基于GARBF神经网络的土壤属性信息空间插值方法研究
|
摘要
土壤是受自然因素以及人为因素共同作用而形成。土壤并非一个匀质体,而是一个时空连续的变异体,具有高度的空间异质性。不论在大尺度还是在中小尺度上观察,土壤的空间异质性均存在。由于经济和人力的原因,采样点是有限的,要得到整个研究区的土壤属性信息就必须借助于空间插值方法。但土壤属性的复杂性和不确定性,使常用的插值方法精度往往不能满足要求,因此,改进空间插值方法,以较少样点获取更为详尽的土壤属性空间变异规律,就成为当前研究的热点。
本研究以眉山太和镇和尚义镇为试验区,分别以700米和50米为间隔,采集大小两个尺度下的土壤样品80个和30个,以土壤有效铜和有效锌为研究对象,将两个样本分为独立的训练样本和检验样本数据集,在训练样本集的基础上共设计了4种样点布局方案,以广泛应用的普通克里格法和RBF神经网络作为对照,研究GARBF神经网络技术对土壤属性信息的空间插值能力。
GARBF神经网络即遗传径向基函数神经网络具有很强的非线性计算能力,是解决非线性系统预测问题行之有效的研究工具。本研究将地理坐标(X,Y)和距离插值点最近的5个点作为网络的输入值,即网络的输入节点数为7,输出为采样点或者未知点的土壤属性值,输出节点为1。模型在对现有的样本进行学习和训练中,利用遗传算法优化计算RBF神经网络隐层到输出层的权值,直到网络掌握了这些输入—输出之间的对应关系为止,再用训练好的GARBF神经网络来预测各个插值点元素的含量,将预测结果存为记事本格式文件,借助ArcGIS9.0软件转成Raster文件,生成插值栅格图。研究结果表明:
(1)在大、小个尺度不同布局方案(a、b、c、d)下,由三种方法(GARBF、RBF、Ordinary Kriging)的散点图可知,GARBF神经网络利用遗传算法优化RBF神经网络权值,提高了对训练样本(有效铜、有效锌)的网络拟合能力,三种插值方法对训练样本的拟合能力为GARBF＞RBF＞Ordinary Kriging。
(2)以平均绝对误差和误差均方根作为插值精度的评价指标,无论在大尺度还是在小尺度中GARBF神经网络的插值精度均高于RBF神经网络和普通克里格插值法。主要结果如下:
在大尺度中GARBF与RBF神经网络相比,有效铜和有效锌训练样本的逼近误差分别降低0.02～0.01(a-Cu)、0.20～0.22(b-Cu)、0.22～0.25(a-Zn)、0.10～0.11(b-Zn),检验样本的插值误差分别降低0.23～0.26(a-Cu)、0.16～0.12(b-Cu)、0.13～0.11(a-Zn)、0.02～0.13(b-Zn);GARBF与Ordinary Kriging相比,训练样本的逼近误差分别降低1.18～1.43(a-Cu)、0.98～1.16(b-Cu)、1.19～1.47(a-Zn)、1.46～1.87(b-Zn),检验样本的插值误差分别降低0.57～0.30(a-Cu)、0.02～0.05(b-Cu)、0.14～0.20(a-Zn)、0.51～0.24(b-Zn)。
在小尺度中GARBF与RBF神经网络相比,有效铜和有效锌训练样本的逼近误差分别降低0.01～0.01(c-Cu)、0.21～0.25(d-Cu)、0.10～0.12(c-Zn)、0.10～0.11(d-Zn),检验样本的插值误差分别降低0.12～0.12(c-Cu)、0.01～0.04(d-Cu)、0.04～0.07(c-Zn)、0.05～0.05(d-Zn);与Ordinary Kriging相比,训练样本的逼近误差分别降低0.49～0.69(c-Cu)、1.19～1.31(d-Cu)、0.38～0.53(c-Zn)、0.36～0.60(d-Zn);检验样本的插值误差分别降低0.37～0.42(c-Cu)、0.53～0.59(d-Cu)、0.01～0.08(c-Zn)、0.08～0.27(d-Zn)。GARBF神经网络的各项误差最小,故插值精度最高。
(3)不同尺度下,三种方法的空间插值图有一定的差异。大尺度中三种方法的插值图都呈现出相似的分布规律。小尺度中三种插值方法的插值图都有一定的差异性,具体体现在总体趋势的不同和代表元素含量高低的栅格分布的范围不同,这可能与小尺度采样点减少有关。总体而言,以神经网络的插值图更能表现土壤元素的空间异质性尤其是GARBF神经网络在尊重原始实测数据值的情况下,整体分布相对离散,斑块更丰富,突出了数据分布的波动性,更能反映土壤属性的实际空间分布状况。这主要是因为遗传算法避免了神经网络容易陷入局部最优点,扩大了对土壤中相关空间信息的搜索面积,在一定程度上能摆脱类似克里格插值的“平滑效应”。
Soil property is the result of combined action of nature and human factors.soil is non-homogeneous body, but space-time successive variant,with higher spatial heterogeneity. Soil has spatial heterogeneity in large scale or small scale. Because of economy and manpower, sampling sites are definite, so in order to obtain soil spatial information, we should rely on interpolation method. Due to the complexity and uncertainty of soil property, the precision of common interpolation method always can not often meet request. So, improving the spatial interpolation method to obtain the laws of soil spatial variability with lesser sampling sites became a hotspot in the research field now.
TaiHe town and Shangyi town, MeiShan county were selected for the research. Two samples were collected in different scale, one was collected in large scale including 80 soil points,their interval was 700m, the other one was collected in small scale including 30 soil points and their interval was 50m. Available zinc and available cuprum were selected as the object for research.The samples were divided into training and validation datum sets. In order to research the performance of GARBF Neural Networks for soil spatial information interpolation, 4 sampling schemes were designed based on the two training sample set and the performance of GARBF Neural Networks was compared with RBF Neural Networks and Ordinary Kriging method which were widely applied.
