基于多模型优选的区域土壤重金属含量空间预测方法研究

doi:10.19741/j.issn.1673-4831.2019.0326

摘要/Abstract

摘要： 土壤重金属含量空间预测研究对实现区域土壤资源的优化利用以及土壤环境的保护和污染防治具有重要意义。以江苏省常州市金坛区为例，基于源、汇和空间分异因子，利用BP神经网络（back-propagation network）建模方法，分别构建了源汇模型（BP-S）、空间分异模型（BP-K）和改进的多因素综合模型（BP-SK），模拟预测了区域土壤重金属Cd、Pb、Cr、Cu和Zn含量的空间分布，并对各模型预测精度进行对比分析。针对不同模型在不同区域和元素间预测精度的差异，优选出预测精度最高的模型组合，以此探求区域重金属含量空间分布最优预测结果。结果表明：（1）BP-SK模型对Cd、Cr、Cu和Zn含量预测精度均高于BP-S和BP-K模型，仅在对Pb含量的预测中BP-S、BP-K模型精度高于BP-SK模型，BP-SK模型比其他模型更能突出局部特征，包含的信息更丰富。（2）优选后最优模型预测精度较原单一模型均有不同程度的提高，对Cd、Pb、Cr、Cu和Zn含量的预测精度分别提高15.15%、20.71%、19.19%、1.75%和9.24%。（3）各模型对Cd、Pb、Cr、Cu和Zn含量的空间预测高值区均位于区域中部和东北部，低值区位于西部丘陵山区，BP-SK模型在人为影响剧烈的地区预测效果更好，而BP-K模型在自然因素影响较大的丘陵山地区的适用性更好。

关键词: 土壤重金属, 源-汇, 空间分异, BP神经网络, 空间预测

Abstract: Spatial prediction of soil heavy metals is of great significance for utilization of regional soil resources, environment protection and pollution prevention. Jintan District in Changzhou City, Jiangsu Province was chosen as study area. Spatial variation model (BP-K), source-sink model (BP-S) and comprehensive model (BP-SK) were applied to simulate and predict the spatial distribution of heavy metals, including Cd, Pb, Cr, Cu and Zn. The results of the Models' performance were evaluated by coefficient of determination, root-mean-square deviation, mean absolute error and so on. Furthermore, the prediction results from the best performance model were selected to calculate heavy metal spatial distribution in each sub-region. The results show that:(1) The coefficient of determination of BP-SK model was higher than that of BP-S and BP-K for Cd, Cr, Cu and Zn. Only for Pb, the coefficients of determination of BP-S and BP-K were higher than that of the BP-SK model. BP-SK can strengthen local characteristics and uncover more information. (2) The comprehensive model performed better than original single model. The root-mean-square deviation of Cd, Pb, Cr, Cu and Zn were improved by 15.15%, 20.71%, 19.19%, 1.75% and 9.24%, respectively. (3) In prediction results, the high-value areas for Cd, Pb, Cr, Cu, and Zn were located in the central and northeastern parts, and the low-value areas were located in west hilly and mountainous areas. The BP-SK model has a better performance in areas with severe human influence, while the BP-K model has better applicability in hilly area where natural factors have a greater impact.

Key words: soil heavy metal, source-sink, spatial differentiation, back-propagation network, spatial prediction

中图分类号:

黄赵麟, 丁懿, 王君櫹, 贾振毅, 曾菁菁, 周生路. 基于多模型优选的区域土壤重金属含量空间预测方法研究[J]. 生态与农村环境学报, 2020, 36(3): 308-317.

HUANG Zhao-lin, DING Yi, WANG Jun-xiao, JIA Zhen-yi, ZENG Jing-jing, ZHOU Sheng-lu. Spatial Prediction Method of Regional Soil Heavy Metals Content Based on Multiple Model Optimization[J]. Journal of Ecology and Rural Environment, 2020, 36(3): 308-317.

