Hyperspectral Remote Sensing in Characterizing Soil Salinity Severity using SVM Technique - A Case Study of Alluvial Plains

Justin George K., Suresh Kumar


Hyperspectral remote sensing is widely used for analyzing and estimating the severity of soil salinity in arid and semi-arid regions, throughout the world. The present study is an attempt to map the various soil salinity severity classes using different hyperspectral indices generated using EO-1 Hyperion data and Support Vector Machine (SVM) method, in the Mathura region of Indo-Gangetic plain of India. Various hyperspectral indices such as Soil Adjusted Vegetation Index (SAVI), Desertification Soil Index (DSI), Salinity Index (SI) and Normalized Difference Water Index (NDWI) were chosen, generated and effectively used for characterizing and mapping soil salinity severity. Salt infestation in the study area was categorized into four classes of normal, slight, moderate, high soil salinity. Hyperspectral indices helped in identification of various features like vegetation, waterlogged area and soil areas under various classes of soil salinity. The salinity index and desertification soil indices were found to respond well to varying degrees of soil salinity. The SVM technique generated soil salinity map with overall classification accuracy of 78.13 percent, with a kappa statistic of 0.71. The results indicated highest accuracy in high soil salinity class in comparison to other classes, attaining producers and users accuracies of 85.71% and 90.0% respectively. Slight saline class showed poor producers and users accuracy. The result showed high accuracy for mapping soil salinity severity with machine learning classifier like SVM using various indices generated from hyperspectral remote sensing data. These generated images can be effectively used in planning of various management practices and effective reclamation measures of salt affected soils.


Hyperion Hyperspectral Indices; Indo-Gangetic Plains; Salt Salinity Severity; Support Vector Machine (SVM)

Full Text: PDF


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

*2016 Journal Impact Factor was established by dividing the number of articles published in 2014 and 2015 with the number of times they are cited in 2016 based on Google Scholar, Google Search and the Microsoft Academic Search. If ‘A’ is the total number of articles published in 2014 and 2015, and ‘B’ is the number of times these articles were cited in indexed publications during 2016 then, journal impact factor = A/B. To know More: (http://en.wikipedia.org/wiki/Impact_factor)