设为首页  |   加入收藏
引用本文:
【打印本页】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
过刊浏览    高级检索
本文已被:浏览 36次   下载 0  
分享到: 微信 更多
基于特征变量与SVROK算法的湿地土壤有机质空间变异特征
陈思明1,2, 王 宁2, 秦艳芳1, 张红月1
1.闽江学院海洋学院;2.福建农林大学林学院
摘要:
选取适宜变量与有效方法有助于揭示河口湿地土壤有机质的空间异质性,对维护湿地生态平衡和全球碳循环的具有重要作用。以福州市闽江河口湿地为研究区,采用逐步回归分析与主成分分析法筛选显著的特征变量,运用支持向量机回归克里格法(SVROK)分析湿地土壤有机质的空间异质性,并与神经网络克里格法(BPNNOK)、回归克里格法(RK)进行比较。结果表明:归一化植被指数(NDVI)、比值植被指数(RVI)、土壤水分指数(PDI)、汇流累积量(FA)及沉积物移动指数(STI)与土壤有机质含量关系密切,其逐步回归模型的判定系数R2为0.446,显著性概率值P<0.0001,可转换为3个独立的主成分作为模型的自变量。研究区土壤有机质的空间变异主要受结构性因素影响,呈现出“北低南高”的空间格局,采用SVROK模型的预测精度更高,可较好的体现河口湿地土壤有机质的空间异质特征。该研究可为同类区域的土壤有机质空间特征研究提供方法支撑。
关键词:  土壤有机质  逐步回归分析法  主成分分析法  支持向量机克里格法  河口湿地
DOI:
分类号:S156.8
基金项目:福州市科技计划项目(2018-S-111);福建省教育厅中青年教师教育科研项(JT180407)
Spatial variability of soil organic matter content in estuary wetland, southeast China based on characteristic variables and SVROK.
chen siming1,2, Wang ning2, Qin Yanfang1, Zhang hongyue1
1.Ocean college, Minjiang University;2.. College of Forestry, Fujian Agriculture and Forestry University
Abstract:
Choosing the suitable auxiliary and effective method is the prerequisite to accurately predict the spatial distribution of soil organic matter (SOM) in estuarine wetland. In order to achieve this, a case study was conducted in the Minjiang Estuary Wetland of Fuzhou, China. A total of 23 environmental factors were extracted by ArcGIS Geostatistical analyst and remote sensing image analysis technique. Then, stepwise regression model and principal component analysis were used to select the characteristic variables. At last a hybrid model of the support vector machine-ordinary Kriging (SVROK) was proposed to analyze the spatial variability of soil organic matter, and compared with BP neural network-ordinary Kriging (BPNNOK) and regression Kriging (RK). The results show that: normalized vegetation index (NDVI), ratio vegetation index (RVI), perpendicular Drought Index (PDI), flow accumulation (FA) and sediment movement index (SMI) were significantly correlated with soli organic matter content, which had the higher coefficient of determination (R2 = 0.446) and the significant probability value(P < 0.0001). Three principal components which explained at least 94% of the total variance, were extracted from these environmental factors by principal component analysis and used as characteristic variables. The spatial variability of soil organic matter was affected by structural factors, showing a trend of " lower in the north and higher in the south". Compared with RK and BPNNOK, The SVROK had the highest prediction accuracy, and more accurately reflected the spatial variability of soil organic matter. This method can provide a methodological support for the study of spatial variability of soil organic matter in the same region.
Key words:  Soil organic matter  stepwise regression  principal component analysis  extreme learning machine kriging  Estuary Wetland

您是第2907477位访问者
版权所有 © 《土壤》编辑部
本系统由北京勤云科技发展有限公司设计   京ICP备09084417号