共查询到19条相似文献，搜索用时 187 毫秒
1.
样点密度对土壤有机质空间预测结果的影响——以河南封丘县土壤为例 总被引：5，自引：1，他引：5
以河南省封丘县表层土壤有机质含量为例,探讨土壤样点密度对区域化土壤变量描述性统计特征、半方差函数理论模型拟合效果、普通Kriging插值预测结果的精度与表现目标变量空间变异的能力等多方面的影响。研究结果表明,样点数量从5000个大幅减少至20个,研究区表层样品有机质含量均值未发生显著变化。当土壤样点≥625个时,表层土壤有机质含量半方差函数模型具有较好的拟合效果,可以通过Kriging插值手段获得精度较高且对目标变量空间变异特征解释能力较强的预测结果;当土壤样点≤78个时,半方差函数模型理论上无法通过拟合获得,通过普通Kriging插值手段不能获得研究区表层土壤有机质含量理想的预测结果。 相似文献
2.
土壤空间预测与数字化制图的精度受土壤样点规模、采样策略、预测模型选择、目标区域地貌与成土环境复杂程度、协变量数据质量等多种因素共同制约。选择河南省为研究区,基于9种土壤样点规模、5种采样方法,应用5种最具代表性的机器学习(Machinelearning,ML)算法对耕地表层土壤pH实施空间预测与数字化制图,用以对比分析不同样点规模与采样方法对ML模型的性能表现及土壤pH预测精度的影响。结果表明：(1)当研究区土壤样点规模从200个经由400个、800个、1 200个、1 600上升至2 000个时,无论使用何种采样方法,所有ML模型的性能表现与预测精度均呈快速上升的总体趋势;当样点规模达到并超过2 000个时,大多数ML性能表现及预测精度趋于稳定,表明2 000个土壤样点可能是这些ML模型预测研究区耕地表层土壤pH的样点规模阈值。(2)5种ML模型性能表现及其土壤pH预测精度存在明显差距,基于树结构的随机森林(Random forests,RF)和Cubist表现最好,无论使用哪种采样方法,这两种模型预测结果的决定系数(R2)均可稳定在0.75～0.80之间、RM... 相似文献
3.
基于随机森林模型的耕地表层土壤有机质含量空间预测——以河南省辉县市为例 总被引：5，自引：0，他引：5
耕地表层土壤有机质含量与作物生长发育密切相关,掌握土壤有机质空间分布对土壤肥力定向培养和农业生产指导具有重要意义。本研究以河南省辉县市5 922个耕地资源管理单元图斑中心点为基础数据,并分别按8∶2、7∶3、6∶4的比例随机划分训练数据集和验证数据集,以土壤类型作为辅助定性变量,利用随机森林模型模拟预测土壤有机质含量与自然环境变量(坡向、曲率、坡度、高程、土壤质地、归一化植被指数NDVI)、社会经济因子(排水能力、灌溉状况)之间的复杂非线性关系。结果表明:①当训练集与检验集中样点数量的比例为8∶2时,对应的随机森林模型总体上预测精度较高;②选用80%基础数据作为训练集时,预测得到的地图与已有图件相比,相关性达到0.859;③当用303个实地数据验证时,预测值与实测值的皮尔逊相关系数为0.595。通过对影响因子的重要性排序,发现土壤质地是研究区农用地表层土壤有机质含量的最重要影响因子。因此,随机森林模型作为机器学习和数据挖掘的有效方法,能较好地模拟输入变量与有机质含量之间的关系,预测图件与实际情况相符,但对有机质含量精细的差异不能很好体现。 相似文献
4.
提升土壤属性空间预测精度对实现农田精准施肥和保护生态环境具有重要意义。利用河北省滦平县采集的1 773个样点耕地表层(0～20cm)土壤有机质(SOM)及其地理环境数据,通过逐步回归分析方法筛选出最优环境变量;基于其中1 426个农田样点分别建立多元线性回归(Multiple Linear Regression,MLR)、随机森林(Random Forest,RF)、贝叶斯正则化神经网络(Bayesian regularization neural network,BRNNBP)以及与普通克里格(OK)整合模型(MLR-OK、RF-OK和BRNNBP-OK)预测SOM空间分布,以其余347个样点数据为测试集检验分析不同模型预测精度,并对模型残差进行半方差函数和空间自相关分析以评价模型拟合效果。结果表明,研究区耕地表层土壤SOM处在8.62～35.64 g·kg-1变化区间,变异系数为20.26%,属中等程度空间变异;SOM高值区主要分布在东北及东南海拔较高地区,低值区多分布在西南及中部河谷地区;海拔、坡度和年均温度与SOM关系密切(P<0.001);整合模型... 相似文献
5.
