水资源研究  >> Vol. 3 No. 2 (April 2014)

区域性水土空间变异的人工神经指示克立格技术研究
Research on the Zonal Water-Soil Resource Spatial Variation Using Artificial Neural Indicator Kriging Technology

DOI: 10.12677/JWRR.2014.32021, PDF, HTML, 下载: 2,386  浏览: 8,819  国家自然科学基金支持

作者: 刘全明:内蒙古农业大学,水资源与水土工程研究所,呼和浩特;陈永强:内蒙古水利水利水电勘测设计院测绘处,呼和浩特

关键词: 区域性水土空间变异人工神经指示克立格Zonal Water-Soil Resource Spatial Variation Artificial Neural Indicator Kriging

摘要: 本文基于非参数地质统计学的指示Kriging法思想,借助人工神经网络高度非线性逼近的技术优点,以河套灌区内一典型实验区的土壤水盐空间变异性为案例,进行了非参数统计与人工智能技术的创新性融合研究。经与普通克立格、BP神经网络、指示克立格与析取克立格估计值对比分析发现:人工神经指示克立格法具有指示克立格的优点,即对数据无统计假定,不涉及特异值识别与处理,又可以高度逼近线性与非线性函数,很好地解决非线性估值问题,可用于土壤水盐监测及相关工作中
Abstract: Based on the spatial variation of soil water-salt at one representative experimental section in Hetao irrigation zone, directed by Indicator Kriging of non-parameter Geostatistic theory, using the high non-linear approximating ability of ANN, this paper innovated fusion of the non-parameter statistic and artificial intelligence technologies. Compared with the Ordinary Kriging, BP, Indicator Kriging, and Distinctive Kriging estimating values, it is founded that Artificial Neural Indicator Kriging has the characteristics of indicator kriging: 1) no need to make statistical assumptions for raw data; 2) not involving identification and specificity values treatment; 3) a high degree of approximation of linear and nonlinear functions; which can solve nonlinear problems effectively, so it can be used to monitor soil water and salt and the related work.

文章引用: 刘全明, 陈永强. 区域性水土空间变异的人工神经指示克立格技术研究[J]. 水资源研究, 2014, 3(2): 152-159. http://dx.doi.org/10.12677/JWRR.2014.32021

