while using google earth engine to classify the land use of an area, the error of property 'pc2' of feature '1_1_1_1_0_0' is missing, appears.
actually this error appears for all bands of my testing data. here is my code:
var classesT = t_forest_2001.merge(t_rice_2001).merge(t_dryfarm_2001).merge(t_village_2001)
.merge(t_water_2001) .merge(t_bare_2001);
print(classesT);
Map.addLayer(classesT ,{}, 'test');
var bands = ['PC2','PC1','slope', 'NDWI','NDVI','NDBI','texture'];
var testing = classified.sampleRegions({
collection: classesT,
properties:['landuse'],
scale: 30
});
//var con= testing.errorMatrix('landuse','classification')
//print ('accu',con.producersAccuracy().project([0]));
//var classifiedT = testing.select(bands).classify(classifier);
Map.addLayer(classified ,{min:0, max:5, palette: ['#358521', '#63ff60',
'#ffb783', '#be3939','#68f8ff','#ffe78f']},'classification');
var confusionMatrix = ee.ConfusionMatrix(testing.classify(classifier)
.errorMatrix({
actual: 'landuse',
predicted: 'classification'
}));
print('Test:', confusionMatrix);
print('Overall Accuracy Test:', confusionMatrix.accuracy());
print('kappa Test:', confusionMatrix.kappa());
print('Producers Accuracy Test:', confusionMatrix.producersAccuracy());
print('Consumers Accuracy Test:', confusionMatrix.consumersAccuracy());
Related
I am about to calculate Chorophyll-a in the water bodies in one region, as I outlined above. I have created a mask, with water=1, land=0(transparent）. And I want to calculate quality formula (NDCI, refer to normalized difference chl-a index) over the mask I created in the last step. Here are my code.
function maskS2clouds(image) {
var qa = image.select('QA60')
var cloudBitMask = 1 << 10;
var cirrusBitMask = 1 << 11;
var mask = qa.bitwiseAnd(cloudBitMask).eq(0).and(
qa.bitwiseAnd(cirrusBitMask).eq(0))
return image.updateMask(mask).divide(10000)
.select("B.*")
.copyProperties(image, ["system:time_start"])
}
var tiles = ['29UNV']
var collection = ee.ImageCollection("COPERNICUS/S2_SR")
.filterDate('2020-01-01', '2020-12-31')
.filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20))
.filter(ee.Filter.inList('MGRS_TILE', tiles))
print(collection)
var minmin = collection.map(maskS2clouds)
print(minmin)
var calndwi = function(image){
//water mask
var NDWI = image.normalizedDifference(['B3', 'B8']).rename('NDWI');
return image.addBands(NDWI).updateMask(NDWI.gt(0));
};
print(minmin.map(calndwi));
//Add NDWI to the clipped image collection
var withNDWI = minmin.map(calndwi).select('NDWI');
print("NDWI collection", withNDWI);
var bb = withNDWI.first();
Map.addLayer(bb,{},'ss');
var addNDCI = function(image) {
var ndci = image.normalizedDifference(['B5', 'B4']).rename('NDCI');
return image.addBands(ndci);
};
var withNDCI = minmin.map(addNDCI).select('NDCI');
print("NDCI collection", withNDCI);
var MASK = function(image) {
var mask = bb.mask(image);
return image.addBands(mask);
};
var maskk = withNDCI.map(MASK).select('mask');
print(maskk)**
and it give me the bug like ImageCollection (Error)
Error in map(ID=20200106T114451_20200106T114531_T29UNV):Image.select: Pattern 'mask' did not match any bands.what should I do? thanks a million
The maskk object does not contain any bands named mask, because your MASK function does not create or add any bands with that name.
What your code does, as you've currently written it, is this:
var MASK = function(image) {
// Apply a mask over the 'bb' image.
var mask = bb.mask(image);
// return 'image' (which was the 'mask' parameter above),
// with ALL bands from the object 'mask', which is now a 'masked' version of bb.
// since mask = bb.mask(image), all the bands from bb will be added.
return image.addBands(mask);
};
var maskk = withNDCI
// Map the 'MASK' function over the 'withNDCI' collection
.map(MASK)
// Attempt to select a band named 'mask' (which does not exist).
.select('mask');
I'm not sure what you're looking for when you try to select the mask 'band' - I assume what you want is the masked NCDI image. That's essentially what you have already - but the band names of the 'maskk' object are "NDWI" and "NDCI", since it is derived from the bb, and those are the bands that bb contains. There is no band named "mask".
I calculated the MNDWI value of the picture collection
function MNDWI(image) {
var mndwi = image.normalizedDifference(['SR_B6', 'SR_B3']).rename('mndwi');
return image.addBands(mndwi);
}
// display MNDWI layer
var withMndwi = filtered.map(MNDWI);
var composite = withMndwi.median().clip(polygon);
var MndwiComposite = composite.select('mndwi');
I also use statistic to calculate the threshold
var chart = ui.Chart.image.seriesByRegion({
imageCollection: withMndwi,
regions: pol,
band: 'mndwi',
reducer:ee.Reducer.mean(),
scale:10, });
Now I want to consider every single value of the image collection, I did try something as recommendation in this [post][1] like:
function masking (image){
var sample = image.sample();
var threshold = sample.gte(chart); // gte = greater (gt) + equal (eq)
var mask = threshold.updateMask(threshold);
return image.updateMask(mask);
}
But it notices that: sample.gte is not a function
What should I do for now?
