To Map and Characterized the Sub-Pixel Classification of Soil Properties using Remote Sensing And GIS

A Subpixel spectral analytical process was used to classify the soil in LISS -IV data using thematic mapper imagery in India. The sub-pixel process enabled the detection of soil and geology in mixed pixels. two hundred pixels were field verified for each soil species to independently measure errors of omission and commission. The cypress total accuracy was 89 percent and the geology total accuracy was 91 percent field investigations revealed that both soil and geology were successfully classified when they occurred both as pure stands and when mixed with other soil species and water. In a comparison with traditional classification technique (iso-data maximum likelihood and minimum distance) the Subpixel classification of soil and geology yielded improved results. Large area of wetland where cypress was heavily mixed with other tree species were correctly classified by the Subpixel process and not classified by traditional classifiers.