基于多源辅助数据和神经网络模型的稻田土壤砷空间分布预测
|
摘要
合适的方法和多源的辅助数据对于准确预测土壤重金属的空间分布具有重要意义.该研究提出一种径向基函数神经网络结合普通克里格法的模型(RBFNN_OK),由主成分分析(PCA)提取的地形因子、遥感数据和邻近信息等多源辅助数据作为自变量,预测江西省都昌县稻田土壤砷空间分布.为验证RBFNN_OK的可行性:首先在全县范围内采集144个稻田表层(0～20 cm)土壤样品,运用ArcGIS地统计模块随机抽取115个(80%)采样点作为测试集,29个(20%)采样点作为验证集.其次多源辅助数据包括地形因子、遥感数据和邻近信息等14个定量因子作为预测变量,将预测变量进行主成分分析,得到前10个主成分的累积贡献率达到97.62%.再次一个特定的RBFNN_OK被用来预测土壤砷空间分布.最后将RBFNN_OK模型的预测结果与径向基神经网络模型(RBFNN)、回归克里格模型(RK)和多元逐步线性回归模型(MSLR)进行比较.结果表明,RBFNN_OK的测量值标准偏差与均方根误差的比值(RPD)较其它3种方法分别提高了14.92%、35.71%和44.67%.此外,RBFNN_OK还提供了更加真实且有关土壤砷空间分布的细节信息.RBFNN_OK取得最优效果可能归因于引入多源辅助数据,考虑多源辅助数据和土壤砷之间的多重共线性和非线性关系.该方法可为稻田土壤砷调查与环境保护提供更为精准的信息.
A suitable method and appropriate auxiliary data are important for accurately predicting heavy metal distribution in soils. Here we propose a radial basis function neural network combined with ordinary kriging(RBFNN_OK), multi-source auxiliary data such as topographic factors, remote sensing data, and neighboring information extracted by principal component analysis(PCA) as independent variables for predicting the spatial distribution of arsenic in paddy soils in Duchang County, Jiangxi Province, China. First, surface(0～20 cm) soil samples were collected from 144 sampling points in paddy fields across the study area; 115(80%) of the sampling points were selected at random as the calibration set and 29(20%) were selected as the validation set using ArcGIS Geostatistical Analyst. Next, multi-source auxiliary data includes 14 quantitative factors such as the topographic factors, remote sensing data, and neighboring information were selected as auxiliary variables, these variables were used for PCA and the cumulative contribution of the first 10 principal components to the total variance reached 97.62%. Then, a particular RBFNN_OK model was adapted to predict the spatial distribution of soil arsenic using the first 10 principal components. Finally, the predictions of RBFNN_OK were compared with those of radial basis function neural network(RBFNN), regression kriging(RK), and multiple stepwose linear regression(MSLR) for assessment of prediction accuracy. Results showed that the ratio of standard deviation of measured values to root mean square error of predictions was 2.85 for RBFNN_OK and 1.97～2.48 for the other three models, RBFNN_OK was increased by 14.92%, 35.71% and 44.67%, respectively, compared with the others. In addition, RBFNN_OK provides more detailed information about the spatial distribution of soil arsenic. The improved performance of RBFNN_OK can be attributed to the introduction of multi-source auxiliary data, to consider the multicollinearity and nonlinear relationship between multi-source auxiliary data and soil arsenic. This method may provide more accurate information for the investigation of arsenic in the paddy soil and environmental protection.
A suitable method and appropriate auxiliary data are important for accurately predicting heavy metal distribution in soils. Here we propose a radial basis function neural network combined with ordinary kriging(RBFNN_OK), multi-source auxiliary data such as topographic factors, remote sensing data, and neighboring information extracted by principal component analysis(PCA) as independent variables for predicting the spatial distribution of arsenic in paddy soils in Duchang County, Jiangxi Province, China. First, surface(0～20 cm) soil samples were collected from 144 sampling points in paddy fields across the study area; 115(80%) of the sampling points were selected at random as the calibration set and 29(20%) were selected as the validation set using ArcGIS Geostatistical Analyst. Next, multi-source auxiliary data includes 14 quantitative factors such as the topographic factors, remote sensing data, and neighboring information were selected as auxiliary variables, these variables were used for PCA and the cumulative contribution of the first 10 principal components to the total variance reached 97.62%. Then, a particular RBFNN_OK model was adapted to predict the spatial distribution of soil arsenic using the first 10 principal components. Finally, the predictions of RBFNN_OK were compared with those of radial basis function neural network(RBFNN), regression kriging(RK), and multiple stepwose linear regression(MSLR) for assessment of prediction accuracy. Results showed that the ratio of standard deviation of measured values to root mean square error of predictions was 2.85 for RBFNN_OK and 1.97～2.48 for the other three models, RBFNN_OK was increased by 14.92%, 35.71% and 44.67%, respectively, compared with the others. In addition, RBFNN_OK provides more detailed information about the spatial distribution of soil arsenic. The improved performance of RBFNN_OK can be attributed to the introduction of multi-source auxiliary data, to consider the multicollinearity and nonlinear relationship between multi-source auxiliary data and soil arsenic. This method may provide more accurate information for the investigation of arsenic in the paddy soil and environmental protection.
