Comparison Study on the Estimation of the Spatial Distribution of Regional Soil Metal(loid)s Pollution Based on Kriging Interpolation and BP Neural Network

Soil pollution by metal(loid)s resulting from rapid economic development is a major concern. Accurately estimating the spatial distribution of soil metal(loid) pollution has great significance in preventing and controlling soil pollution. In this study, 126 topsoil samples were collected in Kunshan City and the geo-accumulation index was selected as a pollution index. We used Kriging interpolation and BP neural network methods to estimate the spatial distribution of arsenic (As) and cadmium (Cd) pollution in the study area. Additionally, we introduced a cross-validation method to measure the errors of the estimation results by the two interpolation methods and discussed the accuracy of the information contained in the estimation results. The conclusions are as follows: data distribution characteristics, spatial variability, and mean square errors (MSE) of the different methods showed large differences. Estimation results from BP neural network models have a higher accuracy, the MSE of As and Cd are 0.0661 and 0.1743, respectively. However, the interpolation results show significant skewed distribution, and spatial autocorrelation is strong. Using Kriging interpolation, the MSE of As and Cd are 0.0804 and 0.2983, respectively. The estimation results have poorer accuracy. Combining the two methods can improve the accuracy of the Kriging interpolation and more comprehensively represent the spatial distribution characteristics of metal(loid)s in regional soil. The study may provide a scientific basis and technical support for the regulation of soil metal(loid) pollution.

[1]  Yuanfang Huang,et al.  Temporal and spatial variability of soil organic matter in a county scale agricultural ecosystem , 2007 .

[2]  I. Thornton,et al.  Urban Geochemistry: A study of the influence of anthropogenic activity on the heavy metal content of soils in traditionally industrial and non-industrial areas of Britain , 1996 .

[3]  Linsheng Yang,et al.  Urinary Arsenic Metabolites of Subjects Exposed to Elevated Arsenic Present in Coal in Shaanxi Province, China , 2011, International journal of environmental research and public health.

[4]  Margaret A. Oliver,et al.  Geostatistics in Physical Geography. Part I: Theory , 1989 .

[5]  Yong-guan Zhu,et al.  Trace metal contamination in urban soils of China. , 2012, The Science of the total environment.

[6]  Sally Brown,et al.  Case studies and evidence-based approaches to addressing urban soil lead contamination , 2017 .

[7]  R. Webster,et al.  Kriging: a method of interpolation for geographical information systems , 1990, Int. J. Geogr. Inf. Sci..

[8]  Martinus J. Bergman,et al.  Estimating Nonpoint Source Pollution Loads With a GIS Screening Model , 1995 .

[9]  Yunfeng Xie,et al.  Spatial distribution of soil heavy metal pollution estimated by different interpolation methods: accuracy and uncertainty analysis. , 2011, Chemosphere.

[10]  Chuanhua Yu,et al.  Performance Evaluation of Public Non-Profit Hospitals Using a BP Artificial Neural Network: The Case of Hubei Province in China , 2013, International journal of environmental research and public health.

[11]  Dennis L. Corwin,et al.  Applications of GIS to the Modeling of NonPoint Source Pollutants in the Vadose Zone: A Conference Overview , 1996 .

[12]  Tianyou Chai,et al.  Source mapping and determining of soil contamination by heavy metals using statistical analysis, artificial neural network, and adaptive genetic algorithm , 2015 .

[13]  Shenglu Zhou,et al.  Fraction distribution and bioavailability of soil heavy metals in the Yangtze River Delta--a case study of Kunshan City in Jiangsu Province, China. , 2011, Journal of hazardous materials.

[14]  Xiang Wei.  Design and Selection of Construction, Parameters and Training Method of BP Network , 2001 .

[15]  B. Zheng,et al.  Health risks of children's cumulative and aggregative exposure to metals and metalloids in a typical urban environment in China. , 2016, Chemosphere.

[16]  R. Mclaren,et al.  Soil Factors Affecting Heavy Metal Solubility in Some New Zealand Soils , 2006 .

[17]  K. Juang,et al.  Comparison of three nonparametric kriging methods for delineating heavy-metal contaminated soils. , 2000 .

[18]  S. Singh,et al.  Geostatistical and multivariate analysis of soil heavy metal contamination near coal mining area, Northeastern India , 2014, Environmental Earth Sciences.

[19]  Guoqing Shen,et al.  Status and fuzzy comprehensive assessment of combined heavy metal and organo-chlorine pesticide pollution in the Taihu Lake region of China. , 2005, Journal of environmental management.

[20]  R Neutra,et al.  Statistical association between cancer incidence and major-cause mortality, and estimated residential exposure to air emissions from petroleum and chemical plants. , 1984, Environmental health perspectives.

[21]  Jian Zhao,et al.  Division-based rainfall-runoff simulations with BP neural networks and Xinanjiang model , 2009, Neurocomputing.

[22]  G. Muller.  INDEX OF GEOACCUMULATION IN SEDIMENTS OF THE RHINE RIVER , 1969 .

[23]  A. Moragues,et al.  The use of a geographical information system to assess the effect of traffic pollution , 1996 .

[24]  G. Metternicht,et al.  Testing the performance of spatial interpolation techniques for mapping soil properties , 2006 .

[25]  B. J. Carter,et al.  Factors influencing heavy metal distribution in six Oklahoma benchmark soils , 1997 .

[26]  Lu Yan.  Optimization and application research of BP neural network , 2001 .

[27]  Xuezheng Shi,et al.  Using robust kriging and sequential Gaussian simulation to delineate the copper- and lead-contaminated areas of a rapidly industrialized city in Yangtze River Delta, China , 2007 .

[28]  Jin Li,et al.  A review of comparative studies of spatial interpolation methods in environmental sciences: Performance and impact factors , 2011, Ecol. Informatics.

[29]  J. Gumbo,et al.  Assessment of Heavy Metals in Municipal Sewage Sludge: A Case Study of Limpopo Province, South Africa , 2014, International journal of environmental research and public health.

[30]  Xuezheng Shi,et al.  Priority selection rating of sampling density and interpolation method for detecting the spatial variability of soil organic carbon in China , 2015, Environmental Earth Sciences.

[31]  John H. Young,et al.  Geospatial Interpolation and Mapping of Tropospheric Ozone Pollution Using Geostatistics , 2014, International journal of environmental research and public health.

[32]  Shenglu Zhou,et al.  Modeling and mapping of critical loads for heavy metals in Kunshan soil. , 2016, The Science of the total environment.

[33]  Chi Peng,et al.  Risk assessment of Cd polluted paddy soils in the industrial and township areas in Hunan, Southern China. , 2016, Chemosphere.