GARBF Neural Networks(Genetic Algorithm Radias Basis Function Neural Networks), which had strong nonlinear computing competence, was an effective tool for solving the nonlinear system problem. In this paper, the coordinate of the soil points and the values of the 5 soil points which were close to the points needed interpolating were designed as the input of net, so there were 7 nodes in the input layer, the value of the soil property of sampling sites or unknown soil point was the output of the net and there was 1 node in the output layer. In the course of studying and being trained, the model optimized the weights between RBF neural network hidden layer and output layer, using Genetic Algorithm.until the Network learns the relationship between input and output, GARBF can predict the content of each interpolation site. The result of predict value save as .txt file, it can be transferred Raster file and formed the interpolation figure of grid by using the ArcGIS 9.0. The results indicated:
(1) The large and small scale under four different sampling schemes (a & b & c & d),the scatter figure of three methods (GARBF and RBF and Ordinary Kriging) showed GARBF used genetic algorithm optimize weight of RBF neural network, and raised the fitting capacity for training sample .The fitting capacity of three methods applied to the same area followed the sequence of GARBF > RBF > Ordinary Kriging.
(2) Average absolute error and root mean square error were chosen to judge precision of the interpolation methods, whether the points was collected in large or small scale, the interpolation precision of GARBF neural network method excelled RBF neural network and the Kriging method. The main results as follow:
In large scale, GARBF as compared with RBF, the approximate errors of the training samples about available cuprum were reduced by 0.02～0.01 in Scheme a and by 0.20～0.22 in Scheme b, available zinc by 0.22～0.25 in Scheme a and by 0.10～0.11 in Scheme b. The interpolation errors of the test samples about available cuprum by 0.23～0.26 in Scheme a and by 0.16～0.12 in Scheme b, available zinc by 0.13～0.11 in Scheme a and by 0.02～0.13 in Scheme b. GARBF as compared with Ordinary Kriging, the approximation errors of the training samples about available cuprum were reduced by 1.18～1.43 in Scheme a and by 0.98～1.16 in Scheme b, available zinc by 1.19～1.47 in Scheme a and by 1.46～1.87 in Scheme b. The interpolation errors of the test samples about available cuprum by 0.57～0.30 in Scheme a and by 0.02～0.05 in Scheme b, available znic by 0.14～0.20 in Scheme a and by 0.51～0.24 in Scheme b.
In small scale, GARBF as compared with RBF, the approximate errors of the training samples about available cuprum were reduced by 0.01～0.01 in Scheme c and by 0.21～0.25 in Scheme d,available zinc by 0.10～0.12 in Scheme c and by 0.10～0.11 in Scheme d, then The interpolation errors of the test samples about available cuprum by 0.12～0.12 in Scheme c and by 0.01～0.04 in Scheme d, available zinc by 0.04～0.07 in Scheme c and by 0.05～0.05 in Scheme d; GARBF as compared with Ordinary Kriging, the approximation errors of the training samples about available cuprum were reduced by 0.49～0.69 in Scheme c and by 1.19～1.31 in Scheme d ,available zinc by 0.38～0.53 in Scheme c and by 0.36～0.60 in Scheme d ,The interpolation errors of the test samples about available cuprum by 0.37～0.42 in Scheme c and by 0.53～0.59 in Scheme d , available znic by 0.01～0.08 in Scheme c and by 0.08～0.27 in Scheme d. So it was obvious that the GARBF neural network was the least in error and the highest in interpolation precision.
(3) In different scale, there were some difference in the interpolation map of three methods.The interpolation map of three methods had similar distribution tendency in large scale. But in small scale, the interpolation map of three methods had some diversity. That is, total tendency was different and the rang of raster distribution represented the elements was different too, and it was possiblily related to decrease of sampling point. In general, the interpolation map of nerual network showed the elements of soil spatial heterogeneity predominantly, GARBF neural network respect for the value of the original data especially, the overall distribution was discrete relative, plaque was abundant, distribution of the data variability was prominent and reflected the soil properties of the spatial distribution in the actual situation preferably. The reason was genetic algorithm overcame the tendency of neural networks to land in local optima and expanded the scope of search of spatial information pertaining to soil, thus to a certain extent avoiding a similar problem of "smooth effect" like Ordinary Kriging.