基于回归克里格和遥感的紫色土区土壤有机质含量空间预测 总被引：4，自引：1，他引：3
精确预测紫色土区土壤有机质含量的空间分布,对于指导紫色土区农业生产和培肥土壤具有重要意义。以杜家沟小流域为研究区,以遥感影像作辅助变量,采用回归克里格法,预测土壤有机质含量的空间分布,并与参照方法的预测精度进行比较。结果表明:(1)Landsat ETM+影像的波段2和波段5是土壤有机质含量多元线性回归预测的最佳辅助变量,回归残差的最优半方差函数模型为球状模型,模型的拟合精度较高;(2)土壤有机质含量呈由沟谷逐渐向坡顶递减的趋势,空间变异的细节信息表达较好;(3)回归克里格法在验证点的预测值与实测值的拟合能力更好,预测结果更倾向于无偏的,MAE、RMSE和R2均优于参照方法。因此,回归克里格法是紫色土区土壤有机质含量高精度空间预测的有效方法。 相似文献
6.
【目的】以江西省泰和县为研究区域,揭示县域尺度耕地土壤有机质(SOM)的空间分布规律。【方法】设计覆盖整个泰和县耕地的采样网络,采集361个表层(0～20 cm)土壤样品。使用普通克里格插值法探究研究区耕地土壤有机质含量的空间分布特征,利用随机森林模型结合经典统计方法探究泰和县耕地土壤有机质空间分异的主要影响因素。【结果】研究区耕地土壤有机质含量均值为31.05 g kg-1,处于较丰富水平,表明泰和县耕地土壤肥力水平较好。泰和县耕地土壤有机质具有中等程度的空间自相关性,具有中部低、东西高的空间分布特征。秸秆还田和海拔是耕地土壤有机质含量的主要影响因子,解释率为56.37%和18.73%。土壤pH、成土母质、施肥量和灌溉能力对土壤有机质含量也具有显著影响,解释率分别为9.66%、9.47%、6.76%和5.45%。【结论】采取秸秆还田、合理施用石灰和完善排水设施等田间管理措施可以有效提高耕地土壤有机质含量,改善土壤保肥固碳能力,对促进农业可持续发展,助力实施国家“碳达峰”和“碳中和”战略具有重要价值和意义。 相似文献
7.
以蓝田县西北部农耕区2012年1 114份土壤有机质、碱解氮、有效磷、速效钾4个指标为基础,利用地理信息系统和地统计学相结合的方法,在对协变量个数控制的前提下,通过交叉检验系数和精度提高系数,探索协同克里格插值法对各土壤养分空间分布预测精度的影响。结果表明:各土壤养分空间分布不均匀,土壤养分存在中等变异性;利用增加协同变量方法,依据协变量之间相关性强弱控制协变量进入模型的次序对各土壤养分指标进行协同克里格插值,能提高预测精度,当协变量个数达到3时,各养分指标精度提高分别为有机质0.353%,碱解氮1.114%,有效磷1.088%,速效钾0.646%。研究结果较为准确地预测了样区4个养分指标的空间分布特征,结合土壤类型及土壤施肥管理方法,探讨了土壤养分空间分布特征的原因。 相似文献
8.
针对丘陵红壤区铜冶炼厂周围水稻土污染区（1.40km^2）,在景观尺度上,采用协同克里格方法,研究了影响表层土壤Cu含量空间分布预测的辅助因子。基于空间自相关性、间距、长轴方位角以及各种预测误差,评价了辅助变量（包括秸秆全Cu含量StrawCu、籽粒全Cu含量GrainCu、土壤全Cd含量Cd、土壤pH、土壤有机质OM、高程H）对表层土壤Cu含量分布预测精度的影响。结果表明,单辅助变量的协同克里格预测值与实测值相关系数的大小顺序为Cu/Cd〉Cu/H〉Cu/StrawCu〉Cu/GrainCu〉Cu/OM、Cu/pH,而多辅助变量协同克里格预测的相关系数大小顺序为Cu（/Cd,StrawCu）〉Cu（/Cd,StrawCu,H）〉Cu（/Cd,StrawCu,GrainCu）〉Cu/（StrawCu,GrainCu）〉Cu（/Cd,H）。与土壤全Cu含量的普通克里格插值精度相比,利用表层土壤全Cd含量、水稻秸秆全Cu含量、高程作为辅助变量与水稻土表层全Cu含量进行协同克里格插值可以显著提高预测精度;但水稻籽粒全Cu含量作为辅助变量对预测精度影响不显著;而土壤有机质含量和土壤pH作为辅助变量反而降低了预测精度。在对表层土壤全Cu含量分布的多辅助变量协同克里格预测中,表层土壤全Cd含量和水稻秸秆全Cu含量的影响最大,其次是高程,水稻籽粒全Cu含量不能提高对表层土壤全Cu含量分布的预测精度。 相似文献
9.
