基于贝叶斯最大熵的多因子空间属性预测新方法

为了在空间数据预测时充分利用样点和环境数据，提出了在贝叶斯最大熵方法框架下将经典地统计方法与环境相关法结果融合、利用多源数进行空间预测的新方法；并以湖北省京山县土壤有机质含量为例，验证该方法的可行性．以由数字高程模型（digital elevation model，DEM）生成的各种相关地形因子作为环境数据，并分为密集建模集J（330个样点）和稀疏建模集II（100个样点），分别用普通克里金法和本文所提方法进行土壤有机质空间预测，用预留的50个样点进行精度分析．结果表明：本文所提方法的预测精度较普通克里金法的高，其I和II2组建模集精度分别提高了10．95％和22．72％，特别在样点较稀疏时，...

Full description

Saved in:
Bibliographic Details
Published in浙江大学学报（农业与生命科学版） Vol. 39; no. 6; pp. 636 - 644
Main Author 杨勇 张楚天 贺立源
Format Journal Article
LanguageChinese
Published 华中农业大学资源与环境学院，农业部长江中下游耕地保育重点实验室，武汉 430070 2013
Subjects
克里金法
土壤
环境相关法
空间属性预测
贝叶斯最大熵
环境相关法
Bayesian maximum entropy
贝叶斯最大熵
environmental correlation
空间属性预测
soil
克里金法
spatial prediction
Kriging
土壤
Online AccessGet full text
ISSN1008-9209
DOI10.3785/j.issn.1008-9209.2013.05.231

Cover

More Information
Summary:为了在空间数据预测时充分利用样点和环境数据，提出了在贝叶斯最大熵方法框架下将经典地统计方法与环境相关法结果融合、利用多源数进行空间预测的新方法；并以湖北省京山县土壤有机质含量为例，验证该方法的可行性．以由数字高程模型（digital elevation model，DEM）生成的各种相关地形因子作为环境数据，并分为密集建模集J（330个样点）和稀疏建模集II（100个样点），分别用普通克里金法和本文所提方法进行土壤有机质空间预测，用预留的50个样点进行精度分析．结果表明：本文所提方法的预测精度较普通克里金法的高，其I和II2组建模集精度分别提高了10．95％和22．72％，特别在样点较稀疏时，在相关环境因子的辅助下，精度提高幅度更大．说明将经典地统计方法与环境相关法结果相融合的多因子空间属性预测方法使预测结果既能体现样点的空间自相关，又能体现被预测属性与其他属性间的相关性．
Bibliography:33-1247/S
The spatial distributions of soil properties （e. g. , organic matter and heavy metal content） are vital to soil quality evaluation and regional environment assessment. Currently, the spatial distribution of soil properties is usually predicted with classical geostatistics or environmental correlation. These two methods are different in theory. Geostatistics is based on spatial correlation of sampling points. However, it contains some deficiencies, such as the lack of effective utilization of environmental information, the smoothing effect of predicted results, difficult to meet the assumption of single point to muhipoint Gaussian distribution etc. On the other hand, the theoretical basis of environmental correlation is based on the relationship between soil and environment, but it ignores the spatial correlation among sampling points, These two methods complement each other. Thus, it is very important to study how to integrate these two methods, so that the spatial correlation among sampling points a
ISSN:1008-9209
DOI:10.3785/j.issn.1008-9209.2013.05.231