Spatial Interpolation of Soil Nutrients Based on BP Neural Network

以广东省增城市为研究对象,采集了全市内200个土壤样点,利用 BP神经网络插值方法对研究区土壤的氮和磷进行空间插值预测,将插值结果与土壤样点实测值进行对比,得到预测数据的误差均方根。结果表明, BP神经网络的插值精度比克里格高,在样点较少的情况下,BP神经网络的插值结果克服了克里格插值方法的平滑效应。 BP神经网络对插值的样本数据的分布类型没有要求,比传统插值方法有更强的泛化能力,是一种可替代的插值方法。     

农业用地土壤重金属样本点数据精化方法——以北京市顺义区为例

样本点空间分布是样点数据检测评价和挖掘分析的关键因素。以北京市顺义区为例，研发了一种农业用地土壤重金属样本点数据精化方法：首先构建样本点均匀变异指数和均匀因子离散图来共同检测样本点数据均匀性，进一步将样本点类型划分为均匀样本点、聚集样本点和稀疏样本点并确定其数量；其次删除聚集样本点，基于研究区历史数据加密稀疏样本点；最后基于地理空间样本点均匀变异指数、特征空间偏离指数和插值误差共同评价数据精化效果。结果表明，研究区样本点的均匀变异指数为0.429，存在一个聚集样本点和一个稀疏样本点，空间偏离指数为0.327，空间属性插值误差为6.538；冗余数据精化后进行均匀性检测没有发现聚集样本点和稀疏样本点，均匀变异指数下降到0.406，特征空间偏离指数微弱下降，空间属性插值误差下降到6.357。研究表明该方法可以对提高采样数据的均匀性和代表性提供理论指导，可以服务于土壤污染防治行动计划（土十条）、土壤污染状况详查等，为更加精确研究土壤空间信息变化提供一定的基础条件。     

复杂地形下风场插值与林火蔓延模拟应用研究

山区地形复杂多变,风场随地形而变化,作为影响林火蔓延的主要因素,风场数据的准确程度将直接影响山地林火蔓延预测的结果。选择同时考虑地形起伏变化和距离作为主要因子的风场插值方法,设计并开发实现风场插值功能,并与基于空间距离的传统反距离权重(IDW)插值方法进行了比较研究。通过实验验证表明,所实现的基于地形起伏的风场插值方法对山区风场的模拟更接近实际;利用该方法的插值结果输入林火蔓延模拟,模拟的火场形状与实际范围具有更高的相似度。     

基于ArcGIS的近10年黑龙江省旬平均气温插值与建库

以ArcGIS Geostatictical Analyst为支撑,利用高程、坡向数据作为辅助,采用协同克里格（Cokriging）方法,对黑龙江省近10年旬平均气温进行空间插值,36个旬平均气温插值结果均误差、平均标准差和均方根标准差的平均值分别为0.0024℃、0.0006和1.124。基于全部旬平均气温插值结果及其相关数据,建立旬平均气温Geodatabase空间数据库,为气温变化监测、农业区划和实现千亿斤粮食的作物估产等研究奠定基础。     

杨树人工林立木生长量空间相关规律研究

为了使立木胸径测量装置得以用于全林蓄积变化量的动态监测,针对林地内树木代表性样点抽样方法问题,本文提出运用林地立木空间变异函数结合克里格插值的方法进行目标样点抽选.通过对林地实测数据进行分析验证,结果表明该方法有效;通过对立木空间变异函数分析,得出海拔方向是影响立木生长的主要因子,沿海拔方向胸径空间变程是240m,树高变程为360m,说明立木生长量个体间有很好的空间相关性;同时,经过对小于变程的不同参考样点距离进行克里格插值效果验证,得出0.3倍变程为最佳参考样点距离,能使树高预测误差小于2m,胸径预测误差小于1个径级.     