《土壤通报》2015,(6):1289-1298
将湖南省划分为洞庭湖平原区,湘东、湘中丘陵、中低山区,湘南丘陵、中低山区和湘西北中低山区四个地貌景观区,以高密度的耕地表层土壤有机质数据为基础,分析地貌和样点数对插值精度的影响。研究表明:湖南省耕地表层土壤有机质平均含量从高到低依次为:湘南丘陵、中低山区湘东、湘中丘陵、中低山区湘西北中低山区洞庭湖平原区。湖南省耕地表层土壤有机质变异系数在31.23%~37.55%之间,属于中等变异水平;基底效应在12.3%~50.0%之间,其中湘东、湘中丘陵、中低山区和湘南丘陵、中低山区耕地表层土壤有机质呈现强烈的空间自相关,洞庭湖平原区和湘西北中低山区具有中等空间自相关。相同采样密度下,湖南省耕地表层土壤有机质的克里格插值精度从高到低依次为:洞庭湖平原区湘西北中低山区湘东、湘中丘陵、中低山区湘南丘陵空间自相关、中低山区。四个区的耕地表层土壤有机质NRMSE均随着样点数的增加呈现出递减的趋势,表明插值精度逐渐提升。 相似文献
10.
潮土区土壤有机质含量的趋势演变研究——以禹城市为例 总被引：10，自引：1，他引：10
通过分析山东省禹城市100个采样点1980年和2003年耕层土壤的有机质含量,研究了土壤有机质的时空变异特征,探讨了潮土区有机质含量的变化,形成了研究区1980年和2003年有机质含量空间分布图及1980~2003年有机质含量的空间变化图。分析了研究区有机质含量增加的原因。研究结果表明,该市目前土壤有机质含量平均为14.68g kg-1,比1980年的6.0g kg-1增加了8.68 g kg-1,年均提高0.38g kg-1。土壤表层含盐量的降低为土壤养分含量提高提供了条件。 相似文献
11.
基于地形属性使用回归, 克里格和人工神经网络方法估算饱和导水率空间分布 总被引：6，自引：0，他引：6
Several methods,including stepwise regression,ordinary kriging,cokriging,kriging with external drift,kriging with varying local means,regression-kriging,ordinary artificial neural networks,and kriging combined with artificial neural networks,were compared to predict spatial variation of saturated hydraulic conductivity from environmental covariates.All methods except ordinary kriging allow for inclusion of secondary variables.The secondary spatial information used was terrain attributes including elevation,slope gradient,slope aspect,profile curvature and contour curvature.A multiple jackknifing procedure was used as a validation method.Root mean square error (RMSE) and mean absolute error (MAE) were used as the validation indices,with the mean RMSE and mean MAE used to judge the prediction quality.Prediction performance by ordinary kriging was poor,indicating that prediction of saturated hydraulic conductivity can be improved by incorporating ancillary data such as terrain variables.Kriging combined with artificial neural networks performed best.These prediction models made better use of ancillary information in predicting saturated hydraulic conductivity compared with the competing models.The combination of geostatistical predictors with neural computing techniques offers more capability for incorporating ancillary information in predictive soil mapping.There is great potential for further research and development of hybrid methods for digital soil mapping. 相似文献
12.
Stratification of a region based on soil map delineations followed by within-stratum interpolation is sometimes used to combine soil maps and spatial interpolation. However, not all delineations are equally suitable to subdivide an area into precisely located mutually exclusive strata. This paper proposes a flow-path to characterize the nature of soil map delineations and a methodology to integrate the properties of map delineations into ordinary kriging.Four types of delineations were distinguished based on three criteria: the nature of transition (discontinuous or gradual), the mapping accuracy, and the structure of the within-unit spatial variation. For each type of delineation the ordinary kriging algorithm was modified to integrate its properties in the interpolation.As a test case, the sand content of the topsoil in the province of West-Flanders (Belgium) was mapped, using independent test data for validation. Inside the mapping units and at delineations identified as gradual transitions, our procedure, termed ordinary kriging integrating properties of map delineations (OKPD) , performed similarly to stratified ordinary kriging (SOK). However, close to the delineations identified as inaccurately mapped discontinuities the mean square prediction error of OKPD was 0.64 times that of SOK. Moreover, near these delineations, the prediction variance was largely underestimated by SOK (relative variance = 5.1), whereas OKPD produced a more realistic value (relative variance = 1.5). 相似文献
13.
