Principal components as predictor variables in digital mapping of soil classes

被引：10

作者：

ten Caten, Alexandre ^{[1
]}

Diniz Dalmolin, Ricardo Simao ^{[2
]}

Pedron, Fabricio de Araujo ^{[2
]}

Mendonca Santos, Maria de Lourdes ^{[3
]}

机构：

[1] IFF, BR-98130000 Julio De Castilhos, RS, Brazil

[2] Univ Fed Santa Maria, CCR, Dept Solos, BR-97119900 Santa Maria, RS, Brazil

[3] Ctr Nacl Pesquisa Solos, Rio De Janeiro, Brazil

来源：

CIENCIA RURAL | 2011年 / 41卷 / 07期

关键词：

pedometric; multivariate statistical analysis; soil survey; MULTIPLE LOGISTIC-REGRESSION;

D O I：

10.1590/S0103-84782011000700011

中图分类号：

S3 [农学（农艺学）];

学科分类号：

0901 ;

摘要：

Available technologies for Earth observation offer a wide range of predictors relevant to Digital Soil Mapping (DSM). However, models with a large number of predictors, as well as, the existence of multicollinearity among the data, may be ineffective in the mapping of classes and soil properties. The aim of this study was to use the Principal Component Analysis (PCA) to reduce the number of predictors in the multinomial logistic regression (MLR) used in soil mapping. Nine environmental covariates, related to the relief factor of soil formation, were derived from a digital elevation model and named the original variables, which were submitted to PCA and transformed into principal components (PC). The MLR were developed using the terrain attributes and the PC as explanatory variables. The soil map generated from three PC (65.6% of the original variance) had a kappa index of 37.3%, lower than the 48.5% achieved by the soil map generated from all nine original variables.

引用

页码：1170 / 1176

页数：7

共 15 条

[1]

[Anonymous], SIST BRAS CLASS SOL

[2]

Chatterjee S., 2006, Regression Analysis by Example, V4th, P317

[3] Methods for digital soil mapping using a geographical information system [J].