[1]: extract the values for all pixels in a polygon in google earth engine
I am trying to conduct a lulc classification on google earth engine using landsat5 data for 2000, but every time it is showing me the error:
image.select(bands).sampleRegions is not a function
var shp = ee.FeatureCollection(mws)
Map.addLayer(shp, {}, 'My Polygon')
var pol = ee.FeatureCollection(poly2000)
Map.addLayer(pol, {} )
//landcover for 2000//
var dataset = ee.ImageCollection("LANDSAT/LT05/C01/T1_TOA")
.filterBounds(roi1)
.filterDate('2000-01-01', '2000-01-31')
.map(function(image){return image.clip(mws)});
var trueColor432 = dataset.select(['B4', 'B3', 'B2']);
var trueColor432Vis = {};
Map.setCenter(88.41713038056656,26.861987108179317);
Map.addLayer(trueColor432, trueColor432Vis, 'True Color (432)');
var image = trueColor432;
// merging sample points together
var landcover = forest.merge(water).merge(clearing).merge(built_up);
print(landcover);
// selecting bands
var bands= ['B2','B3','B4'];
//sampling the input imagery to get a featurecollection of a training data
var training = image.select(bands).sampleRegions({
collection: landcover,
properties: ['landcover'],
scale: 30
});
//training the classifier
var classifier= ee.Classifier.svm().train({
features: training,
classProperty : 'landcover',
inputProperties: bands
});
//classifying the input imagery
var classified= image.select(bands).classify(classifier);
sampleRegions samples the pixels of an image: https://developers.google.com/earth-engine/apidocs/ee-image-sampleregions
Maybe adding .toBands() works?
var training = image.toBands().select(bands).sampleRegions({
collection: landcover,
properties: ['landcover'],
scale: 30
});
I am working on a land use classification program using the RS algorithm of the GEE platform. The codes are as the following link.
https://code.earthengine.google.com/7e99f1de58c1251bd9bff0ff7af9368b
Specific codes:
var table = ee.FeatureCollection("users/zongxuli/Jing_Jin_Ji");
//Set up bands and corresponding band names
var inBands = ee.List([1,2,3,4,5,7,6,'pixel_qa'])
var outBands = ee.List(['blue','green','red','nir','swir1','temp', 'swir2','pixel_qa'])
// Get Landsat data
var l8s = ee.ImageCollection("LANDSAT/LC08/C01/T1_SR")
.filterDate(2019-01-01,2019-12-31)
.filterBounds(table)
.select(inBands,outBands)
.filter(ee.Filter.lt("CLOUD_COVER",10))
function getIndexes(image){
// Normalized Difference Vegitation Index(NDWI)
var ndvi = image.normalizedDifference(['nir','red']).rename("ndvi");
image = image.addBands(ndvi);
// Normalized Difference Snow Index(NDWI)
var ndsi = image.normalizedDifference(['green','swir1']).rename("ndsi");
image = image.addBands(ndsi);
// Normalized Difference Water Index(NDWI)
var ndwi = image.normalizedDifference(['nir','swir1']).rename("ndwi");
image = image.addBands(ndwi);
// add Enhanced Vegetation Indexes
var evi = image.expression('2.5 * ((NIR - RED) / (NIR + 6 * RED - 7.5 * BLUE + 1))', {
'NIR' : image.select('nir'),
'RED' : image.select('red'),
'BLUE': image.select('blue') }).float();
image = image.addBands(evi.rename('evi'));
// Add Index-Based Built-Up Index (IBI)
var ibiA = image.expression('2 * SWIR1 / (SWIR1 + NIR)', {
'SWIR1': image.select('swir1'),
'NIR' : image.select('nir')}).rename(['IBI_A']);
var ibiB = image.expression('(NIR / (NIR + RED)) + (GREEN / (GREEN + SWIR1))', {
'NIR' : image.select('nir'),
'RED' : image.select('red'),
'GREEN': image.select('green'),
'SWIR1': image.select('swir1')}).rename(['IBI_B']);
var ibiAB = ibiA.addBands(ibiB);
var ibi = ibiAB.normalizedDifference(['IBI_A', 'IBI_B']);
image = image.addBands(ibi.rename('ibi'));
return(image);
}
function getTopography(image,elevation) {
// Calculate slope, aspect and hillshade
var topo = ee.Algorithms.Terrain(elevation);
// From aspect (a), calculate eastness (sin a), northness (cos a)
var deg2rad = ee.Number(Math.PI).divide(180);
var aspect = topo.select(['aspect']);
var aspect_rad = aspect.multiply(deg2rad);
var eastness = aspect_rad.sin().rename(['eastness']).float();
var northness = aspect_rad.cos().rename(['northness']).float();
// Add topography bands to image
topo = topo.select(['elevation','slope','aspect']).addBands(eastness).addBands(northness);
image = image.addBands(topo);
return(image);
}
// Get an image to train and apply classification to.
