Delineation of Soil Variability Using Geostatistics and Fuzzy Clustering Analyses of Hyperspectral Data

Abstract

Abstract A soil map is one of the key data layers for developing a robust global model and evaluating land quality and use. A current soil map produced by conventional soil survey is the major source of soil information. However, such a map may not provide the desired accuracy in terms of scale and cartographic quality as a digital format for geographic information system (GIS) modeling applications. This study was designed to introduce and test the procedures for improving the objectivity and accuracy in the delineation of soil patterns with the use of hyperspectral imagery. These hyperspectral data were analyzed through different models including the linear mixture model, block‐kriging interpolation, and fuzzy‐ c ‐means (FCM) algorithms. Hyperspectral remote sensing data, having very good spectral and spatial resolution, were used for quantifying soil patterns and conditions. A linear spectral mixing model was effectively used not only for reducing dimensionality but also for removing vegetation effects for studying soil patterns from a single soil map layer derived from hyperspectral remote sensing data. Block kriging interpolation based on a semivariogram fitted with the isotropic exponential model represented soil patterns very well beyond the limitation of the size of pixel. Fuzzy‐ c ‐means clustering analysis showed clear membership patterns and segmented soil patterns effectively, although this is not a soil map in the conventional sense.