本研究以眉山太和镇和尚义镇为试验区,分别以700米和50米为间隔,采集大小两个尺度下的土壤样品80个和30个,以土壤有效铜和有效锌为研究对象,将两个样本分为独立的训练样本和检验样本数据集,在训练样本集的基础上共设计了4种样点布局方案,以广泛应用的普通克里格法和RBF神经网络作为对照,研究GARBF神经网络技术对土壤属性信息的空间插值能力。
GARBF神经网络即遗传径向基函数神经网络具有很强的非线性计算能力,是解决非线性系统预测问题行之有效的研究工具。本研究将地理坐标(X,Y)和距离插值点最近的5个点作为网络的输入值,即网络的输入节点数为7,输出为采样点或者未知点的土壤属性值,输出节点为1。模型在对现有的样本进行学习和训练中,利用遗传算法优化计算RBF神经网络隐层到输出层的权值,直到网络掌握了这些输入—输出之间的对应关系为止,再用训练好的GARBF神经网络来预测各个插值点元素的含量,将预测结果存为记事本格式文件,借助ArcGIS9.0软件转成Raster文件,生成插值栅格图。研究结果表明:
(1)在大、小个尺度不同布局方案(a、b、c、d)下,由三种方法(GARBF、RBF、Ordinary Kriging)的散点图可知,GARBF神经网络利用遗传算法优化RBF神经网络权值,提高了对训练样本(有效铜、有效锌)的网络拟合能力,三种插值方法对训练样本的拟合能力为GARBF＞RBF＞Ordinary Kriging。
(2)以平均绝对误差和误差均方根作为插值精度的评价指标,无论在大尺度还是在小尺度中GARBF神经网络的插值精度均高于RBF神经网络和普通克里格插值法。主要结果如下:
在大尺度中GARBF与RBF神经网络相比,有效铜和有效锌训练样本的逼近误差分别降低0.02～0.01(a-Cu)、0.20～0.22(b-Cu)、0.22～0.25(a-Zn)、0.10～0.11(b-Zn),检验样本的插值误差分别降低0.23～0.26(a-Cu)、0.16～0.12(b-Cu)、0.13～0.11(a-Zn)、0.02～0.13(b-Zn);GARBF与Ordinary Kriging相比,训练样本的逼近误差分别降低1.18～1.43(a-Cu)、0.98～1.16(b-Cu)、1.19～1.47(a-Zn)、1.46～1.87(b-Zn),检验样本的插值误差分别降低0.57～0.30(a-Cu)、0.02～0.05(b-Cu)、0.14～0.20(a-Zn)、0.51～0.24(b-Zn)。
在小尺度中GARBF与RBF神经网络相比,有效铜和有效锌训练样本的逼近误差分别降低0.01～0.01(c-Cu)、0.21～0.25(d-Cu)、0.10～0.12(c-Zn)、0.10～0.11(d-Zn),检验样本的插值误差分别降低0.12～0.12(c-Cu)、0.01～0.04(d-Cu)、0.04～0.07(c-Zn)、0.05～0.05(d-Zn);与Ordinary Kriging相比,训练样本的逼近误差分别降低0.49～0.69(c-Cu)、1.19～1.31(d-Cu)、0.38～0.53(c-Zn)、0.36～0.60(d-Zn);检验样本的插值误差分别降低0.37～0.42(c-Cu)、0.53～0.59(d-Cu)、0.01～0.08(c-Zn)、0.08～0.27(d-Zn)。GARBF神经网络的各项误差最小,故插值精度最高。
(3)不同尺度下,三种方法的空间插值图有一定的差异。大尺度中三种方法的插值图都呈现出相似的分布规律。小尺度中三种插值方法的插值图都有一定的差异性,具体体现在总体趋势的不同和代表元素含量高低的栅格分布的范围不同,这可能与小尺度采样点减少有关。总体而言,以神经网络的插值图更能表现土壤元素的空间异质性尤其是GARBF神经网络在尊重原始实测数据值的情况下,整体分布相对离散,斑块更丰富,突出了数据分布的波动性,更能反映土壤属性的实际空间分布状况。这主要是因为遗传算法避免了神经网络容易陷入局部最优点,扩大了对土壤中相关空间信息的搜索面积,在一定程度上能摆脱类似克里格插值的“平滑效应”。
Soil property is the result of combined action of nature and human factors.soil is non-homogeneous body, but space-time successive variant,with higher spatial heterogeneity. Soil has spatial heterogeneity in large scale or small scale. Because of economy and manpower, sampling sites are definite, so in order to obtain soil spatial information, we should rely on interpolation method. Due to the complexity and uncertainty of soil property, the precision of common interpolation method always can not often meet request. So, improving the spatial interpolation method to obtain the laws of soil spatial variability with lesser sampling sites became a hotspot in the research field now.
TaiHe town and Shangyi town, MeiShan county were selected for the research. Two samples were collected in different scale, one was collected in large scale including 80 soil points,their interval was 700m, the other one was collected in small scale including 30 soil points and their interval was 50m. Available zinc and available cuprum were selected as the object for research.The samples were divided into training and validation datum sets. In order to research the performance of GARBF Neural Networks for soil spatial information interpolation, 4 sampling schemes were designed based on the two training sample set and the performance of GARBF Neural Networks was compared with RBF Neural Networks and Ordinary Kriging method which were widely applied.
GARBF Neural Networks(Genetic Algorithm Radias Basis Function Neural Networks), which had strong nonlinear computing competence, was an effective tool for solving the nonlinear system problem. In this paper, the coordinate of the soil points and the values of the 5 soil points which were close to the points needed interpolating were designed as the input of net, so there were 7 nodes in the input layer, the value of the soil property of sampling sites or unknown soil point was the output of the net and there was 1 node in the output layer. In the course of studying and being trained, the model optimized the weights between RBF neural network hidden layer and output layer, using Genetic Algorithm.until the Network learns the relationship between input and output, GARBF can predict the content of each interpolation site. The result of predict value save as .txt file, it can be transferred Raster file and formed the interpolation figure of grid by using the ArcGIS 9.0. The results indicated:
(1) The large and small scale under four different sampling schemes (a & b & c & d),the scatter figure of three methods (GARBF and RBF and Ordinary Kriging) showed GARBF used genetic algorithm optimize weight of RBF neural network, and raised the fitting capacity for training sample .The fitting capacity of three methods applied to the same area followed the sequence of GARBF > RBF > Ordinary Kriging.