空间插值技术在冬小麦单产预测中的应用

在对冬小麦单产农业气象预测方法研究中,将空间插值技术应用到单产预测中,即对降水量、温度等农业气象因子进行空间插值。不仅将单产预测区域的气象因子从点数据插值成面数据,而且解决了单产预测中农业气象模型空间外推问题,从而提高了冬小麦单产预测的精度,具有一定的实用性。     

基于GIS的传统插值方法比较研究——以山东省多年平均气温为例

利用GIS软件空间内插方法,采用7种不同的传统插值方法对山东省多年平均气温进行内插,生成内插表面模型并进行误差分析。结果表明,以误差均值为标准,趋势面插值方法较优,自然领域插值方法误差最大,同时,传统内插方法无法加入高程影响因子。     

一类加权有理插值样条曲面及局部约束控制

目的 构造一类新的基于函数值与偏导数值的加权有理插值样条曲面,讨论该样条曲面的相关性质并分析曲面的局部约束控制。方法 一方面,先从x方向构造有理三次插值样条,再从y方向构造二元有理插值样条曲面;另一方面,按相反次序构造另一个二元有理插值样条曲面;最后将两种插值曲面加权得到一类新的有理插值样条曲面。结果 讨论插值曲面的性质,包括基函数、边界性质、积分加权系数的性质以及误差估计。通过选择合适的参数和加权系数,在不改变插值数据的前提下实现对插值区域内的局部约束控制。结论 实验结果表明,新的加权有理插值样条曲面具有良好的约束控制性质。     

基于农业气象模型的农作物单产估算——以湖北省中稻为例

先对气象数据进行空间插值处理,然后通过作物单产区划选择代表性的模拟县,根据模拟县历年作物单产的变化趋势得到作物波动产量,并对波动产量和气象因子进行相关性分析,提取与作物单产相关性最大的气象因子,建立一元线性或多元回归方程,估算作物产量,将估算结果与实际统计结果进行比较。结果表明,作物单产估算结果与统计数据的误差为-7．74％～9．80％。     

Spatial Interpolation and Sample Size Optimization for Soil Copper （Cu） Investigation in Cropland Soil at County Scale Using Cokriging

Knowledge on spatial distribution and sampling size optimization of soil copper （Cu） could lay solid foundations for environmetal quality survey of agricultural soils at county scale. In this investigation, cokriging method was used to conduct the interpolation of Cu concentraiton in cropland soil in Shuangliu County, Sichuan Province, China. Based on the original 623 physicochmically measured soil samples, 560, 498, and 432 sub-samples were randomly selected as target variable and soil organic matter （SOM） of the whole original samples as auxiliary variable. Interpolation results using Cokriging under different sampling numbers were evaluated for their applicability in estimating the spatial distribution of soil Cu at county sacle. The results showed that the root mean square error （RMSE） produced by Cokriging decreased from 0.9 to 7.77%, correlation coefficient between the predicted values and the measured increased from 1.76 to 9.76% in comparison with the ordinary Kriging under the corresponding sample sizes. The prediction accuracy using Cokriging was still higher than original 623 data using ordinary Kriging even as sample size reduced 10%, and their interpolation maps were highly in agreement. Therefore, Cokriging was proven to be a more accurate and economic method which could provide more information and benefit for the studies on spatial distribution of soil pollutants at county scale.     

县域农田土壤铜含量的协同克里格插值及采样数量优化

 【目的】研究县域农田土壤铜含量的空间分布和采样数量,为农田土壤环境质量调查提供帮助。【方法】采用协同克里格方法,以初始的623个土壤铜含量数据及在此基础上随机抽取的560、498和432个数据为目标变量,并以初始的623个土壤有机质含量数据为辅助变量,对四川省双流县农田土壤铜含量进行插值分析,并对不同样点数量下协同克里格法在县域尺度农田土壤铜含量空间分布研究中的适用性进行评价。【结果】相同取样数量下,协同克里格法的均方根误差相对于普通克里格法可降低0.9%～7.77%,预测值和实测值之间的相关系数可提高1.76%至9.76%。利用协同克里格法,在土壤铜含量数据量缩减10%的情况下,其估值精度仍高于初始的623个土壤铜含量数据的普通克里格估值,且二者的分布图具有高度相似性。【结论】协同克里格作为一种更为精确和经济的方法,可为县域尺度农田土壤重金属含量的空间分布研究提供更多的信息和帮助。     