参考文献 35

[1]	王国庆,林玉锁.土壤环境标准值及制订研究:服务于管理需求的土壤环境标准值框架体系[J].生态与农村环境学报,2014,30(5):552-562.[WANG Guo-qing,LIN Yu-suo.Soil Environmental Standard Values(SESV) and Their Development:A Proposed SESV Framework Serving the Needs of Soil Environmental Management[J].Journal of Ecology and Rural Environment,2014,30(5):552-562.]
[2]	李姗姗,曹广超,石平超,等.青岛城区土壤重金属元素空间分布及其现状评价[J].生态与农村环境学报,2015,31(1):112-117.[LI Shan-shan,CAO Guang-chao,SHI Ping-chao,et al.Status Quo and Evaluation of the Spatial Distribution of Heavy Metals in Urban Soil of Qingdao City[J].Journal of Ecology and Rural Environment,2015,31(1):112-117.]
[3]	徐兰,周敏,袁旭音,等.苏南区域农田土壤和大气颗粒中镉和铅含量及对水稻的贡献研究[J].生态与农村环境学报,2018,34(3):201-206.[XU Lan,ZHOU Min,YUAN Xu-yin,et al.Study on Cadmium and Lead Concentrations in Soils and Atmospheric Particles and Their Contributions to Rice in the Typical Agricultural Area of Southern Jiangsu Province[J].Journal of Ecology and Rural Environment,2018,34(3):201-206.]
[4]	孟敏,杨林生,韦炳干,等.我国设施农田土壤重金属污染评价与空间分布特征[J].生态与农村环境学报,2018,34(11):1019-1026.[MENG Min,YANG Lin-sheng,WEI Bing-gan,et al.Contamination Assessment and Spatial Distribution of Heavy Metals in Greenhouse Soils in China[J].Journal of Ecology and Rural Environment,2018,34(11):1019-1026.]
[5]	曹宏杰,王立民,罗春雨,等.三江平原地区农田土壤中几种重金属空间分布状况[J].生态与农村环境学报,2014,30(2):155-161.[CAO Hong-jie,WANG Li-min,LUO Chun-yu,et al.Spatial Distribution of Heavy Metals in Agricultural Soil in Sanjiang Plain[J].Journal of Ecology and Rural Environment,2014,30(2):155-161.]
[6]	全国土壤污染状况调查公报(2014年4月17日)[J].环境教育,2014(6):8-10.
[7]	曾希柏,徐建明,黄巧云,等.中国农田重金属问题的若干思考[J].土壤学报,2013,50(1):186-194.[ZENG Xi-bai,XU Jian-ming,HUANG Qiao-yun,et al.Some Deliberations on the Issues of Heavy Metals in Farmlands of China[J].Acta Pedologica Sinica,2013,50(1):186-194.]
[8]	陈飞香,程家昌,胡月明,等.基于RBF神经网络的土壤铬含量空间预测[J].地理科学,2013,33(1):69-74.[CHEN Fei-xiang,CHENG Jia-chang,HU Yue-ming,et al.Spatial Prediction of Soil Properties by RBF Neural Network[J].Scientia Geographica Sinica,2013,33(1):69-74.]
[9]	周宁,李超,满秀玲.基于Logistic回归和RBF神经网络的土壤侵蚀模数预测[J].水土保持通报,2015,35(3):235-241,2.[ZHOU Ning,LI Chao,MAN Xiu-lin.Prediction of Soil Erosion Modulus Based on Logistic Regression and RBF Neural Network[J].Bulletin of Soil and Water Conservation,2015,35(3):235-241,2.]
[10]	王琳琳.BP人工神经网络用于城市土壤中重金属(Cd、Pb)形态分析的研究[D].长春:吉林大学,2009.[WANG Lin-lin.Application of Back-propagation Artificial Neural Network in Speciation of Plumbum and Cadmium in City Soil[D].Changchun:Jilin University,2009.]
[11]	姚荣江,杨劲松,邹平,等.区域土壤水盐空间分布信息的BP神经网络模型研究[J].土壤学报,2009,46(5):788-794.[YAO Rong-jiang,YANG Jin-song,ZOU Ping,et al.BP Neural Network Model for Spatial Distribution of Regional Soil Water and Salinity[J].Acta Pedologica Sinica,2009,46(5):788-794.]
