0

My Goal is to extract Spatial Information for Usage in Tensorflow.

I´ve got Spatial Information from Landsat(30m) and Modis(500m), if I want to extract this Information, do I need any form of reprojection? or does Google Earth Engine ensure precise Value extraction?

Ive tried using reproject on Modis imagery, by using the Landsat projection

with `var lsPr = LS8Col.first().projection()

var preSnowCollection = ee.ImageCollection('MODIS/006/MOD10A1').select('NDSI_Snow_Cover')
.filterBounds(geometry).filterDate('2005-01-01','2005-01-06')
var snow = preSnowCollection.first()
var snowPr = snow.projection()

Map.addLayer(snow,[],'snow')

var snowre = preSnowCollection.first().reproject(lsPr)
var snowrePr = snowre.projection()

Map.addLayer(snowre,[],'snowre')

print(snowPr)
print(snowrePr)

MODIS original:

enter image description here

MODIS reprojected to Landsat:

enter image description here

These Bumps, make me curious. I've read Projections Page and have to admit that I don´t understand if this is just a visualization thing, or if my data will actually become faulty by reprojecting.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.