引文
Ahmed Z U,Panaullah G M,Degloria S D,et al.2011.Factors affecting paddy soil arsenic concentration in Bangladesh:prediction and uncertainty of geostatistical risk mapping[J].Science of the Total Environment,412(412/413):324-335
Biswas S R,Macdonald R L,Chen H Y H.2017.Disturbance increases negative spatial autocorrelation in speciesdiversity[J].Landscape Ecology,32(4):823-834
Cambardella C A.1994.Field-scale variability of soil properties in central Iowa soils[J].Soilence Society of America Journal,58(5):1501-1511
Dai F,Zhou Q,Lv Z,et al.2014.Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau[J].Ecological Indicators,45(5):184-194
Dai L,Wang L,Li L,et al.2018.Multivariate geostatistical analysis and source identification of heavy metals in the sediment of Poyang Lake in China[J].Science of the Total Environment,621:1433-1444
Feng J,Zhao J,Bian X,et al.2012.Spatial distribution and controlling factors of heavy metals contents in paddy soil and crop grains of rice-wheat cropping system along highway in East China[J].Environmental Geochemistry and Health,34(5):605-614
Goovaerts P.1997.Geostatistics for Natural Resources Evaluation[M].Oxford University Press,USA
Geen A V,Zheng Y S,Goodbred J,et al.2008.Flushing history as a hydrogeological control on the regional distribution of arsenic in shallow groundwater of the Bengal Basin[J].Environmental Science&Technology,42(7):2283-2288
Grunwald S.2009.Multi-criteria characterization of recent digital soil mapping and modeling approaches[J].Geoderma,152:195-207
Guo X,Li H Y,Yu H M,et al.2018.Drivers of spatio-temporal changes in paddy soil pH in Jiangxi Province,China from 1980 to2010[J].Scientific Reports,DOI:10.1038/s41598-018-20873-5
Hengl T,Heuvelink G B M,Stein A.2004.A generic framework for spatial prediction of soil variables based on regression-kriging[J].Geoderma,120(1/2):75-93
Hu Y,Jia Z,Cheng J,et al.2016.Spatial variability of soil arsenic and its association with soil nitrogen in intensive farming systems[J].Journal of Soils and Sediments,16(1):169-176
江西省地质调查研究院.2009.鄱阳湖地球化学图集[M].南昌:江西科学技术出版社.106-107
江叶枫,孙凯,郭熙,等.2017.基于环境因子和邻近信息的土壤属性空间分布预测[J].环境科学研究,30(7):1059-1068
Jiang Y F,Rao L,Sun K,et al.2018.Spatio-temporal distribution of soil nitrogen in Poyang Lake ecological economic zone(South-China)[J].Science of the Total Environment,626:235-243
Kim K,Moon J T,Kim S H,et al.2009.Importance of surface geologic condition in regulating As concentration of groundwater in the alluvial plain[J].Chemosphere,77(4):478-484
Kumar S,Lal R,Liu D.2012.A geographically weighted regression kriging approach for mapping soil organic carbon stock[J].Geoderma,189-190(6):627-634
李启权,王昌全,岳天祥,等.2008.不同输入方式下RBF神经网络对土壤性质空间插值的误差分析[J].土壤学报,45(2):360-365
Li Y.2010.Can the spatial prediction of soil organic matter contents at various sampling scales be improved by using regressionkriging with auxiliary information?[J].Geoderma,159(1):63-75
Li Q Q,Yue T X,Wang C Q,et al.2013a.Spatially distributed modeling of soil organic matter across China:An application of artificial neural network approach[J].Catena,104(2):210-218
Li X Y,Liu L J,Wang Y G,et al.2013b.Heavy metal contamination of urban soil in an old industrial city(Shenyang)in Northeast China[J].Geoderma,192(1):50-58
Lv J,Liu Y,Zhang Z,et al.2015.Identifying the origins and spatial distributions of heavy metals in soils of Ju country(Eastern China)using multivariate and geostatistical approach[J].Journal of Soils&Sediments,15(1):163-178
Li QQ,Wang C Q,Dai T F,et al.2017a.Prediction of soil cadmium distribution across a typical area of Chengdu Plain,China[J].Scientific Reports,DOI:10.1038/s41598-017-07690-y
