Primary competition visual

CGIAR Crop Yield Prediction Challenge

Helping Kenya
$3 000 USD
Completed (~5 years ago)
Prediction
Earth Observation
890 joined
195 active
Starti
Oct 21, 20
Closei
Feb 07, 21
Reveali
Feb 07, 21
Cloud removal and image procession
Help · 10 Oct 2021, 17:36 · 5

Did anyone try to use sentinel 2 to retrive the same fields photos in tif extension? or anyone tried to do some cloud removal from the image? we want to try super resoloution and try to do cloud removal to enhance the vegtiation indecies for specific fields?

Discussion 5 answers

Hello. I participated in this competition. For cloud removal you have to use QA60 band. In that band, pixels values are: 0: clear, 1024: clouds, and 2048: cirrus.

Regards.

11 Oct 2021, 03:57
Upvotes 0

I'm sorry for replying late but would you describe more how you did the cloud removal in more detailed way please?

I do that directly on Google Earth Engine (https://earthengine.google.com/) using the code below.

function maskS2clouds(image) {   var qa = image.select('QA60');   // Bits 10 and 11 are clouds and cirrus, respectively.   var cloudBitMask = 1 << 10;   var cirrusBitMask = 1 << 11;   // Both flags should be set to zero, indicating clear conditions.   var mask = qa.bitwiseAnd(cloudBitMask).eq(0)       .and(qa.bitwiseAnd(cirrusBitMask).eq(0));   return image.updateMask(mask).divide(10000); } var dataset = ee.ImageCollection('COPERNICUS/S2_SR')                   .filterDate('2020-01-01', '2020-01-30')                   // Pre-filter to get less cloudy granules.                   .map(maskS2clouds); Regards.

More information here:

https://developers.google.com/earth-engine/datasets/catalog/COPERNICUS_S2_SR