Google Earth Engine – Adding Band Values from CSV to Image Collection for Classification

classificationcsvgoogle-earth-enginemulti-bandrandom forest

I am currently working with GEDI data and Random Forest Classification in Google Earth Engine. I have a csv file which contains 42 bands and about 3600 points. My aim is to import this csv into GEE and do the Random Forest Classification and then take the regression map. The problem happened when I tried to run the regression map by ee.Image.classify and error occured Regression: Layer error: Image.select: Pattern 'Blue' did not match any bands.. How could I add the bands value from CSV file to the Image Collection to avoid this error and run the code?
My code is as follow:

var table = ee.FeatureCollection("projects/ee-vietfix14/assets/GEDIdatapoints1");
var training = table.distinct('system:index');
// AOI 
var aoi = ee.Geometry.Polygon(
    [[[-53.727841320713424, 5.4107641852798425],
      [-53.727841320713424, 2.605426055652731],
      [-51.640438976963424, 2.605426055652731],
      [-51.640438976963424, 5.4107641852798425]]], null, false).buffer(1e4);
var heightBand = 'rh99'

Map.addLayer(table)
Map.centerObject(aoi, 12)
////////////////////////////////////////////////////////
var filter = ee.Filter.and(
  ee.Filter.bounds(aoi),
  ee.Filter.date('2019-01-01', '2021-01-01')

  )
var S2composite = ee.ImageCollection(
    ee.Join.saveFirst('cloudProbability').apply({
        primary: ee.ImageCollection('COPERNICUS/S2_SR').filter(filter),
        secondary: ee.ImageCollection('COPERNICUS/S2_CLOUD_PROBABILITY').filter(filter),
        condition: ee.Filter.equals({leftField: 'system:index', rightField: 'system:index'})
    })
  ).map(function (image) {
  var cloudFree = ee.Image(image.get('cloudProbability')).lt(30)
  return image.updateMask(cloudFree).divide(10000)
  })


var bands =['Blue','Green','Red','NIR','SWIR1','SWIR2','NDVI','EVI','NDWI','MSAVI','SAVI','GNDVI','CVI','DVI','NDMI','GRVI','MSR','GSAVI','GARI','GLI','NDGI','NBR','NDII','SWIR1_Ratio_SWIR2','NIR_Ratio_SWIR1', 'RVI','VVdb','VHdb','ratio_VV_VH','RVIpal','HVdb','HHdb','ratio_HV_HH'];
var S2_composite = S2composite.median();
print(S2_composite)
/////////////////////////////////////////////////////////////////////
// Train a random forest classifier for regression 
var classifier = ee.Classifier.smileRandomForest(50)
  .setOutputMode('REGRESSION')
  .train({
    features: training, 
    classProperty: heightBand,
    inputProperties: bands
    });
print(classifier)
var regression = S2_composite.select(bands).classify(classifier, 'predicted').clip(aoi);
// Load and define a continuous palette
var palettes = require('users/gena/packages:palettes');

// Choose and define a palette
var palette = palettes.colorbrewer.YlGn[5];
var viz = {palette: palette, min: 0,max:60};
Map.addLayer(regression, viz, 'Regression');

My code link: [https://code.earthengine.google.com/14825f7350139a75d1f02796e3c817a3]

My table: [https://code.earthengine.google.com/?asset=projects/ee-vietfix14/assets/GEDIdatapoints1]

