Investigation of Remote Sensing Imageries for Identifying Soil Texture Classes Using Classification Methods

Abstract

In this paper, the usefulness of remote sensing imageries for identifying soil texture classes was evaluated by classification trees under one-against-one (OAO), one-against-all, and all-together schemes. A set of normalized difference vegetation indices (NDVIs) was obtained from cloud-free Landsat images over a small mountainous watershed. Terrain indicators (elevation, slope, and topographic wetness index) were derived from a digital elevation map (30 m). Models with different input parameters (purely NDVI, purely topography and stratum, and NDVI plus topography and stratum) were developed. Overall accuracy, kappa statistic, receiver operating characteristics (ROC), and the area under ROC curve (AUC) were applied to evaluate the classification accuracy. Results showed that the classification strategy had great effects on the outputs. The models under OAO scheme performed better with averaged overall accuracy, kappa statistic, and AUC of 0.949, 0.821, and 0.87, respectively. Among them, the model with NDVI plus topography and stratum performed best with overall accuracy, kappa statistic, and AUC of 0.975, 0.918, and 0.907, respectively. Similar performances were obtained by the model with purely NDVI and the model with purely topography and stratum. More samples of clay and sand were identified with the help of NDVI. The contributions of NDVI to explain soil texture class variability were 144%, 0%, and 14% for clay, loam, and sand, respectively. NDVI measured during the stem and leaf growth period of sweet potatoes was the optimum period for identifying soil texture classes in the watershed. Our findings will provide valuable information for assessing the quality of ecological environment using remote sensing data.