0

I am creating unsupervised classifications of an area to detect landscape/vegetation change over time.

For each year:

  • I have created an NDVI of the area based on a composite of Landsat images acquired in April and May of that year.
  • I then performed an unsupervised classification (create sets of training samples > set a clusterer to kmeans with 5 clusters > instantiate a clusterer for each NDVI > create and display classes)

I would like to see how the NDVI values were portioned into different classes (ex: Class 1 = 0.0 - 0.2, Class 2 = 0.2 - 0.45, etc.) Where can I find this information?

1 Answer 1

1

To figure out what K-Means did, you (re)cluster the training data and then compute the mean of each of those clusters with reduceColumns and a grouped reducer. If you only have 1 covariate, then the breaks will be 1/2 way between the mean of each pair of neighbours.

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.