Open Access Open Access  Restricted Access Subscription Access

doi:10.3808/jei.201700368
Copyright © 2017 ISEIS. All rights reserved

Application of Object Oriented Image Classification and Markov Chain Modeling for Land Use and Land Cover Change Analysis

S. S. Paul1,2, J. Li1,3*, R. Wheate4, and Y. Li1

  1. WZU-UNBC Joint Research Institute of Ecology and Environment, Wenzhou University (WZU), Wenzhou, Zhejiang Province, P. R. China
  2. Faculty of Land and Food Systems, University of British Columbia (UBC), 2357 Main Mall, Vancouver, BC V6T 1Z4, Canada
  3. Environmental Engineering Program, University of Northern British Columbia (UNBC), Prince George, BC V2N 4Z9, Canada
  4. Geography Program, University of Northern British Columbia (UNBC), Prince George, BC V2N 4Z9, Canada

*Corresponding author. Tel.: +1 250 960 6397; fax: +1 250 960 5845. E-mail address: Jianbing.Li@unbc.ca (J. Li).

Abstract


Object oriented image classification (OOIC) and neural network aided Markov Chain (MC) modeling tools were used to map and predict land use and land cover (LULC) changes. A case study in the Kiskatinaw River Watershed (KRW) of Canada was presented. With an overall classification accuracy of 90.45%, the multi-temporal Landsat satellite images of KRW were analyzed for 11 selected LULC types. It was found that KRW experienced a significant wetland depletion along with a change in forest cover types from 1984 to 2010. The vulnerability of LULC change in different parts of KRW was predicted through MC modeling based on the obtained transition probability, and the results indicated slight LULC changes from 2010 with a wetland depletion of 67.89 km2. In summary, the proposed methods generated valuable results for informed LULC management and hold the potential to be applied to other watersheds.

Keywords: IDRISI selva, land use and land cover (LULC) change, landsat imagery, Markov Chain model, object oriented image classification (OOIC), remote sensing


Full Text:

PDF

Supplementary Files:

Refbacks

  • There are currently no refbacks.