Impacts of spatial resolution on land cover classification

  • Suwanprasit C
  • Srichai N
Citations of this article
Mendeley users who have this article in their library.


Regularly updated land cover information is a requirement for various land management application. Remote sensing scenes can provide information highly useful for real-time modeling of the earth environment. However, the spatial resolution is also a very important factor to acquire the information on satellite imagery. This paper summarizes the basic conclusions of work in which the spatial resolution of satellite imagery, related to the factor of scale for land cover classification, was investigated. Optical data collected by two different sensors (THEOS with 15-m resolution and Landsat 5-TM with resolution 30-m) in 2010 were tested against the ability to correctly classify specific land cover classes at different scales of observation. Support Vector Machines (SVMs) classifier was used and Kathu district, Phuket, Thailand was the study area. The land cover was classified into 7 groups as forest, built-up, road, water, agriculture, grassland and bare land. The result indicated that the overall accuracy of THEOS with 15 m was slightly higher than Landsat-5 TM with 30 m resolution (90.65% and 89.00%, respectively). The outcome of the study can be discussed further to assess the suitable spatial resolution for land cover classification mapping of Kathu district. Understanding the role of scale on the spectral signatures of satellite data will help the correct interpretation of any classification results.




Suwanprasit, C., & Srichai, N. (2012). Impacts of spatial resolution on land cover classification. Proceedings of the Asia-Pacific Advanced Network, 33(0), 39.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free