Comparison of MLC and FCM Techniques with Satellite Imagery in A Part of Narmada River Basin of Madhya Pradesh, India

Arun Mondal, Deepak Khare, Sananda Kundu

Abstract


Landuse and land cover are most important part which is linked with the environment and climate in various ways. This is also important for the modeling of greenhouse gas emissions, carbon balance etc., and is important for understanding the landscape features. The main objective of the present work is to reduce uncertainties in the landuse and land cover pattern. Remote sensing technique is extremely important for the classification purposes by empirical observation and algorithms. In case of present study, a part of Narmada river basin was taken where change in the landuse and landcover was assessed from the Landsat images of the year 2011 with two classification techniques of Maximum Likelihood Classification (MLC) and Fuzzy C-Mean (FCM). The major landuse classes are water body, built-up, vegetation, agricultural land and fallow land. The image has been digitally classified by both MLC and FCM algorithms which have been validated by the accuracy assessment process. The overall accuracy achieved by the FCM was about 84% while with MLC it was about 79%. The Survey of India toposheet was used as the base map for the purpose of geo-correction. FCM was found to be more accurate in comparison to MLC because of its soft classification technique.


Keywords


Landuse, Narmada River Basin, MLC, FCM, Accuracy

Full Text: PDF

Refbacks

  • 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)