基于三种空间预测模型的海南岛土壤有机质空间分布研究 总被引：9，自引：0，他引：9
为探索适合热带地形复杂区土壤有机质(SOM)含量的空间预测方法,以海南岛为研究区域,结合地形因子、归一化植被指数、土壤类型、土地利用类型变量,选用普通克里格法(OK)、回归克里格法(RK)、随机森林模型(RF)三种方法对训练集128个样点SOM含量的空间分布规律进行预测,并通过验证集32个验证点比较了三种方法的预测精度。结果表明:(1)0~5 cm土层三种方法的平均预测误差(ME)均接近于0,从均方根预测误差(RMSE)来看,RF(0.8867)RK(0.910 4)OK(0.9641),从决定系数(R~2)来看,RF(0.214 1)RK(0.171 5)OK(0.070 8)。综合以上三个参数,该土层最优拟合模型为RF。同理得出0~20、20~40、40~60 cm土层的最优拟合模型分别为RF、RF、OK。RK和RF能够更好地描述SOM含量局部变异信息;(2)四个土层SOM含量的均值分别为19.67、15.89、10.30、8.07 g kg~(-1),呈现出西南、东北高,西部、东南沿海地区低的空间分布趋势。 相似文献
14.
Nematodes are indicators of soil quality and soil health. Knowledge of the relationships between nematode-based soil quality indices and environmental properties is beneficial for assessing environmental threats on soil biota. This study evaluated the spatial distribution of nematode-based soil quality indices in a 23-ha heavy metal-polluted nature reserve using geostatistical methods. We expected that a selection of abiotic soil properties (pH and moisture, clay, organic matter, cadmium (Cd), and zinc (Zn) contents) could explain a significant portion of the spatial variation of the indices and that regression kriging could more accurately model their spatial distribution than ordinary kriging. A stratified simple random sampling scheme was used to select 80 locations where soil samples were taken to extract nematodes and derive the indices. The area had a distinct gradient in soil properties with Cd and Zn content ranging from 0.07 to 68.9 and 5.3 to 1329 mg kg-1, respectively. Linear regression models were fitted to describe the relationships between the indices and soil properties. By also modelling the spatial correlation structure of regression residuals using spherical semivariograms, regression kriging was used to produce maps of the indices. The regression models explained between 21% and 44% of the total original variance in the indices. Soil pH was a significant explanatory variable in almost all cases, while heavy metal conent had a remarkably low effect. In some cases, the regression residuals had spatial structure. Independent validation indicated that in all cases, regression kriging performed slightly better because of having lower values of the root mean square prediction error and a mean prediction error closer to zero than ordinary kriging. This study showed the importance of soil properties in explaining the spatial distribution of biological soil quality indices in ecological risk assessment. 相似文献
15.
《国际水土保持研究(英文)》2022,10(3):470-486
This study was performed to examine the separate and simultaneous influence of predictive models’ choice alongside sample ratios selection in soil organic matter (SOM). The research was carried out in northern Morocco, characterized by relatively cold weather and diverse geological conditions. The dataset herein used accounted for 1591 soil samples, which were randomly split into the following ratios: 10% (～150 sample ratio), 20% (～250 sample ratio), 35% (～450 sample ratio), 50% (～600 sample ratio) and 95% (～1200 sample ratio). Models herein involved were ordinary kriging (OK), regression kriging (RK), multiple linear regression (MLR), random forest (RF), quantile regression forest (QRF), Gaussian process regression (GPR) and an ensemble model. The findings in the study showed that the accuracy of SOM prediction is sensitive to both predictive models and sample ratios. OK combined with 95% sample ratio performed equally to RF in conjunction with all the sample ratios, as the latter did not show much sensitivity to sample ratios. ANOVA results revealed that RF with a ～10% sample ratio could also be optimum for predicting SOM in the study area. In conclusion, the findings herein reported could be instrumental for producing cost-effective detailed and accurate spatial estimation of SOM in other sites. Furthermore, they could serve as a baseline study for future research in the region or elsewhere. Therefore, we recommend conducting series of simulation of all possible combinations between various predictive models and sample ratios as a preliminary step in soil organic matter prediction. 相似文献
16.