Li QQ,Zhang H,Jiang X Y,et al.2017b.Spatially distributed modeling of soil organic carbon across China with improved accuracy[J].Journal of Advances in Modeling Earth Systems,DOI:10.1002/2016MS000827
Mcbratney A B,Santos M L M,Minasny B.2003.On digital soil mapping[J].Geoderma,117(1):3-52
Miller H J.2004.Tobler's First Law and Spatial Analysis[J].Annals of the Association of American Geographers,94(2):284-289
Mishra U,Lal R,Liu D S,et al.2010.Predicting the spatial variation of the soil organic carbon pool at a regional scale[J].Soil Science Society of America Journal,74(3):906-914
Mcbratney A,Field D J,Koch A.2014.The dimensions of soil security[J].Geoderma,213(1):203-213
Mirzaee S,Ghorbani-Dashtaki S,Mohammadi J,et al.2016.Spatial variability of soil organic matter using remote sensing data[J].Catena,145:118-127
Odeha I O A,Mcbratney A B,Chittleborough D J.1994.Spatial prediction of soil properties from landform attributes derived from a digital elevation model[J].Geoderma,63(3/4):197-214
Rogan N,Dolenec T,Serafimovski T,et al.2010.Distribution and mobility of heavy metals in paddy soils of the Ko cˇani Field in Macedonia[J].Environmental Earth Sciences,61(5):899-907
Razakamanarivo R H,Grinand C.2011.Mapping organic carbon stocks in eucalyptus plantations of the central highlands of Madagascar:Amultiple regression approach[J].Geoderma,162(3/4):335-346
史舟,王乾龙,彭杰,等.2014.中国主要土壤高光谱反射特性分类与有机质光谱预测模型[J].中国科学:地球科学,44(5):978-988
Zhang S,Huang Y,Shen C,et al.2012.Spatial prediction of soil organic matter using terrain indices and categorical variables as auxiliary information[J].Geoderma,171-172(2):35-43
Zhao H,Xia B,Fan C,et al.2012.Human health risk from soil heavy metal contamination under different land uses near Dabaoshan Mine,Southern China[J].Science of the Total Environment,417-418(7385):45-54
曾希柏,徐建明,黄巧云,等.2013.中国农田重金属问题的若干思考[J].土壤学报,50(1):186-194
Biswas S R,Macdonald R L,Chen H Y H.2017.Disturbance increases negative spatial autocorrelation in speciesdiversity[J].Landscape Ecology,32(4):823-834
Cambardella C A.1994.Field-scale variability of soil properties in central Iowa soils[J].Soilence Society of America Journal,58(5):1501-1511
Dai F,Zhou Q,Lv Z,et al.2014.Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau[J].Ecological Indicators,45(5):184-194
Dai L,Wang L,Li L,et al.2018.Multivariate geostatistical analysis and source identification of heavy metals in the sediment of Poyang Lake in China[J].Science of the Total Environment,621:1433-1444
Feng J,Zhao J,Bian X,et al.2012.Spatial distribution and controlling factors of heavy metals contents in paddy soil and crop grains of rice-wheat cropping system along highway in East China[J].Environmental Geochemistry and Health,34(5):605-614
Goovaerts P.1997.Geostatistics for Natural Resources Evaluation[M].Oxford University Press,USA
Geen A V,Zheng Y S,Goodbred J,et al.2008.Flushing history as a hydrogeological control on the regional distribution of arsenic in shallow groundwater of the Bengal Basin[J].Environmental Science&Technology,42(7):2283-2288
Grunwald S.2009.Multi-criteria characterization of recent digital soil mapping and modeling approaches[J].Geoderma,152:195-207
Guo X,Li H Y,Yu H M,et al.2018.Drivers of spatio-temporal changes in paddy soil pH in Jiangxi Province,China from 1980 to2010[J].Scientific Reports,DOI:10.1038/s41598-018-20873-5
Hengl T,Heuvelink G B M,Stein A.2004.A generic framework for spatial prediction of soil variables based on regression-kriging[J].Geoderma,120(1/2):75-93
