I'm classifying images of Red River Delta. Unfortunately, the region is split into two consecutive Sentinel 1A images. Therefore, I want to mosaic them into single image for convenient classification.

How do I do this?

Here is the code:

// Use these bands for prediction.
var bands = ['VV', 'VH'];

// Load a sentinel 1A image to be used for prediction.
var img1 = ee.Image('COPERNICUS/S1_GRD/S1A_IW_GRDH_1SDV_20170104T225034_20170104T225059_014688_017E5C_6A39').select(bands);

var img2 = ee.Image('COPERNICUS/S1_GRD/S1A_IW_GRDH_1SDV_20170104T225059_20170104T225124_014688_017E5C_750B').select(bands);

var img_temp = ee.Image.cat([img1, img2]);
  • Welcome to GIS SE! As a new user be sure to take the Tour. For questions that involve code we ask that you show us where you are stuck with your own code by including a code snippet as text in your question. There is an edit button beneath your question which will enable you to do that and a {} button that enables you to format any highlighted code nicely. What happens when you run the code that you have presented? – PolyGeo Jan 5 '18 at 2:45
  • 2
    It is very challenging to mosaic Sentinel-1 images because of the viewing angles. If you work with GRD, I would simply avoid and combine after classification, because the standard pre-processing available in GE is not sufficient to remove topographic effect. – radouxju Jan 5 '18 at 8:08
  • In addition to including the code as text, make sure that you have fully defined all of your values so that others can rerun your code. In your example, the variables img, points, training, and bands are all undefined. – Tyler Erickson Jan 5 '18 at 13:57
  • @radouxju Thank you very much. For the viewing angle problem, is it significant for consecutive images? – Chung Jan 6 '18 at 3:06
  • @Tyler Erickson I have included the code for easy editting. Thank you for your suggest. – Chung Jan 6 '18 at 3:08