(2) Average absolute error and root mean square error were chosen to judge precision of the interpolation methods, whether the points was collected in large or small scale, the interpolation precision of GARBF neural network method excelled RBF neural network and the Kriging method. The main results as follow:
In large scale, GARBF as compared with RBF, the approximate errors of the training samples about available cuprum were reduced by 0.02～0.01 in Scheme a and by 0.20～0.22 in Scheme b, available zinc by 0.22～0.25 in Scheme a and by 0.10～0.11 in Scheme b. The interpolation errors of the test samples about available cuprum by 0.23～0.26 in Scheme a and by 0.16～0.12 in Scheme b, available zinc by 0.13～0.11 in Scheme a and by 0.02～0.13 in Scheme b. GARBF as compared with Ordinary Kriging, the approximation errors of the training samples about available cuprum were reduced by 1.18～1.43 in Scheme a and by 0.98～1.16 in Scheme b, available zinc by 1.19～1.47 in Scheme a and by 1.46～1.87 in Scheme b. The interpolation errors of the test samples about available cuprum by 0.57～0.30 in Scheme a and by 0.02～0.05 in Scheme b, available znic by 0.14～0.20 in Scheme a and by 0.51～0.24 in Scheme b.
In small scale, GARBF as compared with RBF, the approximate errors of the training samples about available cuprum were reduced by 0.01～0.01 in Scheme c and by 0.21～0.25 in Scheme d,available zinc by 0.10～0.12 in Scheme c and by 0.10～0.11 in Scheme d, then The interpolation errors of the test samples about available cuprum by 0.12～0.12 in Scheme c and by 0.01～0.04 in Scheme d, available zinc by 0.04～0.07 in Scheme c and by 0.05～0.05 in Scheme d; GARBF as compared with Ordinary Kriging, the approximation errors of the training samples about available cuprum were reduced by 0.49～0.69 in Scheme c and by 1.19～1.31 in Scheme d ,available zinc by 0.38～0.53 in Scheme c and by 0.36～0.60 in Scheme d ,The interpolation errors of the test samples about available cuprum by 0.37～0.42 in Scheme c and by 0.53～0.59 in Scheme d , available znic by 0.01～0.08 in Scheme c and by 0.08～0.27 in Scheme d. So it was obvious that the GARBF neural network was the least in error and the highest in interpolation precision.
(3) In different scale, there were some difference in the interpolation map of three methods.The interpolation map of three methods had similar distribution tendency in large scale. But in small scale, the interpolation map of three methods had some diversity. That is, total tendency was different and the rang of raster distribution represented the elements was different too, and it was possiblily related to decrease of sampling point. In general, the interpolation map of nerual network showed the elements of soil spatial heterogeneity predominantly, GARBF neural network respect for the value of the original data especially, the overall distribution was discrete relative, plaque was abundant, distribution of the data variability was prominent and reflected the soil properties of the spatial distribution in the actual situation preferably. The reason was genetic algorithm overcame the tendency of neural networks to land in local optima and expanded the scope of search of spatial information pertaining to soil, thus to a certain extent avoiding a similar problem of "smooth effect" like Ordinary Kriging.
引文
[1]周慧珍,龚子同,Lamp J.土壤空间变异性研究[J].土壤学报,1996,33(3):222-241.
[2]王学峰,章衡.土壤有机质的空间变异性[J].土壤,1995,27(2):85-89.
[3]王政权.地统计学及在生态学中的应用[M].北京:科学出版社,1999.
[4]华孟,于坚.土壤物理学[M].北京:北京农业大学出版社.1993,41-42.
[5]曾怀恩,黄声亭.基于Kriging方法的空间数据插值研究[J].测绘工程,2007,16(5):5-13.
[6]李明辉,何风华,申卫军,等.基于土壤生物空间异质性分析的空间土壤生态学研究[J].土壤,2005,37(4):375-381.
[7]何勇,张淑娟,方慧.基于人工神经网络的田间信息插值方法研究[J].农业工程学报,2004,20(3):120-123.
[8]岳天祥,刘纪远.多源信息融合数据模型[J].世界科技研究与发展,2001,23(5):1-4.
[9]Goovaerts EGeostatistics for Natural Resources Evaluation[J].New York:Oxford University Press.,1997.250-300.
[10]Wang G,Gertner G.,Parysow P,et al.Spatial prediction and uncertainty analysis of topographic factors for the revised soil losses Equation(RUSEL)[J].Soil Water Conservation.,2000,55(4):374-384
[11]柴杰,江青茵,曹志凯.RBF神经网络的函数逼近能力及其算法[J].模式识别与人工智能,2002,15(3):310-315.
[12]胡大伟,新民,许泉.基于ANN的土壤重金属分布和污染评价研究[J].长江流域资源与环境,2006,15(4):475-479.
[13]李启权,王昌全,岳天祥,等.不同输入方式下RBF神经网络对土壤性质的空间插值能力研究[J].土壤学报,2008,45(2):360-365.
[14]王旭东,邵惠鹤.RBF神经网络理论及其在控制中的应用[J].信息与控制,1997,26(4):272-284.
[15]李钰,孔凡国.基于模糊理论和遗传算法的神经网络权值优化[J].上海工程技术大学学报,2007,21(2):130-131.
[16]杨玉爱,何念祖,叶正钱.有机肥料对土壤锌、锰有效性的影像[J].土壤学报,1990,27(2):195-200.
[17]赵彦峰,史学正,黄标,等.工业型城乡交错区农业土壤Zn的空间分异及其影像因子探讨-以无锡市为例[J].土壤,2006,38(1):29-35.
[18]王凤花,张淑娟.精细农业田间信息采集关键技术的研究进展[J].农业机械学报,2008,39(5):111-113.
[19]刘杏梅,徐建明,章明奎,等.太湖流域土壤养分空间变异特征分析.以浙江省平湖市为例[J].浙江大学学报:农业与生命科学版,2003,29(1):76-82.
[20]Zhang S R,Sun B,Zhao Q G,et al.Temporal-spatial variability of soil organic carbon stocks in a rehabilitating ecosystem[J].Pedosphere,2004,14(4):501-508.
[21]Sun B,Zhou S L,Zhao Q G.Evaluation of spatial and temporal changes of soil quality based on geostatistical analysis in the hill region of subtropical China[J].Geoderma,2003,115:85-99.