var image = ee.ImageCollection('LANDSAT/LC08/C01/T1_SR')
.filterBounds(table)
.first();
// get bands
var bands=image.bandNames();
print(bands);
// integers starting from zero in the training data.
var label = 'lcode';
// Overlay the points on the imagery to get training.
var trainings = image.select(bands).sampleRegions({
collection: l8s, //.filterDate(2019-01-01,2019-12-31),
properties: [label],
scale: 30
});
// The randomColumn() method will add a column of uniform random
// numbers in a column named 'random' by default.
var sample = trainings.randomColumn();
var split = 0.7; // Roughly 70% training, 30% testing.
var training = sample.filter(ee.Filter.lt('random', split));
print(training.size());
// Random forest
var classifier = (ee.Classifier.smileRandomForest(15)
.train({
features: training,
classProperty: label,
inputProperties: bands
}));
var classified = image.classify(classifier);
print(classified);
So far, I always received the wrong message "Number (Error) Empty date ranges not supported for the current operation." when running the program. What am I doing wrong?
There is a quotation problem in image collection date filtering:
// Get Landsat data
var l8s = ee.ImageCollection("LANDSAT/LC08/C01/T1_SR")
.filterDate(2019-01-01,2019-12-31)
.filterBounds(table)
.select(inBands,outBands)
.filter(ee.Filter.lt("CLOUD_COVER",10))
it must be:
// Get Landsat data
var l8s = ee.ImageCollection("LANDSAT/LC08/C01/T1_SR")
.filterDate('2019-01-01','2019-12-31')
.filterBounds(table)
.select(inBands,outBands)
.filter(ee.Filter.lt("CLOUD_COVER",10))
And in training for classifier section:
// Overlay the points on the imagery to get training.
var trainings = image.select(bands).sampleRegions({
collection: l8s, //.filterDate(2019-01-01,2019-12-31),
properties: [label],
scale: 30 });
it must be :
// Overlay the points on the imagery to get training.
var trainings =
image.select(bands).sampleRegions({
collection: table,
properties: [label],
scale: 30 });
I want to use supervised classification to classify a pattern that has a clear temporal pattern. For example, identifying stands of deciduous trees in a coniferous forest. NDVI would change overtime in the deciduous stands in a regular pattern that should be easily detectable. I assume there's an easy method to flatten the temporal dataset into a single image so that the bands in that image can be used in a classification algorithm. Maybe using .map(....)?
Here's some code to build the answer from:
var startDate = '2016-05-01';
var endDate = '2016-09-01';
var lng = -122.3424; var lat = 37.9344; //SF
var region = ee.Geometry.Point(lng, lat);
//Image Import
var l8 = ee.ImageCollection('LANDSAT/LC08/C01/T1_TOA')
.filterBounds(region)
.filterDate(startDate,endDate);
// NDVI temporal
var ndvi = l8.map(function(image) {
var ndvi = image.normalizedDifference(['B5', 'B4']).rename("NDVI");
return ndvi;
});
Map.addLayer(ndvi,{},"NDVI Temporal"); // 8 images with 1 band
//NDVI FLATTENED??????? I want 1 image with 8 bands. The below code doesn't work...
var ndviFlat = ee.Image().addBands(ndvi.map(function(image){
var temp = image.select("NDVI");
return temp;
}));
From there, I will pass ndviFlat to .sampleRegions, which only works with Images not ImageCollections:
//Classification Model:
var points = ee.FeatureCollection([trainingPointsPos,trainingPointsNeg]).flatten();
var training = ndviFlat.sampleRegions({
collection: points,
properties: ['class'],
scale: 30
});
var trained = ee.Classifier.randomForest(20).train(training, 'class', bands);
classified = regLayers.select(bands).classify(trained);
Here's one way:
var startDate = '2016-05-01';
var endDate = '2016-09-01';
var lng = -122.3424;
var lat = 37.9344; //SF
var region = ee.Geometry.Point(lng, lat);
//Image Import
var l8 = ee.ImageCollection('LANDSAT/LC08/C01/T1_TOA')
.filterBounds(region)
.filterDate(startDate, endDate);
var empty = ee.Image();
// NDVI temporal
var ndvi = ee.Image(l8.iterate(function(image, previous) {
var name = ee.String('NDVI_').cat(image.id());
var ndvi = image.normalizedDifference(['B5', 'B4']).rename(name);
return ee.Image(previous).addBands(ndvi);
}, empty));
// Remove the annoying non-band
ndvi = ndvi.select(ndvi.bandNames().remove('constant'));
Map.centerObject(region, 13);
Map.addLayer(ndvi, {}, 'ndvi');