Improved Prediction and Reduction of Sampling Density for Soil Salinity by Different Geostatistical Methods

The spatial estimation for soil properties was improved and sampling intensities also decreased in terms of incorporated auxiliary data. In this study, kriging and two interpolation methods were proven well to estimate auxiliary variables： cokriging and regression-kriging, and using the salinity data from the first two stages as auxiliary variables, the methods both improved the interpolation of soil salinity in coastal saline land. The prediction accuracy of the three methods was observed under different sampling density of the target variable by comparison with another group of 80 validation sample points, from which the root-mean-square error （RMSE） and correlation coefficient （r） between the predicted and measured values were calculated. The results showed, with the help of auxiliary data, whatever the sample size of the target variable may be, cokriging and regression-kriging performed better than ordinary kriging. Moreover, regression-kriging produced on average more accurate predictions than cokriging. Compared with the kriging results, cokriging improved the estimations by reducing RMSE from 23.3 to 29% and increasing r from 16.6 to 25.5%, regression-kriging improved the estimations by reducing RMSE from 25 to 41.5% and increasing r from 16.8 to 27.2%. Therefore, regression-kriging shows promise for improved prediction for soil salinity and reduction of soil sampling intensity considerably while maintaining high prediction accuracy. Moreover, in regression-kriging, the regression model can have any form, such as generalized linear models, non-linear models or tree-based models, which provide a possibility to include more ancillary variables.     

样点数对县域土壤养分空间变异特征评价的影响

以广东省阳西县测土配方施肥耕地地力调查数据为基础,应用地统计学和GIS空间分析技术,对耕层土壤pH、有机质、全氮、有效磷和速效钾进行空间插值质量研究。结果表明:(1)土壤养分变异系数的顺序为速效钾>速效磷>有机质>全氮>pH,插值误差随土壤养分空间变异系数增大而增加。(2)插值精度随着插值样点数的增加而不断提高,土壤养分的预测值与实测值的相关系数逐渐增加。采样密度相同时,土壤养分的标准均方根误差(NRMSE)值由大到小的变化顺序是速效钾>有效磷>全氮>有机质>pH值。(3)对阳西县土壤养分空间变异情况进行评价时,土壤pH值和全氮采样时应以30～60 hm2耕地为一个采样单元;土壤有机质采样时应以20～30 hm2耕地为一个采样单元;土壤有效磷和速效钾采样时应最大以20 hm2耕地为一个采样单元。     

Soil Test,Aerial Image and Yield Data as Inputs for Site-specific Fertility and Hybrid Management Under Maize

Several potential sources of information exist to support precision management of crop inputs. This study evaluated soil test data, bare-soil remote sensing imagery and yield monitor information for their potential contributions to precision management of maize (Zea mays L.). Data were collected from five farmer-managed fields in Central New York in 1999, 2000, and 2001. Geostatistical techniques were used to analyze the spatial structure of soil fertility (pH, P, K, NO₃ and organic matter content) and yield variables (yield, hybrid response and N fertilization response), while remote sensing imagery was processed using principal component analysis. Geographic information system (GIS) spatial data processing and correlation analyses were used to evaluate relationships in the data. Organic matter content, pH, P, and K were highly consistent over time and showed high to moderate levels of spatial autocorrelation, suggesting that grid soil sampling at 2.5–5.5ha scale may be used as a basis for defining fertility management zones. Soil nitrate levels were strongly influenced by seasonal weather conditions and showed low potential for site-specific N management. Aerial image data were correlated to soil organic matter content and in some cases to yield, mainly through the effect of drainage patterns. Aerial image data were not well correlated with soil fertility indicators, and therefore were not useful for defining fertility management zones. Yield response to hybrid selection and nitrogen fertilization rates were highly variable among years, and showed little justification for site-specific management. In conclusion, we recommend grid-based management of lime, P, and K, but no justification existed within our limited study area for site-specific N or hybrid management.     

