I’ve tried a variety of input bands like 2348 or all bands together but non of them work properly. Now I’m going to install SNAP 6.0 and try classification procedure again. Previously, I’ve executed supervised classification in SNAP 6.0 without any problem and I think this problem caused by a built in bug in SNAP 7.0. If I reach to a meaningful result on this case I will share with you.
January 13, 2020, 7:53am
maybe something went wrong during the update to version 7. Please let us know if it works when you go back to SNAP 6.0
I don’t know but I have same problem in SNAP 6.0. Do you have any tutorial or user guide for sentinel-2 classification procedure in SNAP software?
I saw many video tutorials in youtube but they didn’t use sentinel-2 images.
January 13, 2020, 8:40am
how did you resample the subset?
When I run the S2 Resampling operator on the subset product (it does work, you’re right), I get this message:
Maybe you first run the S2 Resampling operator and create a subset afterwards. This takes longer, but worked for me in the past.
I don’t have any problem in resampling operator and it works well. I’m following these steps:
download S2 L2A
open in snap 7
spatial subset using subset operator
resampling suing resampling operator: make all bands same pixel size.
collecting training data from resampled data
open Random Forest Classification
select training data
defining output address
shows bad result!
January 13, 2020, 9:12am
It was reported here that Sentinel-2 data has to be reprojected to WGS84 before collecting the training data and applying the classification:
I reproject the data into Geographic Lat/Lon. After that, the values do not change.
I try some times with some different data and I find out that in the classification step, it works with the Lat/Lon project.
a few minute ago I’ve tried random forest classification for landsat data and it works well without any problem. I think coordinate system cause this problem, according to this now I’m gonna to check sentinel-2 coordinate system and I will share you final result.
When I changed sentinel-2 coordinate system to wgs84, classification problem has solved completely.
Thanks for your excellent support.
March 7, 2020, 12:07pm
dear Amirhossein ,I classifed with sentinel-2 images too .but i didn’t work the step that Subset raster.Is this step necessary
Can you clarify a bit more about the sentinel 2 image classification in snap 7. I am new to this kind of Sentinel2 classification. I will be so thankful if you give more details about your workflow. cheers, Farman
March 16, 2020, 12:30pm
please have a look at these instructions:
Thanks ABraun for your swift reply on my issue. I will have a deep look at it and let you know with my results… Cheers
March 16, 2020, 2:49pm
Dear sir .There is no surface reflectance document for Sentinel-2, and I would like you to recommend me .
March 16, 2020, 2:56pm
every Sentinel-2 product contains refleactance. These instructions are valid for all multispectral products.
March 16, 2020, 3:13pm
here?I mean that files what can help me to identify the different figure types.
March 16, 2020, 3:15pm
please try to use the search function, many things are already explained in other topics:
The "dl" unit
can you please help me with that ? i did reprojection with utm/wgs84 and its still having issuees
December 16, 2021, 5:29pm
when i tried reprojection, i don’t know why it doesn’t work i receive an error . by the way I’m in morocco.
can u please help me and tell me how i can do the reprojection
December 16, 2021, 5:56pm
Please share the error message, otherwise we cannot help.