[22]许宗林,苟曦,李昆,等.四川省耕地土壤养分分布特征与动态变化趋势探讨[J].西南农业学报,2008,21(3):718-723.
[23]刘斌,黄玉溢,陈桂芬.广西耕地土壤铜的含量及其影像因素[J].广西农业科学,2006,37(6):707-709.
[24]Tyler G,Pahlsson A M B,Bengtsson G,Baath E,Tranvik L.Heavy-metal ecology of terrestrial plants,microorganisms and invertebrates[J].Water,Air and Soil Pollution,1989,47:189-215.
[25]吕晓男,孟赐福,麻万诸.重金属与土壤环境质量及食物安全问题研究[J].中国生态农业学报,2007,15(2):197-200.
[26]张庆利,史学正,黄标,等.南京城郊蔬菜基地土壤有效态铅、锌、铜和镉的空间分异及其驱动因子研究[J].土壤,2005,37(1):41-47.
[27]石小华,杨联安,张蕾.土壤速效钾养分含量空间插值方法比较研究[J].水土保持学报,2006,20(2):68.
[28]周勇,聂艳.土地信息系统理论方法实践[M].北京:化学工业出版社,2005:113-115.
[29]谭继强,丁明柱.空间数据插值方法评价[J].测绘与空间地理信息,2004,4(27):11-14.
[30]邹汾生,董军义.空间数据建模中的内插方法讨论[J].中国钨业,2004,4(19):36-40.
[31]朱会义,刘述林,贾绍凤.自然地理要素空间插值的几个问题[J].地理研究,2004,4(23):425-426.
[32]R.B.Jackson.Geostatistical Patterns of soil Heterogeneity Around Individual Perennial Plants[J].Joural of Ecology,1993,81:683-692.
[33]黄杏元,劲松,汤勤.地理信息系统概论[M].北京:高等教育出版社,2001,93-103.
[34]吴立新,史文中.地理信息系统原理与算法[M].北京:科学出版社,2003.
[35]李新,程国栋,卢玲.空间内插方法比较[J].地球科学进展.2000,15(3):260-265.
[36]Burrough,Peter A.Principles of Geographic Information Systems for Land Resources Assessment[M].Oxford University Press,1986.
[37]肖玉,谢高地,安凯.土壤速效磷含量空间插值方法比较研究[J].中国生态农业学报,2003,11(1):56-58.
[38]Brodsky L,Vanek v,Bazalova M,atel.The differences In the interpolation methods for mapping spatial varability of soil property[J].Rostlinna-Vyroba,47(12):529-535.
[39]BecklerA,Fench B W,Chandler L D,et al.Chamcterization of western corn rootworm (Coleoptera:Chysomelidae)population dynamics in relation to landscape attributes[J].Agricultural&Forest Entomology,2004,6(2):129-104.
[40]王坷,Bailey,J.土壤钾素空间变异性和空间插值方法的比较研究[J].植物营养与肥料学学报,2000,6(3):318-322,344.
[41]邬伦,刘瑜,张晶,等.地理信息系统原理方法和应用[M].北京:科学出版社,2001:184-185.
[42]姚卫华.空间插值技术在地球化学图制作过程中的应用[A].长安大学硕士学位论文[C],2005.
[43]王心枢,李廷芳.北京平原地区土壤铜背景图的计算机绘制[J].环境科学学报,1985,4(7):28-36.
[44]沈思渊,徐琪,熊毅.太湖流域主要生态区中土壤组合的性态变异规律[J].土壤学报,1986,4(8):24-31.
[45]黄健全,高明全,胡雪涛.实用地质制图[M].北京:地质出版社,1998.
[46]Voltz M,Webster R A.Comparison of kriging,cubic splines and classification for predicting soil properties from sample information[J].Journal-of-Soil-Science,1990,41(3):473-490.
[47]Kastanek F J,Nielsen D R.Description of soil water characteristics using cubic spline interpolation[J].Soil Sci.Soc.Am.J,2001,65(2):279-283.
[48]阎洪.气候时空数据的样条插值与应用[J].地理与地理信息科学,2003,19(5):27-31.
[49]G.philip Roberston.Geostatistics in Ecology Interpolating with Known Variance[J].Ecology,1987,68(3):744-748.
[50]Richard E.Rossi.Geostatistical Tools for Modeling and Interpreting Ecological Spatial dependence[J].Ecological Monographs,1992,62(2):277-314.
[51]胡克林,李保国,林启美,等.农田土壤养分的空间变异性特征[J].农业工程学报,1999,15(3):33-38.
[52]自由路,李保国,胡克林.黄淮海平原土壤盐分及其组成的空间变异性特征研究[J].土壤肥料,1999,(3):22-26.
[53]Goovaerts P.Geostatistics for Natural Resources Evaluation[M].New York:Oxford University Press.1997.
[54]Wang G,Gertner G,Parysow P,et al.Spatial prediction and uncertainty analysis of topographic factors for the revised soil losses Equation(RUSEL)[J].J.Soil Water Conserv.,2000,55:374-384.
[55]Fotheringham A S,Charlton M,Brunsdon C.The geography of parameter space:an inverstigation of spatial non-stationarity[J].INT J Geographical Information Systems,1996,10(5):605-627.
[56]Journel A G.Modeling uncertainty and spatial dependence:Stochastic imaging[J].INT J Geographical Information Systems,1996,10(5):517-522.
[57]沈掌泉,周斌,孔繁胜.应用广义回归神经网络进行空间变异研究[J].土壤学报,2004,41(3):471-475.
[58]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版设,1995.
[59]杨海荣.基于RBF人工神经网络的空间插值[J].长沙交通学院学报,2005,22(1):68-71.
[60]李诈泳,邓新明.基于BP网络大气环境质量评价[J].干旱环境监测,1997,(3):11-13.