参考文献

[1] RIZZO, D. M., DOUGHERTY, D. E. Characterization of aquifer properties using artificial neural networks: Neural Kriging. Water Resources Research, 1994, 30(2): 483-497.
[2] JEROSCH, K., SCHLUTER, M. Methane spacial distribution research about geography information Mosaic based on indicator Kriging technical on Hakon Mosby deep sea volcano. Ecology Information, 2006, 1(4): 391-406.
[3] LEBRON, L. M. G., SCHAAP, D. L. Saturated hydraulic conductivity prediction from microscopic pore geometry measurements and neural networks analysis. Water Resources Research, 1999, 35(10): 3149-3158.
[4] EMEVY, X., ORTIZ, J. M. Shortcomings of multiple indicator Kriging for assessing local distributions. Applied Earth Science, 2004, 113(4): 249-259.
[5] JOURNEL, A. G. Non-parametric estimation of spatial distribution. Mathematical Geology, 1983, 15(3): 445-468.
[6] CARR, J. R. and BAILEY, R. E. Use of indicator variogram for an enhanced spatial analysis. Mathematical Geology, 1985, 17(8): 797-812.
[7] MAIER, H. R. and DANDY, G. C. The use of artificial neural networks for the prediction of water quality parameters. Water Resources Research, 1996, 32(4): 1013-1022.
[8] VAUGHAN, P. J., LESCH, S. M., CORWIN, D. L., et al. Water content effect on soil salinity prediction: A geostatistical study using cokriging. Soil Science Society of America Journal, 1995, 59(4): 1146-1156.
[9] SMITH, J. L., HALVORSON, J. J. and PAPENDICK, R. J. Using multiple-variable indicator Kriging for evaluating soil quality. Soil Science Society of America Journal, 1993, 57(3): 743-749.
[10] GOOYAERTS, P. Comparative performance of indicator algorithms for modeling conditional probability distribution functions. Mathematical Geology, 1994, 26(3): 389-411.
[11] HALVORSON, J. J., SMITH, J. L., BOLTON, H., et al. Evaluating shrub-associated sptterns of soil properties in shrub-steppe ecosystem using multiple-variable geostatistics. Soil Science Society of America Journal, 1995, 59(5): 1476-1487.
[12] JOURNEL, A. G. Combining knowledge from diverse resources: An alternative to traditional data independence hypotheses. Mathematical Geology, 2002, 34(5): 573-596.
[13] 杨建强, 罗先强. 土壤盐渍化与地下水动态特征关系研究[J]. 水土保持通报, 1999, 19(6): 11-15.
YANG Jianjiang, LUO Xianqiang. Study on the relationship between the soil salinization and groundwater dynamic characteristics. Journal of Soil and Water Conservation Bulletin, 1999, 19 (6): 11-15. (in Chinese)
[14] 赵辉, 吕谋超, 等. 引黄灌溉对商丘地区浅层地下水动态影响研究[J]. 灌溉排水, 2000, 19(2): 38-40.
ZHAO Hui, LV Mouchao, et al. Shallow groundwater dynamic impact study on the Yellow River irrigation in Shangqiu area. Journal of Irrigation and Drainage, 2000, 19(2): 38-40. (in Chinese)
[15] 屈忠义, 陈亚新, 等. 区域土壤水盐动态的人工神经网络预测研究[J]. 灌溉排水, 2002, 21(4): 40-44.
Qu Zhongyi, CHEN Yaxin, et al. Regional soil water and salt dynamic prediction research based on the Artificial Neural Network.Journal of Irrigation and Drainage, 2002, 21(4): 40-44. (in Chinese)
[16] 屈忠义, 陈亚新, 等. 内蒙古河套灌区节水工程实施后地下水变化的BP模型预测[J]. 农业工程学报, 2003, 19(1): 59-62.
Qu Zhongyi, CHEN Yaxin, et al. The BP model prediction of groundwater change after the implementation of water saving engineering in Inner Mongolia hetao irrigation area. Journal of Agricultural Engineering, 2003, 19(1): 59-62. (in Chinese)
[17] 刘全明, 陈亚新, 魏占民, 等. 基于人工智能计算技术的区域性土壤水盐环境动态监测[J]. 农业工程学报, 2006, 22(10): 1-6.
LIU Quanming, CHEN Yaxin, WEI Zhanmin, et al. Regional soil water and salt environment dynamic monitoring based on the Artificial Intelligence computing technology[J].Journal of Agricultural Engineering, 2006, vol. 22 (10) : 1-6. (in chinese)
[18] FYTAS, K., CHAOUAI, N.E. and LAVIGNE, M. Gold deposits estimation using indicator Kriging. CIM Bulletin, 1990, 80: 77-83.
[19] GOOYAERTS, P., WEBSTER, R. and DUBOIS, J. P. Assessing the risk of soil contamination in the Swiss Jura using indicator geostatistics. Environmental and Ecological Statistics, 1997, 4(1): 31-48.
[20] 侯景儒. 指示克立格法的理论及方法[J]. 地质与勘探, 1990, 26(3): 28-38.
HOU Jingru. Indicator Kriging theory and method. Geology and Prospecting, 1990, 26(3): 28-38. (in Chinese)
[21] 李保国, 胡克林, 黄元仿, 等. 区域浅层地下水硝酸盐含量评价的指示克立格法[J]. 水利学报, 2001, 3: 1-5.
LI Baoguo, HU Kelin, Huang yuanfang, et al. Regional evaluation of the Nitrate content in shallow groundwater based on the Indicator Kriging method. Journal of Water Conservancy, 2001, 3: 1-5. (in Chinese)
[22] 吴蓉, 周志芳. 基于指示克立格方法的裂隙介质渗透性参数空间分布规律分析[J]. 水利学报, 2004, 6: 104-107. WU Rong, ZHOU Zhifang. Spatial distribution analysis of the fissure medium permeability parameters based on the Indicator Kriging. Journal of Water Conservancy, 2004, 6:104-107. (in Chinese)
[23] 徐英, 陈亚新, 王俊生, 刘全明. 农田土壤水分和盐分空间分布的指示克立格分析评价[J]. 水科学进展, 2006, 17(4): 477-482.
XV Ying, CHEN Yaxin, WANG Junsheng and LIU quanming. The analysis and evaluation of the spatial distribution of soil moisture and salt using Indicator Kriging. Advances in Water Science, 2006, 17(4): 477-482. (in Chinese)
[24] 陈亚新, 史海滨, 魏占民, 等. 土壤水盐信息空间变异的预测理论与条件模拟[M]. 北京: 科学出版社, 2005.
CHEN Yaxin, SHI Haibin, WEI Zhanmin, et al. Forecast theory and Conditional Simulation of spatial variability about the soil water and salt information. Beijing: Science Press, 2005. (in Chinese)
[25] 刘全明, 陈亚新, 魏占民, 等. 非参数统计理论与人工智能技术在水土空间变异中的应用研究[J]. 灌溉排水学报, 2006, 25(1): 49-53.
LIU Quanming, CHEN Yaxin, WEI Zhanmin, et al. Application research of nonparametric statistics theory and artificial intelligence technology in the spatial variation of the soil and water. Journal of Irrigation and Drainage, 2006, 25(1): 49-53. (in Chinese)
[26] 刘全明, 陈亚新, 魏占民, 徐冰. 土壤水盐空间变异的指示克立格法阈值及其函数关系研究[J]. 水利学报, 2009, 40(9): 1127-1134.
LIU Quanming, CHEN Yaxin, WEI Zhanmin and XU Bing. Relationship research between Cutoff Value of Indicator Kriging and functional zonal Water-salt Resource Spatial Variation. Journal of Water Conservancy, 2009, 40(9): 11271134. (in Chinese)