Integrating remote sensing information with crop model to monitor wheat growth and yield based on simulation zone partitioning

Research into crop growth models at the spatial scale is of great significance for evaluating crop growth, predicting grain yield and studying global climate change. Coupling spatial remote sensing (RS) data can effectively promote the simulation of growth models at spatial scales. However, the integration of RS data and crop models to produce a coupled model based on pixel by pixel requires a large amount of calculations. Simulation zone partitioning is used to separate and cluster the large area into a few relatively uniform zones. Then, the growth model can run on the basis of these units. This method both reflects spatial heterogeneity and avoids repeated simulations of regions with similar attributes, improving the simulation efficiency. In this study, simulation partitioning was performed using soil nutrient indices (organic matter content, total nitrogen content and available potassium content) and corresponding spatial characteristics of wheat growth, as indicated by RS data. A coupled model, integrating RS information and the WheatGrow model, using vegetation indices as the coupling parameters (based on the Particle Swarm Optimization algorithm and PROSAIL model), was developed. The aim was to realize accurate prediction of wheat growth parameters and grain yield at the spatial scale. Good zone partitions were obtained by partitioning with the spatial combination of soil nutrient indices and the wheat canopy vegetation index, calculated during the main growth (jointing, heading and filling) stages. The variation coefficients of each index within individual simulation sub-zones were much smaller than those of the indices across the whole area. An analysis of variance showed that the indices were significantly different between the simulation sub-zones, which indicated that appropriate simulated sub-zones had been defined. The minimum root mean square error of the leaf area index, leaf nitrogen accumulation and yield between the predicted values and the values simulated by the coupled model were 0.92, 1.12 g m^?2, and 409.70 kg ha^?1, respectively, which were obtained when the soil-adjusted vegetation index was used as a partitioning zone and assimilating parameter. These results demonstrated that the coupled model of the crop model and RS data, based on the simulation sub-zones had a good prediction accuracy. The results provide important technical support for increasing model efficiency, when crop models need to be applied at the spatial scale.     

罗江县农田土壤全氮协同克里格插值和采样数量优化研究

[目的]研究县域土壤全氮含量的空间分布和采样数量,为紫色土丘陵区采样提供参考。[方法]利用协同克里格法,以初始的1 777个土壤全氮含量数据为随机抽取的数据,分别随机抽取1 599、1 421和1 243个数据为目标变量,并以初始的1 777个土壤有机质数据为辅助变量,对四川省罗江县土壤全氮含量进行插值分析,从而利用协同克里格法对县域尺度下农田土壤全氮含量在不同样点数量下空间分布中的适用性进行评价。[结果]在相同取样数量下,全氮协同克里格法的均方根误差相对于普通克里格法降低0.019 6%～0.072 5%,预测值和实测值之间的相关系数提高0.69%～0.90%。利用协同克里格法,土壤全氮含量数据在缩减30%情况下,其估值精度高于1 777个样点下的普通克里格估值,且二者的分布图都具有较高的拟合度。[结论]协同克里格法是一种经济、精准的方法,可为县域土壤养分含量的空间分布提供基础信息。     

基于Kriging插值和BP神经网络结合的粮仓温度场预测模型研究及实现

针对复杂仓储环境中粮情温度单点预测效果不理想、现有温度场建模难以满足工程应用需求等问题,基于温度场理论,结合分布式测温系统结构,提出了基于粮堆温度数据的温度场预测模型。该模型基于BP神经网络,利用粮仓内离散测温点数据预测对应点的未来温度数据;再采用Kriging插值法进行空间插值,利用已知位置的温度值估计出未知点的温度值,进而建立温度场的预测模型。仿真测试结果表明,温度预测的平均绝对百分误差为1.253 5%,均方根误差为0.106 0,预测效果良好。采用Kriging插值法进行温度点的插值,其平均绝对百分误差为9.470 0%,均方根误差为0.865 1。对比于传统的粮堆温度单点预测算法,该模型能够更好地反映粮仓内温度场变化趋势以及温度分布的情况,为粮仓管理者提供更好的数据支持,实现辅助决策。该模型可扩展性强,能够适用于各种仓储现场。     

