2

I have a question related to Drawing polygon and extracting land cover inside using Google Earth Engine?

I'm trying to work out how to calculate habitat type area from within a specific polygon in google earth engine using Copernicus data. I can do both of these tasks, just not together.

var s1 = ee.ImageCollection("COPERNICUS/S1_GRD"),
S2 = ee.ImageCollection("COPERNICUS/S2"),
fc = ee.FeatureCollection("ft:1w_ciwxR9FKm0rzMH8oJ3MdyE-1U15PfiOFlGW5Ib"),
fc2 = ee.FeatureCollection("ft:18Xvf7jG2EI4mJMwj0oLV2u-05bAPiwJDaxSRy2ep");
//Set a point of interest 
var aoi = fc; 
//Set bands of interest
var bands = ['B2', 'B3', 'B4','B8', 'B11', 'B12'];

//Import and filter Sentinel 2 collection
var S2 = ee.ImageCollection('COPERNICUS/S2')
.filterDate('2016-07-01', '2016-08-01')
.filterBounds(aoi)
print(S2);
var image = S2.mosaic();

Map.addLayer(S2, {'bands': 'B12,B8,B4','min': 0,'max': 4000}, 'Sentinel 2A         SWIR,NIT,R', 0);
var training = image.sampleRegions(fc2, ["info"], 30);
var classifier = ee.Classifier.cart()
.train(training, "info", image.bandNames());
var out = image.classify(classifier);
Map.addLayer(out, {palette: [
'ff0000',// cleared red
'ffcc66',// cultivated
'387242',// forest 
'99ff33',// grass 
'e0e0d1',// rock 
'e0e0d1'// rock grass
], min:1, max:6});

// Create a geometry representing an export region.
var geometry =         ee.Geometry.Rectangle([36.977296602,-15.364411987,37.057018981,-15.447436229]);

Map.addLayer(ee.Image().paint(fc, 1, 3));
var fc = fc2;
Map.addLayer(fc2);

//Create a band for each veg type
var class1 = out.eq(1).select([0],['cleared']);
var class2 = out.eq(2).select([0],['cultivated']);
var class3 = out.eq(3).select([0],['forest']);
var class4 = out.eq(4).select([0],['grass']);
var class5 = out.eq(5).select([0],['rock']);
var class6 = out.eq(6).select([0],['rockgrass']);
// Concatanate the bands into a single image
var total = ee.Image.cat([class1,class2,class3,class4,class5,class6]);

// Extract the landcover band
var landcover = image.select('landcover');

 // Clip the image to the polygon geometry
 var landcover_roi = landcover.clip(geometry);

 //Calculate the total area of each veg type in meters^2
 var count = total.multiply(ee.Image.pixelArea());
 print(total);
 print(count);

 var area = count.reduceRegion(ee.Reducer.sum(), geometry, 30, null, null,        false, 1e10, 1)
print(area);
var cleared = ee.Number(area.get('cleared'));



Export.image.toDrive({ 
image: out,
description: 'imageToDriveDeforestation',
scale: 30,
region: geometry
 });
Improve this question
2
  • You will need to share your Fusion Tables for others to run your code.
    – Tyler Erickson
    Commented Mar 4, 2017 at 23:28
  • I have changed the access permissions to the fusion tables. thanks.
    – James
    Commented Mar 5, 2017 at 1:42

2 Answers 2

Reset to default
2

Here are two ways of doing this. The first is your method of masking with some simplified code. The second is using a grouped reducer:

var s1 = ee.ImageCollection("COPERNICUS/S1_GRD"),
S2 = ee.ImageCollection("COPERNICUS/S2"),
fc = ee.FeatureCollection("ft:1w_ciwxR9FKm0rzMH8oJ3MdyE-1U15PfiOFlGW5Ib"),
fc2 = ee.FeatureCollection("ft:18Xvf7jG2EI4mJMwj0oLV2u-05bAPiwJDaxSRy2ep");

var aoi = fc; 

var bands = ['B2', 'B3', 'B4', 'B8', 'B11', 'B12'];

var S2 = ee.ImageCollection('COPERNICUS/S2')
  .filterDate('2016-07-01', '2016-08-01')
  .filterBounds(aoi);

// You may want to use median here if there's overlapping imagery.
var image = S2.mosaic();

var geometry = ee.Geometry.Rectangle([36.977296602,-15.364411987,37.057018981,-15.447436229]);
Map.centerObject(geometry);

var landcover_roi = image.clip(geometry);