[61]熊忠华,陈琦,郑秀敏,等.基于遗传算法的人工神经网络大气环境评价[J].环境科学与技术.2005,28(4):83-94.
[62]C.L.Chang,S.L.Lo,S.L.Yu.Applying fuzzy theory and genetic algorithm to interpolate precipitation[J].Journal of Hydrology 2005,314:92-104.
[63]杨勇,刘敏,李霖.基于遗传算法的kriging空间分析及其在矿业中的应用[J].矿业研究与开发,2006,26(3):11-15.
[64]左国玉,刘问举,阮晓刚.基于遗传径向基神经网络的声音转换[J].中文信息学报,2004,1(18):78-83.
[65]刘永,张立毅.BP和RBF神经网络的实现及其性能比较[J].电子测量技术,2007,4(30):77-80
[66]J.Moody,C.J.Darken.Fast learning in networks of locally-tuned processing units[J].Neural Comput,1989(1):281-294.
[67]姜鹏飞,蔡之华.基于遗传算法和梯度下降的RBF神经网络组合训练方法[J].计算机应用,2007,27(2):366-372.
[68]Billing S A,Zheng G L.Radial Basis Function Netword Confinguration using Genetic Algorighms[J].NerualNetworks,1995,8(6):877-890.
[69]Vesin J M,Gruter R.Model Selection Using a Simplex Reproduction Genetic Algorithm[J].Signal Pro-cessing,1999,78(3):321-327.
[70]Gen M,Cheng R,Oren S S.Network Design Techniques Using Adapted Genetic Algorithms[J].Advances in Engineering Software,2001,32(9):731-744.
[71]Ludmila I.Kuncheva.Initalizing of an RBF network by genetic algorithm[J].Neurocomputing,1999,(14):373-288.
[72]Haralambos Sarimveis,Alex Alexandridis,et al.A new algorithm for delveloping dynamic radial basis function nerual Network models based on genetic algorithms[J].Computer&Chemical Engineering,2004,(28):209-217.
[73]Nan Qu,Lihua Wang,et al.Radial basis function networks combined with genetic algorithms applied to nondestructive determination of compound erythromycin ethylsuccinate power[J].Chemometrics and intelligent laboratory systems,2007,(7):8-15.
[74]张娟,陈杰,王珊珊.基于遗传算法和RBF网络的番茄生长模型[J].控制与决策,2005,6(20):682-690.
[75]傅伯杰,陈利顶,等.景观生态学原理及其应用[M].北京:科学出版社,2002.16-41.
[76]鲁如坤.土壤农业化学分析方法[M].北京:中国农业科技出版社,2000.
[77]侯景儒,黄竞先.地质统计学的理论与方法[M].北京:地质出版社,1990.
[78]邹汾生,董军义.空间数据建模中的内插方法的讨论[J].中国坞业,2004,19(4):36-40.
[79]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998.
[80]Mhasker H N,Micchelli C A.Approximation by superpositon of sigmoidal and Radial Rasis Functions[J].Advances in Applied Mathematics,1992,13:350-373.
[81]郭丽霞,康宝生.基于微种群遗传算法和RBF神经网络的散乱数据重建方法[J].计算机应用与软件,2008,25(1):33-35.
[82]Qu N,Wang L H,Zhu M C,et al.Radial basis function networks combined with genetic algorithms applied to nondestructive determination of compound erythromycin ethylsuccinate powder[J].Chemometrics and Intelligent Laboratory Systems.,2007,12(7):8-15
[83]Cambardella C A,Moorman T B,Novak J M,et al.Field-scale variability of soil.Properties in central low a soils[J].Soil Sol Sol Am J,1994,58:1501-1511.
[84]Paulin Coulibaly,Francois Anctil,Raomon A ravena,et al.Artificial neural network modeling of water table depth fluctions[J].water Resources Research,2001,37(4):885-896.
[85]周明,孙树栋.遗传算法的原理及应用[M].北京:国防工业出版社,1996.
[86]屈忠义,陈亚新,杨靖宇.人工神经网络在冻土水盐空间变异与条件模拟中的应用比较[J].农业工程学报,2007,7(23):48-52
[2]王学峰,章衡.土壤有机质的空间变异性[J].土壤,1995,27(2):85-89.
[3]王政权.地统计学及在生态学中的应用[M].北京:科学出版社,1999.
[4]华孟,于坚.土壤物理学[M].北京:北京农业大学出版社.1993,41-42.
[5]曾怀恩,黄声亭.基于Kriging方法的空间数据插值研究[J].测绘工程,2007,16(5):5-13.
[6]李明辉,何风华,申卫军,等.基于土壤生物空间异质性分析的空间土壤生态学研究[J].土壤,2005,37(4):375-381.
[7]何勇,张淑娟,方慧.基于人工神经网络的田间信息插值方法研究[J].农业工程学报,2004,20(3):120-123.
[8]岳天祥,刘纪远.多源信息融合数据模型[J].世界科技研究与发展,2001,23(5):1-4.
[9]Goovaerts EGeostatistics for Natural Resources Evaluation[J].New York:Oxford University Press.,1997.250-300.
[10]Wang G,Gertner G.,Parysow P,et al.Spatial prediction and uncertainty analysis of topographic factors for the revised soil losses Equation(RUSEL)[J].Soil Water Conservation.,2000,55(4):374-384
[11]柴杰,江青茵,曹志凯.RBF神经网络的函数逼近能力及其算法[J].模式识别与人工智能,2002,15(3):310-315.
[12]胡大伟,新民,许泉.基于ANN的土壤重金属分布和污染评价研究[J].长江流域资源与环境,2006,15(4):475-479.
