I applied supervised maximum likelihood classification to a yearly stack of Landsat images (resolution 30m). The land cover classes are related to coniferous forest, i.e., forest, clear-cut, fire, bark beetle. I had only few years of available reference aerial photos (resolution 0.5m). Aerial photos do not fully cover the extent of Landsat images (AOI). To assess the accuracy of the classification for single year scene, I extracted a overlapping part between the extent of Landsat and aerial photos:

enter image description here

I calculated the measures of accuracy for the extracted part of fully classified Landsat by set of stratified sampling points per mapped class.

I followed the methods published here:

  • Olofsson, P., Foody, G.M., Herold, M., Stehman, S. V., Woodcock, C.E., Wulder, M.A., 2014. Good practices for estimating area and assessing accuracy of land change. Remote Sens. Environ. 148, 42–57. doi:10.1016/j.rse.2014.02.015 and
  • Olofsson, P., Foody, G.M., Stehman, S. V., Woodcock, C.E., 2013. Making better use of accuracy data in land change studies: Estimating accuracy and area and quantifying uncertainty using stratified estimation. Remote Sens. Environ. 129, 122–131. doi:10.1016/j.rse.2012.10.031

to assess the accuracy of the classification.

Great R code summarizing this can be found here: https://github.com/openforis/accuracy-assessment/blob/master/error_matrix_analysis.R

The error matrix, by this method, is not based on the simple sample counts, but on the estimated proportions of the area. Including the proportion of the mapped classes in accuracy assessment, it is possible to quantify the uncertainty attributable to variability in the sampling. Simply, to adjust the mapped area to map classification error. The error-adjusted area estimates should be accompagnied by confidence interval.

My problem:

I classified 7 Landsat images. I calculated accuracy for extracted parts of them for two years, because of no availability of another reference data sets.

My question:

  • Can I apply the accuracy measures from the years with reference photos to the years without reference photos? (i.e. overall accuracy is 90% in year 1, I assume the same accuracy is in year 2, 3, ...4?)

enter image description here

  • How do you hope to apply the accuracy measures to the years without reference photos?
    – Aaron
    Commented Oct 3, 2016 at 3:12
  • Isn't this a duplicate question with a slightly different title?gis.stackexchange.com/questions/212772/…
    – AnserGIS
    Commented Oct 11, 2016 at 21:52
  • Oh yes, sorry ! tried to splis my multiple questions into a partial question ajnd I have made a mistake.. thanks !
    – maycca
    Commented Oct 13, 2016 at 6:33

1 Answer 1


Your accuracy assessment will only be relevant to the areas and years covered by the reference photos.

However if your data sets are similar (i.e. same sensor, atmospheric correction, area, season) and you followed the same classification process for all images then it is reasonable to assume that the accuracy will be similar across the image series. But the fact that your accuracy figures were calculated from a subset of data has to remain as a caveat.

If [1] your accuracy measures for the areas where you do have hi-res imagery are similar, and [2] a land cover change confusion matrix (Foody 2002) of these areas shows good accuracy then you are justified in assuming your accuracy measures to be valid for the other images.

  • Is there any publication that backs this up? :)
    – M514
    Commented Nov 28, 2017 at 18:15

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.