Map.addLayer(landcover_roi, {'bands': 'B12,B8,B4','min': 0,'max': 4000}, 'Sentinel 2A SWIR,NIT,R', 0);

var training = landcover_roi.sampleRegions(fc2, ["info"], 30);
var classifier = ee.Classifier.cart()
    .train(training, "info", image.bandNames());
var out = landcover_roi.classify(classifier);
Map.addLayer(out, {palette: [
  'ff0000',// cleared red
  'ffcc66',// cultivated
  '387242',// forest 
  '99ff33',// grass 
  'e0e0d1',// rock 
  'e0e0d1'// rock grass
], min:1, max:6});

Map.addLayer(ee.Image().paint(fc, 1, 3));
var fc = fc2;
Map.addLayer(fc2);

var names = ['cleared', 'cultivated1', 'cultivated2', 'grass', 'rock', 'rockgrass'];
var total = out.eq([1, 2, 3, 4, 5, 6]).rename(names);

var count = total.multiply(ee.Image.pixelArea());

// The grouped reducer ignores the weights.  Unweight here for comparison.
var area = count.reduceRegion(ee.Reducer.sum().unweighted(), geometry, 30);
print(area);

var stats = ee.Image.pixelArea().addBands(out).reduceRegion({
  reducer: ee.Reducer.sum().group(1), 
  geometry: geometry, 
  scale: 30,
});
print(stats);
Improve this answer
1
  • More about masking: the mask is used for pixel weights. Some fractional weights in the out image result from clipping. When out is used for groups, its mask is not used for weights. As an alternative to unweighting, you could also transfer the weights in the reduceRegion() by setting the input to ee.Image.pixelArea().updateMask(out.mask())
    – Nicholas Clinton
    Commented Jul 17, 2017 at 23:22
0

I believe this has achieved my goal but would welcome advice on cleaning up the code. 

var s1 = ee.ImageCollection("COPERNICUS/S1_GRD"),
S2 = ee.ImageCollection("COPERNICUS/S2"),
fc = ee.FeatureCollection("ft:1w_ciwxR9FKm0rzMH8oJ3MdyE-1U15PfiOFlGW5Ib"),
fc2 = ee.FeatureCollection("ft:18Xvf7jG2EI4mJMwj0oLV2u-05bAPiwJDaxSRy2ep");
//Set a point of interest 
var aoi = fc; 
//Set bands of interest
var bands = ['B2', 'B3', 'B4','B8', 'B11', 'B12'];

//Import and filter Sentinel 2 collection
var S2 = ee.ImageCollection('COPERNICUS/S2')
.filterDate('2016-07-01', '2016-08-01')
.filterBounds(aoi)
 print(S2);
var image = S2.mosaic();
// Clip the image to the polygon geometry
var landcover_roi = image.clip(geometry1);

Map.addLayer(landcover_roi, {'bands': 'B12,B8,B4','min': 0,'max': 4000},        'Sentinel 2A SWIR,NIT,R', 0);
var training = landcover_roi.sampleRegions(fc2, ["info"], 30);
var classifier = ee.Classifier.cart()
.train(training, "info", image.bandNames());
var out = landcover_roi.classify(classifier);
Map.addLayer(out, {palette: [
'ff0000',// cleared red
'ffcc66',// cultivated
'387242',// forest 
'99ff33',// grass 
'e0e0d1',// rock 
'e0e0d1'// rock grass
], min:1, max:6});

// Create a geometry representing an export region.
var geometry =      ee.Geometry.Rectangle([36.977296602,-15.364411987,37.057018981,-15.447436229]);

Map.addLayer(ee.Image().paint(fc, 1, 3));
var fc = fc2;
Map.addLayer(fc2);

 //Create a band for each veg type
 var class1 = out.eq(1).select([0],['cleared']);
 var class2 = out.eq(2).select([0],['cultivated']);
 var class3 = out.eq(3).select([0],['forest']);
 var class4 = out.eq(4).select([0],['grass']);
 var class5 = out.eq(5).select([0],['rock']);
 var class6 = out.eq(6).select([0],['rockgrass']);
 // Concatanate the bands into a single image
 var total = ee.Image.cat([class1,class2,class3,class4,class5,class6]);

 //Calculate the total area of each veg type in meters^2
 var count = total.multiply(ee.Image.pixelArea());
 print(total);
 print(count);

 var area = count.reduceRegion(ee.Reducer.sum(), geometry, 30, null, null, false, 1e10, 1)
 print(area);
 var cleared = ee.Number(area.get('cleared'));



Export.image.toDrive({ 
image: out,
description: 'imageToDriveDeforestation',
scale: 30,
region: geometry1
});
Improve this answer

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.