
Tecnologias disponíveis para a observação da Terra oferecem uma grande gama de informações sobre componentes ambientais que, por estarem relacionadas com a formação dos solos, podem ser usadas como variáveis preditoras no Mapeamento Digital de Solos (MDS). No entanto, modelos com um grande número de preditores, bem como a existência de multicolinearidade entre os dados, podem ser ineficazes no mapeamento de classes e propriedades do solo. O objetivo deste estudo foi empregar a Análise de Componentes Principais (ACP) visando a selecionar e diminuir o número de preditores na regressão logística múltipla multinomial (RLMM) utilizada no mapeamento de classes de solos. Nove covariáveis ambientais, ligadas ao fator de formação relevo, foram derivadas de um Modelo Digital de Elevação e denominadas variáveis originais, estas foram submetidas à ACP e transformadas em Componentes Principais (CP). As RLMM foram desenvolvidas utilizando-se atributos de terreno e as CP como variáveis explicativas. O mapa de solos gerado a partir de três CP (65,6% da variância original) obteve um índice kappa de 37,3%, inferior aos 48,5% alcançado pelo mapa de solos gerado a partir de todas as nove variáveis originais.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.
multivariate statistical analysis, soil survey, S, pedometric, Agriculture (General), levantamento de solos, Agriculture, pedometria, análise estatística multivariada, S1-972
multivariate statistical analysis, soil survey, S, pedometric, Agriculture (General), levantamento de solos, Agriculture, pedometria, análise estatística multivariada, S1-972
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