Hu Y,Jia Z,Cheng J,et al.2016.Spatial variability of soil arsenic and its association with soil nitrogen in intensive farming systems[J].Journal of Soils and Sediments,16(1):169-176
江西省地质调查研究院.2009.鄱阳湖地球化学图集[M].南昌:江西科学技术出版社.106-107
江叶枫,孙凯,郭熙,等.2017.基于环境因子和邻近信息的土壤属性空间分布预测[J].环境科学研究,30(7):1059-1068
Jiang Y F,Rao L,Sun K,et al.2018.Spatio-temporal distribution of soil nitrogen in Poyang Lake ecological economic zone(South-China)[J].Science of the Total Environment,626:235-243
Kim K,Moon J T,Kim S H,et al.2009.Importance of surface geologic condition in regulating As concentration of groundwater in the alluvial plain[J].Chemosphere,77(4):478-484
Kumar S,Lal R,Liu D.2012.A geographically weighted regression kriging approach for mapping soil organic carbon stock[J].Geoderma,189-190(6):627-634
李启权,王昌全,岳天祥,等.2008.不同输入方式下RBF神经网络对土壤性质空间插值的误差分析[J].土壤学报,45(2):360-365
Li Y.2010.Can the spatial prediction of soil organic matter contents at various sampling scales be improved by using regressionkriging with auxiliary information?[J].Geoderma,159(1):63-75
Li Q Q,Yue T X,Wang C Q,et al.2013a.Spatially distributed modeling of soil organic matter across China:An application of artificial neural network approach[J].Catena,104(2):210-218
Li X Y,Liu L J,Wang Y G,et al.2013b.Heavy metal contamination of urban soil in an old industrial city(Shenyang)in Northeast China[J].Geoderma,192(1):50-58
Lv J,Liu Y,Zhang Z,et al.2015.Identifying the origins and spatial distributions of heavy metals in soils of Ju country(Eastern China)using multivariate and geostatistical approach[J].Journal of Soils&Sediments,15(1):163-178
Li QQ,Wang C Q,Dai T F,et al.2017a.Prediction of soil cadmium distribution across a typical area of Chengdu Plain,China[J].Scientific Reports,DOI:10.1038/s41598-017-07690-y
Li QQ,Zhang H,Jiang X Y,et al.2017b.Spatially distributed modeling of soil organic carbon across China with improved accuracy[J].Journal of Advances in Modeling Earth Systems,DOI:10.1002/2016MS000827
Mcbratney A B,Santos M L M,Minasny B.2003.On digital soil mapping[J].Geoderma,117(1):3-52
Miller H J.2004.Tobler's First Law and Spatial Analysis[J].Annals of the Association of American Geographers,94(2):284-289
Mishra U,Lal R,Liu D S,et al.2010.Predicting the spatial variation of the soil organic carbon pool at a regional scale[J].Soil Science Society of America Journal,74(3):906-914
Mcbratney A,Field D J,Koch A.2014.The dimensions of soil security[J].Geoderma,213(1):203-213
Mirzaee S,Ghorbani-Dashtaki S,Mohammadi J,et al.2016.Spatial variability of soil organic matter using remote sensing data[J].Catena,145:118-127
Odeha I O A,Mcbratney A B,Chittleborough D J.1994.Spatial prediction of soil properties from landform attributes derived from a digital elevation model[J].Geoderma,63(3/4):197-214
Rogan N,Dolenec T,Serafimovski T,et al.2010.Distribution and mobility of heavy metals in paddy soils of the Ko cˇani Field in Macedonia[J].Environmental Earth Sciences,61(5):899-907
Razakamanarivo R H,Grinand C.2011.Mapping organic carbon stocks in eucalyptus plantations of the central highlands of Madagascar:Amultiple regression approach[J].Geoderma,162(3/4):335-346
史舟,王乾龙,彭杰,等.2014.中国主要土壤高光谱反射特性分类与有机质光谱预测模型[J].中国科学:地球科学,44(5):978-988
Zhang S,Huang Y,Shen C,et al.2012.Spatial prediction of soil organic matter using terrain indices and categorical variables as auxiliary information[J].Geoderma,171-172(2):35-43
Zhao H,Xia B,Fan C,et al.2012.Human health risk from soil heavy metal contamination under different land uses near Dabaoshan Mine,Southern China[J].Science of the Total Environment,417-418(7385):45-54
曾希柏,徐建明,黄巧云,等.2013.中国农田重金属问题的若干思考[J].土壤学报,50(1):186-194