Best Answer

The image you're trying to classify must contain the same bands as the training data used when training the classifier. It doesn't. You have to rename the bands include the indexes in your composite. This should give you an idea, using only a subset of your bands (to same me some time, you'll have to complete this yourself):

var S2composite = ee.ImageCollection(
    ee.Join.saveFirst('cloudProbability')
      .apply({
          primary: ee.ImageCollection('COPERNICUS/S2_SR').filter(filter),
          secondary: ee.ImageCollection('COPERNICUS/S2_CLOUD_PROBABILITY').filter(filter),
          condition: ee.Filter.equals({leftField: 'system:index', rightField: 'system:index'})
      })
    )
    .select(
      ['B2', 'B3', 'B4', 'B8'],
      ['Blue','Green','Red', 'NIR']
    )
    .map(function (image) {
      var cloudFree = ee.Image(image.get('cloudProbability')).lt(30)
      var indexes = ee.Image([
        image.normalizedDifference(['Red', 'NIR']).rename('NDVI')
    ])
    return image
      .addBands(indexes)
      .updateMask(cloudFree).divide(10000)
    })


var bands = ['Blue', 'Green', 'Red', 'NIR', 'NDVI']

Related Solutions

[GIS] Combining multiple bands from different image collection into one collection

Assuming you made a unique name for each band, and that you want to obtain one image with 3 bands (one for a, one for b and one for c) you have to addBands, like this:

var a = ee.Image(1).rename('one') // product one
var b = ee.Image(2).rename('two')
var c = ee.Image(3).rename('three')

var final = a.addBands([b, c])

link: https://code.earthengine.google.com/5c3ceef589fc8cbe6036f8f2ef22f2ca

Google Earth Engine – Fixing Random Forest Classification Error for GEDI Datasets

I don't follow how you want this to work. What are the classes you want in your classification? Nevertheless, the reason for your error is this:

var label = 'Relative Height'
var sample = img.select(bands).sampleRegions({
  collection: points,
  properties: [label],
  scale: 30
})

The points collection doesn't contain any Relative Height property. Even if it did, I don't think this quite makes sense.

You could maybe try something like the below. Note that I've never used the GEDI data, and have very limited knowledge of it. So take this approach with a grain of salt. I'd very much appreciate someone with more knowledge on this to jump in and comment.

I'm extracting reference data from the GEDI collection, create Landsat 8/Sentinel 1 composites for the corresponding month, and sample it for training data. A classifier is trained, then finally applied to a composite for a date range of your choosing.

var aoi = ee.Geometry.Polygon([[
  [-52.992228448173776, 5.3639624330339855],
  [-52.992228448173776, 5.216962579558439],
  [-52.898158013603464, 5.216962579558439],
  [-52.898158013603464, 5.3639624330339855]
]]).buffer(1e4)

var heightBand = 'rh95'

var gedi = ee.ImageCollection('LARSE/GEDI/GEDI02_A_002_MONTHLY')
  .filterBounds(aoi)
  .map(function (image) {
    return image
      .updateMask(image.select('quality_flag').eq(1))
      .updateMask(image.select('degrade_flag').eq(0))
      .select(heightBand)
  })
var referenceData = gedi
  .map(toReferenceData)  
  .filterMetadata('count', 'not_equals', 0)
var trainingData = referenceData
  .map(toTrainingData)
  .flatten()

var composite = toComposite('2021-01-01', '2022-01-01')
var classifier = ee.Classifier.smileRandomForest(25)
  .train(trainingData, heightBand, composite.bandNames())
  .setOutputMode('REGRESSION')
var classification = composite.classify(classifier)


print('trainingData', trainingData)
print('classifier', classifier.explain())
Map.addLayer(referenceData.flatten(), null, 'reference data', false)
Map.addLayer(gedi.mosaic().clip(aoi), {bands: heightBand, min: 0, max: 40, palette: '#fffdcd, #e1cd73, #aaac20, #5f920c, #187328, #144b2a, #172313'}, heightBand)
Map.addLayer(composite, {bands: 'red,green,blue', min: 0, max: 2000, gamma: 1.6}, 'optical')
Map.addLayer(composite, {bands: 'VV,VH,ratio_VV_VH', min: [-20, -25, 3], max: [0, -5, 14]}, 'sar')
Map.addLayer(classification, {min: 0, max: 40, palette: '#fffdcd, #e1cd73, #aaac20, #5f920c, #187328, #144b2a, #172313'}, 'height')
Map.centerObject(aoi, 12)


