Soil type classification and mapping using hyperspectral remote sensing data

Hyperspectral remote sensing has been widely used for mapping of soil, its classification and also its texture description. It is beneficial in urban and rural management. The present work reports the study regarding classification soil analysis using Support Vector Machine (SVM). Hyperion Hyperspectral satellite data with 10nm fine spectral resolution of Phulambri region of Aurangabad district of Maharashtra (India) which lies between 20° 06´ N latitude and 75° 25´ E longitude was used for soil classification. Gaussian Radial Basis Function (RBF) kernel of SVM was used to extract five various soils types and achieved overall accuracy of 71.18% and with Kappa Value of 0.57 having sufficient training samples. It was found that the soil of the region may be classified in five categories. The maximum area (51 %) was covered by the brown sandy soil, whereas the minimum (.02%) by gray clay soil. The result is of great significance for soil analysis of very complex region without reduction of dimensionality in satellite data.