[13]李启权,王昌全,岳天祥,等.不同输入方式下RBF神经网络对土壤性质的空间插值能力研究[J].土壤学报,2008,45(2):360-365.
[14]王旭东,邵惠鹤.RBF神经网络理论及其在控制中的应用[J].信息与控制,1997,26(4):272-284.
[15]李钰,孔凡国.基于模糊理论和遗传算法的神经网络权值优化[J].上海工程技术大学学报,2007,21(2):130-131.
[16]杨玉爱,何念祖,叶正钱.有机肥料对土壤锌、锰有效性的影像[J].土壤学报,1990,27(2):195-200.
[17]赵彦峰,史学正,黄标,等.工业型城乡交错区农业土壤Zn的空间分异及其影像因子探讨-以无锡市为例[J].土壤,2006,38(1):29-35.
[18]王凤花,张淑娟.精细农业田间信息采集关键技术的研究进展[J].农业机械学报,2008,39(5):111-113.
[19]刘杏梅,徐建明,章明奎,等.太湖流域土壤养分空间变异特征分析.以浙江省平湖市为例[J].浙江大学学报:农业与生命科学版,2003,29(1):76-82.
[20]Zhang S R,Sun B,Zhao Q G,et al.Temporal-spatial variability of soil organic carbon stocks in a rehabilitating ecosystem[J].Pedosphere,2004,14(4):501-508.
[21]Sun B,Zhou S L,Zhao Q G.Evaluation of spatial and temporal changes of soil quality based on geostatistical analysis in the hill region of subtropical China[J].Geoderma,2003,115:85-99.
[22]许宗林,苟曦,李昆,等.四川省耕地土壤养分分布特征与动态变化趋势探讨[J].西南农业学报,2008,21(3):718-723.
[23]刘斌,黄玉溢,陈桂芬.广西耕地土壤铜的含量及其影像因素[J].广西农业科学,2006,37(6):707-709.
[24]Tyler G,Pahlsson A M B,Bengtsson G,Baath E,Tranvik L.Heavy-metal ecology of terrestrial plants,microorganisms and invertebrates[J].Water,Air and Soil Pollution,1989,47:189-215.
[25]吕晓男,孟赐福,麻万诸.重金属与土壤环境质量及食物安全问题研究[J].中国生态农业学报,2007,15(2):197-200.
[26]张庆利,史学正,黄标,等.南京城郊蔬菜基地土壤有效态铅、锌、铜和镉的空间分异及其驱动因子研究[J].土壤,2005,37(1):41-47.
[27]石小华,杨联安,张蕾.土壤速效钾养分含量空间插值方法比较研究[J].水土保持学报,2006,20(2):68.
[28]周勇,聂艳.土地信息系统理论方法实践[M].北京:化学工业出版社,2005:113-115.
[29]谭继强,丁明柱.空间数据插值方法评价[J].测绘与空间地理信息,2004,4(27):11-14.
[30]邹汾生,董军义.空间数据建模中的内插方法讨论[J].中国钨业,2004,4(19):36-40.
[31]朱会义,刘述林,贾绍凤.自然地理要素空间插值的几个问题[J].地理研究,2004,4(23):425-426.
[32]R.B.Jackson.Geostatistical Patterns of soil Heterogeneity Around Individual Perennial Plants[J].Joural of Ecology,1993,81:683-692.
[33]黄杏元,劲松,汤勤.地理信息系统概论[M].北京:高等教育出版社,2001,93-103.
[34]吴立新,史文中.地理信息系统原理与算法[M].北京:科学出版社,2003.
[35]李新,程国栋,卢玲.空间内插方法比较[J].地球科学进展.2000,15(3):260-265.
[36]Burrough,Peter A.Principles of Geographic Information Systems for Land Resources Assessment[M].Oxford University Press,1986.
[37]肖玉,谢高地,安凯.土壤速效磷含量空间插值方法比较研究[J].中国生态农业学报,2003,11(1):56-58.
[38]Brodsky L,Vanek v,Bazalova M,atel.The differences In the interpolation methods for mapping spatial varability of soil property[J].Rostlinna-Vyroba,47(12):529-535.
[39]BecklerA,Fench B W,Chandler L D,et al.Chamcterization of western corn rootworm (Coleoptera:Chysomelidae)population dynamics in relation to landscape attributes[J].Agricultural&Forest Entomology,2004,6(2):129-104.
[40]王坷,Bailey,J.土壤钾素空间变异性和空间插值方法的比较研究[J].植物营养与肥料学学报,2000,6(3):318-322,344.
[41]邬伦,刘瑜,张晶,等.地理信息系统原理方法和应用[M].北京:科学出版社,2001:184-185.
[42]姚卫华.空间插值技术在地球化学图制作过程中的应用[A].长安大学硕士学位论文[C],2005.
[43]王心枢,李廷芳.北京平原地区土壤铜背景图的计算机绘制[J].环境科学学报,1985,4(7):28-36.
[44]沈思渊,徐琪,熊毅.太湖流域主要生态区中土壤组合的性态变异规律[J].土壤学报,1986,4(8):24-31.
[45]黄健全,高明全,胡雪涛.实用地质制图[M].北京:地质出版社,1998.
[46]Voltz M,Webster R A.Comparison of kriging,cubic splines and classification for predicting soil properties from sample information[J].Journal-of-Soil-Science,1990,41(3):473-490.
[47]Kastanek F J,Nielsen D R.Description of soil water characteristics using cubic spline interpolation[J].Soil Sci.Soc.Am.J,2001,65(2):279-283.
[48]阎洪.气候时空数据的样条插值与应用[J].地理与地理信息科学,2003,19(5):27-31.
[49]G.philip Roberston.Geostatistics in Ecology Interpolating with Known Variance[J].Ecology,1987,68(3):744-748.