function toReferenceData(gedi) {
  var referenceData = gedi
    .sample({
      region: aoi,
      scale : 25,
      numPixels : 200000,
      geometries: true
    })
    .map(function (feature) {
      // Can only use ints as classes
      return feature.set('rh99', feature.getNumber('rh99').round())
    })
  return referenceData
    .set({
      year: gedi.getNumber('year'),
      month: gedi.getNumber('month'),
      count: referenceData.size()
    })
}


function toTrainingData(referenceData) {
  var year = referenceData.getNumber('year')
  var month = referenceData.getNumber('month')
  var fromDate = ee.Date.fromYMD(year, month, 1)
  var toDate = fromDate.advance(1, 'month')
  var composite = toComposite(fromDate, toDate)
  return composite.sampleRegions({
    collection: referenceData,
    properties : [heightBand],
    scale : 30
  })  
}


function toComposite(fromDate, toDate) {
  return toOpticalComposite(fromDate, toDate)
    .addBands(toSarComposite(fromDate, toDate))
}

function toSarComposite(fromDate, toDate) {  
  var composite = ee.ImageCollection('COPERNICUS/S1_GRD_FLOAT')
    .filter(ee.Filter.and(
      ee.Filter.bounds(aoi),
      ee.Filter.date(fromDate, toDate),
      ee.Filter.eq('instrumentMode', 'IW'),
      ee.Filter.listContains('transmitterReceiverPolarisation', 'VV'),
      ee.Filter.listContains('transmitterReceiverPolarisation', 'VH')
    ))
    .map(function (image) {
      return maskBorder(
        toDb(
          toGamma0(image)
        )
      ).select(['VV', 'VH'])
    })
    .median()
  return composite
    .addBands(
      composite.select('VV').divide(composite.select('VH')).rename('ratio_VV_VH')
    )
    

  function toGamma0(image) {
    var gamma0 = image.expression('i/(cos(angle * pi / 180))', {
      'i': image.select(['VV', 'VH']),
      'angle': image.select('angle'),
      'pi': Math.PI
    })
    return image.addBands(gamma0, null, true)    
  }
  
  function toDb(image) {
    return image.addBands(
      image.select(['VV', 'VH']).log10().multiply(10), null, true
    )    
  }
    
  function maskBorder(image) {
    var angle = image.select('angle')
    return image
      .updateMask(
        angle.gt(31).and(angle.lt(45))
      )    
  }    
}


function toOpticalComposite(fromDate, toDate) {
  return ee.ImageCollection('LANDSAT/LC08/C02/T1_L2')
    .filterDate(fromDate, toDate)
    .filterBounds(aoi)
    .map(function (image) {
      var qa = image.select('QA_PIXEL')
      var cloudShadow = bitwiseExtract(qa, 4)
      var snow = bitwiseExtract(qa, 5).rename('snow')
      var cloud = bitwiseExtract(qa, 6).not().rename('cloud')
      return image
        .updateMask(
          cloudShadow.not()
            .and(snow.not())
            .and(cloud.not())
        )
        .select(
          ['SR_B2', 'SR_B3', 'SR_B4', 'SR_B5', 'SR_B6', 'SR_B7'],
          ['blue', 'green', 'red', 'nir', 'swir1', 'swir2']
        )
        .multiply(2.75e-05)
        .add(-0.2)
        .multiply(10000)
        .int16()
    })
    .median()
}

function bitwiseExtract(value, fromBit, toBit) {
  if (toBit === undefined)
    toBit = fromBit
  var maskSize = ee.Number(1).add(toBit).subtract(fromBit)
  var mask = ee.Number(1).leftShift(maskSize).subtract(1)
  return value.rightShift(fromBit).bitwiseAnd(mask)
}

https://code.earthengine.google.com/52f8f4ee6d2ab759e4f0fd1acb1ea2a9

Best Answer

Related Solutions

[GIS] Combining multiple bands from different image collection into one collection

Google Earth Engine – Fixing Random Forest Classification Error for GEDI Datasets

Related Question