[12]	ANAGU I,INGWERSEN J,UTERMANN J,et al.Estimation of Heavy Metal Sorption in German Soils Using Artificial Neural Networks[J].Geoderma,2009,152(1/2):104-112.
[13]	胡大伟,卞新民,王书玉,等.基于BP模型的南通市农田土壤重金属空间分布研究[J].安全与环境学报,2007(2):91-95.[HU Da-wei,BIAN Xin-min,WANG Shu-yu,et al.Study on Spatial Distribution of Farmland Soil Heavy Metals in Nantong City Based on BP-ANN Modeling[J].Journal of Safety and Environment,2007(2):91-95.]
[14]	张红,卢茸,石伟,等.基于RBF神经网络的土壤重金属空间变异研究[J].中国生态农业学报,2012,20(4):474-479.[ZHANG Hong,LU Rong,SHI Wei,et al.Application of RBF Neural Network in Determining Soil Heavy Metal Spatial Variability[J].Chinese Journal of Eco-agriculture,2012,20(4):474-479.]
[15]	郭云开,刘宁,刘磊,等.土壤Cu含量高光谱反演的BP神经网络模型[J].测绘科学,2018,43(1):135-139,152.[GUO Yun-kai,LIU Ning,LIU Lei,et al.Hyper-spectral Inversion of Soil Cu Content Based on BP Neural Network Model[J].Science of Surveying and Mapping,2018,43(1):135-139,152.]
[16]	FU B J,CHEN L D,MA K M,et al.The Relationships Between Land Use and Soil Conditions in the Hilly Area of Loess Plateau in Northern Shaanxi,China[J].Catena,2000,39:69-78.
[17]	石栋奇,卢新卫.西安城区路面细颗粒灰尘重金属污染水平及来源分析[J].环境科学,2018,7:1-11.[SHI Dong-qi,LU Xin-wei.Contamination Levels and Source Analysis of Heavy Metals in the Finer Particles of Urban Road Dust From Xi'an,China[J].Environmental Science,2018,7:1-11.]
[18]	GUÉDRON S,AMOUROUX D,SABATIER P,et al.A Hundred Year Record of Industrial and Urban Development in French Alps Combining Hg Accumulation Rates and Isotope Composition in Sediment Archives From Lake Luitel[J].Chemical Geology,2016,431:10-19.
[19]	POUYAT R V,YESILONIS I D,RUSSELL-ANELLI J,et al.Soil Chemical and Physical Properties that Differentiate Urban Land-use and Cover Types[J].Soil Science Society of America Journal,2007,71(3):1010-1019.
[20]	ZHENG R,ZHAO J,ZHOU X,et al.Land Use Effects on the Distribution and Speciation of Heavy Metals and Arsenic in Coastal Soils on Chongming Island in the Yangtze River Estuary,China[J].Pedosphere,2016,26(1):74-84.
[21]	WANG L,COLES N A,WU C F,et al.Spatial Variability of Heavy Metals in the Coastal Soils Under Long-term Reclamation[J].Estuarine,Coastal and Shelf Science,2014,151:310-317.
[22]	HAO X Z,ZHOU D M,HUANG D Q,et al.Heavy Metal Transfer From Soil to Vegetable in Southern Jiangsu Province,China[J].Pedosphere,2009,19(3):305-311.
[23]	INSAM H,DOMSCH H.Relationship Between Soil Organic Carbon and Microbial Biomass on Chronosequences of Reclamation Sites[J].Microbial Ecology,1988,15(2):177-188.
