|
|
|
Overview |
Urban Sprawl |
Fringe Area Development |
Urban Agglomeration |
Emerging Technologies |
Relevant Links
Accuracy of Land Suitability Modeling using Spectral Characterization
Sutat Dansagoonpon
STAR program, Asian Institute of Technology (AIT)
P.O.Box 4 Klong Luang, Pathumthani 12120, Thailand
Email: st027123@ait.ac.th
Nitin K Tripathi*, and Roberto S. Clemente**
* STAR program, Asian Institute of Technology (AIT)
** WEM program, Asian Institute of Technology (AIT)
Email: nitinkt@ait.ac.th,
clemente@ait.ac.th
Abstract
Land suitability modeling in this study is based on modified FAO framework for climatic and land characteristics requirements. This was carried out using GIS and multi-factor evaluation. Analytical Hierarchical Processing (AHP) and Pairwise Comparison Method were used for factor weighting. To set the correct relative preference level of all evaluation factors without personal bias in this study not only depends on soil theory information and the authors experience but also based on expert opinion expressed by earlier researchers. The confusion matrix output is developed to show the accuracy of suitability classification result by comparing with ground truth information, spectral reflectance values of existing main crops of study area, rubber and oil palm. The suitability classes for rubber distribution in percent for each ground truth class given the overall accuracy 89.5161 % and given the overall accuracy 83.4437 % for oil palm. This new methodology can be accepted. Superimposing both high accuracy images generated crops substitution model. Additionally, it was observed that this land suitability model has displayed a good correlation with the NDVIs of existing crops (rubber and oil palm) with r2 0.7257 and 0.8358 respectively. These results confirm the potential of land suitability zonation based on NDVI values.
|
|
|