海伦市耕层土壤有机质含量空间预测方法研究 总被引：4，自引：1，他引：4
有机质含量是表征土壤肥力质量的重要属性,其空间分布模式对于施肥等耕作管理措施的推荐具有重要的指导意义。本文以我国黑土区黑龙江省海伦市为研究区域,在土壤采样点数量较有限的情况下,分别采用普通克里格、反距离权重、遥感反演和基于土壤学专业知识四种方法对耕层土壤有机质含量进行了空间预测。结果表明:四种方法表征的海伦耕地土壤有机质含量空间分布特征具有相似性,即由东北向西南方向递减。空间预测精度从高到低依次为反距离权重、普通克里格、基于土壤学专业知识和遥感反演法;而在有机质的局部变异细节表达方面,从高到低为遥感反演、基于土壤学专业知识、反距离权重和普通克里格法。四种方法中仅遥感反演法预测结果的极差范围较宽,普通克里格法则存在明显的平滑效应,而综合比较结果则表明,最合适的方法是基于土壤学专业知识的方法。 相似文献
17.
Geospatial measurements of ancillary sensor data, such as bulk soil electrical conductivity or remotely sensed imagery data, are commonly used to characterize spatial variation in soil or crop properties. Geostatistical techniques like kriging with external drift or regression kriging are often used to calibrate geospatial sensor data to specific soil or crop properties. More traditional statistical methods such as ordinary linear regression models are also commonly used. Unfortunately, some soil scientists see these as competing and unrelated modeling approaches and are unaware of their relationship. In this article we review the connection between the ordinary linear regression model and the more comprehensive geostatistical mixed linear model and describe when and under what conditions ordinary linear regression models represent valid spatial prediction models. The formulas for the ordinary linear regression model parameter estimates and best linear unbiased predictions are derived from the geostatistical mixed linear model under two different residual error assumptions; i.e., strictly uncorrelated (SU) residuals and effectively uncorrelated (EU) residuals. The theoretically optimal (best linear unbiased) and computable (linear unbiased) predictions and variance estimates derived under the EU error assumption are examined in detail. Statistical tests for detecting spatial correlation in LR model residuals are also reviewed, in addition to three LR model validation tests derived from classical linear modeling theory. Two case studies are presented that highlight and demonstrate the various parameter estimation, response variable prediction and model validation techniques discussed in this article. 相似文献
18.
开垦对草甸土有机碳的影响 总被引：14，自引：0，他引：14
本文利用经典统计学和地统计学相结合的方法,选取科尔沁沙地东南缘草甸土两块10×10m的样地为例,分析了草地开垦8a后的耕地耕作层土壤有机碳含量和空间分布格局的变化,结果表明:草地与耕地表层(0～10cm)土壤有机碳含量差异不显著,草地亚表层(10～20cm)土壤有机碳含量低于耕地(p<0.05);草地与耕地表层和亚表层土壤有机碳空间分布格局具有明显差异,表现为草地的表层和亚表层的结构异质性分别大于耕地,分数维小于耕地,空间依赖性强于耕地,空间分布格局的破碎程度弱于耕地。耕地表层与亚表层土壤有机碳含量差异不显著(p<0.05),但空间结构特征和空间分布格局存在明显的差异;而草地表层与亚表层土壤有机碳含量差异显著(p<0.05),但空间结构特征和空间分布格局比较相似。因此,开垦不仅影响草甸土有机碳含量的高低,而且影响其空间结构特征和分布格局。这对进一步了解草地开垦对土壤有机碳及全球碳循环和气候变化的影响具有重要意义。 相似文献
19.
基于环境变量的渭干河-库车河绿洲土壤盐分空间分布 总被引：5，自引：4，他引：1
土壤属性的数字制图对精准农业生产和环境保护治理至关重要。为了在大尺度上尽可能精确的监测土壤盐分空间变异性,该文使用普通克里格(ordinary kriging,OK)、地理加权回归(geographically weighted regression,GWR)和随机森林(random forest,RF)方法,结合地形、土壤理化性质和遥感影像数据等16个环境辅助变量,绘制渭干河-库车河绿洲表层土壤盐分分布图。基于决定系数(R^2)、均方根误差(RMSE)和平均绝对误差(MAE)验证模型精度。结果表明:不同方法预测的盐分分布趋势没有显著差异,大体上从研究区的西北向东南部方向增加;结合辅助变量的不同预测方法中,RF方法预测精度最高,R^2为0.74,RMSE和MAE分别为9.07和7.90 mS/cm,说明该模型可以有效地对区域尺度的土壤盐分进行定量估算;RF方法对电导率(electric conductivity,EC)低于2 mS/cm时预测精度最高,RMSE为3.96 mS/cm,很好的削弱了植被覆盖对电导率EC的影响。 相似文献