[24]	DING Qian,CHENG Gong,WANG Yong,et al.Effects of Natural Factors on the Spatial Distribution of Heavy Metals in Soils Surrounding Mining Regions[J].Science of the Total Environment,2017,578:577-585.
[25]	杨娟,王昌全,李冰,等.基于BP神经网络的城市边缘带土壤重金属污染预测:以成都平原土壤Cd为例[J].土壤学报,2007(3):430-436.[YANG Juan,WANG Chang-quan,LI Bing,et al.Prediction of Soil Heavy Metal Pollution of Peri-urban Zone Based on BP Artificial Neural Network:A Case Study of the Chengdu Plain[J].Acta Pedologica Sinica,2007(3):430-436.]
[26]	袁曾任.人工神经网络及其应用[M].北京:清华大学出版社,2001:50-180.
[27]	吴健生,谢舞丹,李嘉诚.土地利用回归模型在大气污染时空分异研究中的应用[J].环境科学,2016,37(2):413-419.[WU Jian-sheng,XIE Wu-dan,LI Jia-cheng.Application of Land-use Regression Models in Spatial-temporal Differentiation of Air Pollution[J].Environmental Science,2016,37(2):413-419.]
[28]	AKAIKE H.A New Look at the Statistical Model Identification[J].IEEE Transactions on Automatic Control,1974,19(6):716-723.
[29]	王库.基于地理权重回归模型的土壤有机质空间预测[J].土壤通报,2013,44(1):21-28.[WANG Ku.Spatial Estimation of Soil Organic Matter by Using Geographically Weighted Regression Model[J].Chinese Journal of Soil Science,2013,44(1):21-28.]
[30]	廖启林,刘聪,许艳,等.江苏省土壤元素地球化学基准值[J].中国地质,2011,38(5):1363-1378.[LIAO Qi-lin,LIU Cong,XU Yan,et al.Geochemical Baseline Values of Elements in Soil of Jiangsu Province[J].Geology in China,2011,38(5):1363-1378.]
[31]	戴彬,吕建树,战金成,等.山东省典型工业城市土壤重金属来源、空间分布及潜在生态风险评价[J].环境科学,2015,36(2):507-515.[DAI Bin,LÜ Jian-shu,ZHAN Jin-cheng,et al.Assessment of Sources,Spatial Distribution and Ecological Risk of Heavy Metals in Soils in a Typical Industry-based City of Shandong Province,Eastern China[J].Environmental Science,2015,36(2):507-515.]
[32]	曹人升,范明毅,黄先飞,等.金沙燃煤电厂周围土壤有机质与重金属分析[J].环境化学,2017,36(2):397-407.[CAO Ren-sheng,FAN Ming-yi,HUANG Xian-fei,et al.Analysis of Organic Matter and Heavy Metals in Soils Around the Coal-fired Power Plant in Jinsha[J].Environmental Chemistry,2017,36(2):397-407.]
[33]	廖敏,黄昌勇,谢正苗.pH对镉在土水系统中的迁移和形态的影响[J].环境科学学报,1999(1):83-88.[LIAO Min,HUANG Chang-yong,XIE Zheng-miao.Effect of pH on Transport and Transformation of Cadmium in Soil-water System[J].Acta Scientiae Circumstantiae,1999(1):83-88.]
[34]	吕建树,张祖陆,刘洋,等.日照市土壤重金属来源解析及环境风险评价[J].地理学报,2012,67(7):971-984.[LÜ Jian-shu,ZHANG Zu-lu,LIU Yang,et al.Sources Identification and Hazardous Risk Delineation of Heavy Metals Contamination in Rizhao City[J].Acta Geographica Sinica,2012,67(7):971-984.]
[35]	李苹,黄勇,林赟,等.北京市怀柔区土壤重金属的分布特征、来源分析及风险评价[J].现代地质,2018,32(1):86-94.[LI Ping,HUANG Yong,LIN Yun,et al.Distribution,Source Identification and Risk Assessment of Heavy Metals in Topsoil of Huairou District in Beijing[J].Geoscience,2018,32(1):86-94.]