

show abstract

Section: Resultsmentioning

confidence: 99%

Improving the spatial prediction accuracy of soil alkaline hydrolyzable nitrogen using GWPCA‐GWRK

Jian

Zhang

et al. 2021

Soil Science Soc of Amer J

View full text Add to dashboard Cite

show abstract

“…The results of this study show that the heavy metals Cr and Cd in the soil of Chongqing city center mainly come from the air environment, and the hot spot value of Cr is distributed in the areas with high air quality comprehensive index, on the contrary, the hot spot value of Cd is mainly distributed in the areas with medium air quality comprehensive index. Previous studies have shown that in the mountainous region of Asturias in the northwest of Spain, the sources of Cr and Cd in the soil are mainly from local air pollution-related factors, such as heavy metals released by vegetation combustion (Fernández and Cotos-Yáñez et al, 2018). Xiaojia Chen(2019) collected road dust samples from Beihai and Shanghai in order to explore the differences of heavy metal characteristics in air quality of different environments, and found that Cd is a traffics-derived metal, and Cr may be affected by natural sources.…”

Section: Population Density and Air Qualitymentioning

confidence: 99%

Analysis and Source Identification of Heavy Metals in Soils of Central Urban Area of Chongqing, China

Chen

Zhu

Cai

et al. 2021

Preprint

View full text Add to dashboard Cite

In megacities, due to frequent human activities, large amounts of metals enter the soil indirectly or directly and eventually flow to people through the food chain. Therefore, the analysis and identification of soil heavy metal sources is an important part of revealing soil heavy metal pollution. The spatial content and potential sources of 11 heavy metals were analyzed from 342 surface soil samples collected from the central city of Chongqing in southwest China. The results showed that the main heavy metal elements under the first principal component loading were copper (Cu), nickel(Ni), zinc (Zn), manganese (Mn), cadmium (Cr),plumbum (Pb) and cadmium(Cd).The second principal component (F2) was mainly loaded with molybdenum (Mo), arsenic (As), mercury (Hg)and antimony (Sb), and the PCA-APCs receptor model of 11 heavy metals was constructed. The PCA-APCs receptor models of 11 heavy metals were constructed. The results of classification regression analysis confirmed the main sources of heavy metals. Population density mainly affected Cu (0.539), soil mainly affected Ni (0.411), Sb (0.493), Zn (0.472) and Mn (0.206), and water quality mainly affected As(0.453) and Mo (0.374). Air quality mainly affects Cd (0.332) and Cr (0.371), traffic activity mainly affects Hg (0.312), and slope mainly affects Pb (0.313). Hot spot analysis showed that heavy metals had a high degree of coincidence with environmental factors such as soil parent material, slope, soil type and traffic activities. The results of this study can be effectively used to make scientific decisions and strategies, and an effective strategy for prevention and control of soil heavy metal pollution should be formulated to protect the urban soil environmental quality.

show abstract

“…GWPCA is an extension of the classical PCA, while PCA analysis can provide information regarding the global internal structure; it fails to consider that the covariance structure of the data can change spatially. In essence, GWPCA performs a local PCA analysis by considering a neighbourhood around each spatial feature [18].…”

Section: Geographically Weighted Principal Components Analysismentioning

confidence: 99%

Geographically Weighted Principal Components Analysis Approach to Evaluate Electricity Consumption Behaviour

Tejedor-Flores

Vicente‐Galindo

Galindo‐Villardón

2020

WIT Transactions on Ecology and the Environment

View full text Add to dashboard Cite

Electricity consumer behaviour is primarily based on individual decisions, which are often driven by external factors such as economic incentives, existing demographics, environmental variables, social norms, and infrastructure. This study aims to understand the amount of electricity used per hour dedicated in the household (HH) sectors and the paid sectors-including agriculture (AG), other productive sectors (PS) and the service and government sector (SG)-using Geographically Weighted Principal Components Analysis (GWPCA). In the literature, we found that a standard Principal Components Analysis (PCA) can be replaced with a GWPCA when we want to account for a certain spatial heterogeneity. To use the GWPCA to compare the results with a standard PCA, we took the data used in a previous investigation and applied both analyses in order to find a better way to understand the electricity consumer behaviour, using a multivariate analysis. The standard PCA reveals that the first three components collectively account for 73.66% of the variation in the data. Using GWPCA, we found a clear geographical variation in the percentage of total variance data, with higher percentages (90%-95%) located in the southwest and a small part of the northeast of the case of study used. Also, the electrical Energy Throughput in Paid Work (ETPW), and the amount of energy used per hour dedicated to the Paid Work sector (EMRPW), appears to play an important part in defining the local structure in the southwest (coastal region) and in the northern part of the case of study used, respectively. The comparison results suggest that GWPCA provides better fitness than the standard PCA model by considering spatial heterogeneity.

show abstract

Geographically Weighted Principal Components Analysis to assess diffuse pollution sources of soil heavy metal: Application to rough mountain areas in Northwest Spain

Cited by 77 publications

References 50 publications

Improving the spatial prediction accuracy of soil alkaline hydrolyzable nitrogen using GWPCA‐GWRK

Improving the spatial prediction accuracy of soil alkaline hydrolyzable nitrogen using GWPCA‐GWRK

Analysis and Source Identification of Heavy Metals in Soils of Central Urban Area of Chongqing, China

Geographically Weighted Principal Components Analysis Approach to Evaluate Electricity Consumption Behaviour

Contact Info

Product

Resources

About