[50]Richard E.Rossi.Geostatistical Tools for Modeling and Interpreting Ecological Spatial dependence[J].Ecological Monographs,1992,62(2):277-314.
[51]胡克林,李保国,林启美,等.农田土壤养分的空间变异性特征[J].农业工程学报,1999,15(3):33-38.
[52]自由路,李保国,胡克林.黄淮海平原土壤盐分及其组成的空间变异性特征研究[J].土壤肥料,1999,(3):22-26.
[53]Goovaerts P.Geostatistics for Natural Resources Evaluation[M].New York:Oxford University Press.1997.
[54]Wang G,Gertner G,Parysow P,et al.Spatial prediction and uncertainty analysis of topographic factors for the revised soil losses Equation(RUSEL)[J].J.Soil Water Conserv.,2000,55:374-384.
[55]Fotheringham A S,Charlton M,Brunsdon C.The geography of parameter space:an inverstigation of spatial non-stationarity[J].INT J Geographical Information Systems,1996,10(5):605-627.
[56]Journel A G.Modeling uncertainty and spatial dependence:Stochastic imaging[J].INT J Geographical Information Systems,1996,10(5):517-522.
[57]沈掌泉,周斌,孔繁胜.应用广义回归神经网络进行空间变异研究[J].土壤学报,2004,41(3):471-475.
[58]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版设,1995.
[59]杨海荣.基于RBF人工神经网络的空间插值[J].长沙交通学院学报,2005,22(1):68-71.
[60]李诈泳,邓新明.基于BP网络大气环境质量评价[J].干旱环境监测,1997,(3):11-13.
[61]熊忠华,陈琦,郑秀敏,等.基于遗传算法的人工神经网络大气环境评价[J].环境科学与技术.2005,28(4):83-94.
[62]C.L.Chang,S.L.Lo,S.L.Yu.Applying fuzzy theory and genetic algorithm to interpolate precipitation[J].Journal of Hydrology 2005,314:92-104.
[63]杨勇,刘敏,李霖.基于遗传算法的kriging空间分析及其在矿业中的应用[J].矿业研究与开发,2006,26(3):11-15.
[64]左国玉,刘问举,阮晓刚.基于遗传径向基神经网络的声音转换[J].中文信息学报,2004,1(18):78-83.
[65]刘永,张立毅.BP和RBF神经网络的实现及其性能比较[J].电子测量技术,2007,4(30):77-80
[66]J.Moody,C.J.Darken.Fast learning in networks of locally-tuned processing units[J].Neural Comput,1989(1):281-294.
[67]姜鹏飞,蔡之华.基于遗传算法和梯度下降的RBF神经网络组合训练方法[J].计算机应用,2007,27(2):366-372.
[68]Billing S A,Zheng G L.Radial Basis Function Netword Confinguration using Genetic Algorighms[J].NerualNetworks,1995,8(6):877-890.
[69]Vesin J M,Gruter R.Model Selection Using a Simplex Reproduction Genetic Algorithm[J].Signal Pro-cessing,1999,78(3):321-327.
[70]Gen M,Cheng R,Oren S S.Network Design Techniques Using Adapted Genetic Algorithms[J].Advances in Engineering Software,2001,32(9):731-744.
[71]Ludmila I.Kuncheva.Initalizing of an RBF network by genetic algorithm[J].Neurocomputing,1999,(14):373-288.
[72]Haralambos Sarimveis,Alex Alexandridis,et al.A new algorithm for delveloping dynamic radial basis function nerual Network models based on genetic algorithms[J].Computer&Chemical Engineering,2004,(28):209-217.
[73]Nan Qu,Lihua Wang,et al.Radial basis function networks combined with genetic algorithms applied to nondestructive determination of compound erythromycin ethylsuccinate power[J].Chemometrics and intelligent laboratory systems,2007,(7):8-15.
[74]张娟,陈杰,王珊珊.基于遗传算法和RBF网络的番茄生长模型[J].控制与决策,2005,6(20):682-690.
[75]傅伯杰,陈利顶,等.景观生态学原理及其应用[M].北京:科学出版社,2002.16-41.
[76]鲁如坤.土壤农业化学分析方法[M].北京:中国农业科技出版社,2000.
[77]侯景儒,黄竞先.地质统计学的理论与方法[M].北京:地质出版社,1990.
[78]邹汾生,董军义.空间数据建模中的内插方法的讨论[J].中国坞业,2004,19(4):36-40.
[79]张乃尧,阎平凡.神经网络与模糊控制[M].北京:清华大学出版社,1998.
[80]Mhasker H N,Micchelli C A.Approximation by superpositon of sigmoidal and Radial Rasis Functions[J].Advances in Applied Mathematics,1992,13:350-373.
[81]郭丽霞,康宝生.基于微种群遗传算法和RBF神经网络的散乱数据重建方法[J].计算机应用与软件,2008,25(1):33-35.
[82]Qu N,Wang L H,Zhu M C,et al.Radial basis function networks combined with genetic algorithms applied to nondestructive determination of compound erythromycin ethylsuccinate powder[J].Chemometrics and Intelligent Laboratory Systems.,2007,12(7):8-15
[83]Cambardella C A,Moorman T B,Novak J M,et al.Field-scale variability of soil.Properties in central low a soils[J].Soil Sol Sol Am J,1994,58:1501-1511.
[84]Paulin Coulibaly,Francois Anctil,Raomon A ravena,et al.Artificial neural network modeling of water table depth fluctions[J].water Resources Research,2001,37(4):885-896.
[85]周明,孙树栋.遗传算法的原理及应用[M].北京:国防工业出版社,1996.
[86]屈忠义,陈亚新,杨靖宇.人工神经网络在冻土水盐空间变异与条件模拟中的应用比较[J].农业工程学报,2007,7(23):48-52
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |