SCP Questions of This Month: July

This post is a collection of questions and answers about the Semi-Automatic Classification Plugin (SCP) and remote sensing which were discussed in the Facebook group and the Google+ Community this month.
These questions vary from supervised classification technique to software issues, and can be useful to the readers of this blog for solving issues about the use of SCP.

Question

With the Landsat 8 downloaded from AWS (Amazon) do we need to preprocess them using SCP or can we load and use them directly in QGIS?

Answer

Yes, you should perform the preprocessing if you want to convert DN to reflectance values

Question

Where can I find the .tiff image for my city? I tried the Landsat 8 section on USGS Earth Explorer, but many files are downloaded.

Answer

Images are provided as separated bands. You should first download the bands and then create a tif file. Please follow this tutorial https://www.youtube.com/watch?v=FcETq8OWM0k

Question

I would like to know how best I can classify an agricultural landscape into their crop types from landsat images? 

Answer

Please read this tutorial https://fromgistors.blogspot.com/2014/01/land-cover-classification-of-cropland.html

Question

In Band set the center wavelength of Landsat 5 bands accidentally left to band order (1.0, 2.0, 3.0, 4.0, 5.0, 6.0) and the ROI signatures computed with these. Will it be a problem? The purpose of classification is a Land Cover Change Detection with Landsat 8 image.

Answer

It is not a problem if you don't need to compare these signatures to the other ones created with the correct center wavelength. However, you can change the Band set and then calculate ROI spectral signatures again (see http://semiautomaticclassificationmanual-v5.readthedocs.io/en/latest/scp_dock.html#roi-signature-list).

Question

How can I fill the gaps to use the Landsat 7 images?

Answer

Please read this tutorial https://fromgistors.blogspot.com/2015/10/tutorial-land-cover-classification-and.html

For any comment or question, join the Facebook group and the Google+ Community about the Semi-Automatic Classification Plugin.