克拉玛依市玛依湖区土壤有机质空间异质性分析

目的 研究克拉玛依市东部生态屏障的水源地玛依湖区土壤有机质的空间分布规律, 为湖区的生态环境保护提供科学依据和数据支撑。方法 以玛依湖区为研究对象,通过野外采样和室内分析,利用趋势分析法、反距离权重插值法、空间自相关法和半变异函数法分析玛依湖区不同土层深度土壤有机质的空间分布规律。结果 趋势法分析表明,玛依湖区土壤有机质含量在0~20、20~40、40~60和60~80 cm土层的变化速率存在差异,整体趋势为土壤有机质含量南北方向呈增加趋势、东西方向呈减少趋势。反距离权重插值法(IDW)研究表明,玛依湖区不同土层土壤有机质水平分布差异较大,局部地区土壤有机质含量存在明显的垂直分布特征,土壤有机质含量变化趋势同趋势法分析结果高度一致,整体表现为土壤有机质含量南北方向呈增加趋势、东西方向呈减少趋势。空间自相关法研究表明,0~20、20~40、40~60和60~80 cm土层的Moran指数分别为0.1643、0.1236、0.1955和0.2461,均在空间上呈现出显著正相关;4个土层的Z值分别为3.1510、2.5934、3.5903和4.6355,底层(40~60和60~80 cm)的土壤有机质空间正相关较显著、空间聚集程度最高,表层(0~20和20~40 cm)空间相关性不显著、空间聚集程度较低。半变异函数分析法表明,底层(40~60和60~80 cm)土层的块金效应分别为0.427和0.420,说明土壤有机质具有一定的空间相关性;表层(0~20和20~40 cm)土层的块金效应分别为0.033和0.045,土壤有机质的空间相关性较弱。结论 不同土层土壤有机质含量水平差异较大,南北方向呈增加趋势,东西方向呈减少趋势,局部地区存在明显的垂直分布特征。土壤有机质在表层(0~20和20~40 cm)空间相关性不显著,空间聚集程度较低;在底层(40~60和60~80 cm)空间相关性较显著,空间聚集程度较高。土壤有机质空间异质性受土壤类型、土壤质地、外围植被类型以及湖区面积变化的影响较大;在湖区外围生态屏障建设时,防护林树种、种植深度、种植密度的选择应当结合土壤有机质含量的空间分布状况进行。     

Sampling Strategies for Mapping ‘Within-field’ Variability in the Dry Matter Yield and Mineral Nutrient Status of Forage Grass Crops in Cool Temperate Climes

In the absence of suitable technology to measure and map the dry matter (DM) yield distributions of forage grass crops within individual fields, a manual procedure of yield mapping has been developed. Samples of herbage are collected just prior to each silage harvest from known grid points within a field, and sward DM yields at each point are predicted from the mineral composition of the herbage, using empirical mathematical models. Yield maps (and maps of sward nutrient status) are then produced by kriging interpolation between the point data. To make the most efficient use of time and resources, however, sampling intensity needs to be kept to the absolute minimum necessary for interpolation purposes. The aim of the present study was to examine the spatial variability in sward DM yield and mineral nutrient status in a large grass silage field under a three-cut system, and devise optimal sampling strategies for mapping the distributions of these parameters at each cut. Herbage samples were collected from the field, prior to each harvest, at 25 m intervals in a regular rectangular grid to provide databases of herbage nutrient contents and DM yields. Different data combinations were abstracted from these databases for comparison purposes, and ordinary kriging used to produce interpolated maps of DM yield and sward N, P, K and S statuses. The results suggested that a sampling density of just seven samples per hectare was adequate for estimating the true population means of sward DM yield and sward N, P, K, and S statuses. For mapping purposes, it was found that the best compromise between interpolation accuracy and sampling efficiency was to collect herbage samples in a 35.4 m×35.4 m equilateral triangular sampling pattern.