基于随机森林的GEE分类图像光谱特征

我使用这个脚本通过GEE中的RF算法,将所有类别的平均光谱特征画在一起,并分别画出分类图像的每个类别。

var bands = ['B1', 'B2', 'B3', 'B4','B5','B6','B7', 'B8', 'B8A', 'B9' ,'B11', 'B12','NDVI', 'EVI', 'GNDVI', 'NBR', 'NDII'];
var Training_Points = Water.merge(Residential).merge(Agricultural).merge(Arbusti).merge(BoschiMisti).merge(Latifoglie).merge(Conifere).merge(BareSoil);
var classes = ee.Image().byte().paint(Training_Points, "land_class").rename("land_class")


var stratified_points = classes.stratifiedSample({
      numPoints: 50,
      classBand: 'land_class',
      scale: 10,
      region: Training_Points,
      geometries: false,
      tileScale: 6
})

print(stratified_points, 'stratified_points')


//Create training data
var training_Stratified = RF_classified.select(bands).sampleRegions({
  collection: stratified_points,
  properties: ['land_class'],
  scale:10,
  tileScale:2
});


var bands = RF_classified.bandNames()
var numBands = bands.length()
var bandsWithClass = bands.add('land_class')
var classIndex = bandsWithClass.indexOf('land_class')

// Use .combine() to get a reducer capable of computing multiple stats on the input
var combinedReducer = ee.Reducer.mean().combine({
  reducer2: ee.Reducer.stdDev(),
  sharedInputs: true})

// Use .repeat() to get a reducer for each band and then use .group() to get stats by class
var repeatedReducer = combinedReducer.repeat(numBands).group(classIndex)

var stratified_points_Stats = training_Stratified.reduceColumns({
    selectors: bands.add('land_class'),
    reducer: repeatedReducer,
})

// Result is a dictionary, we do some post-processing to extract the results
var groups = ee.List(stratified_points_Stats.get('groups'))

var classNames = ee.List(['Water','Residential', 'Agricultural', 'Arbusti', 'BoschiMisti', 'Latifoglie','Conifere', 'BareSoil'])

var fc = ee.FeatureCollection(groups.map(function(item) {
  // Extract the means
  var values = ee.Dictionary(item).get('mean')
  var groupNumber = ee.Dictionary(item).get('group')
  var properties = ee.Dictionary.fromLists(bands, values)
  var withClass = properties.set('class', classNames.get(groupNumber))
  return ee.Feature(null, withClass)
}))

// Chart spectral signatures of training data
var options = {
  title: 'Average Spectral Signatures',
  hAxis: {title: 'Bands'},
  vAxis: {title: 'Reflectance', 
    viewWindowMode:'explicit',
    viewWindow: {
        max:6000,
        min:0
    }},
  lineWidth: 1,
  pointSize: 4,
  series: {
    0: {color: '105af0'},                                   
    1: {color: 'dc350a'}, 
    2: {color: 'caa712'}, 
    3: {color: 'b9ffa4'},
    4: {color: '369b47'},
    5: {color: '21ff2d'},
    6: {color: '275b25'},
    7: {color: 'f7e084'},   
}};

// Default band names don't sort propertly Instead, we can give a dictionary with labels for each band in the X-Axis
var bandDescriptions = {
  'B2': 'B2/Blue',
  'B3': 'B3/Green',
  'B4': 'B4/Red',
  'B5': 'B5/Red Edge 1',
  'B6': 'B5/Red Edge 2',
  'B7': 'B7/Red Edge 3',
  'B8': 'B8/NIR',
  'B8A': 'B8A/Red Edge 4',
  'B11': 'B11/SWIR-1',
  'B12': 'B12/SWIR-2'
}

// Create the chart and set options.
var chart = ui.Chart.feature.byProperty({
  features: fc,
  xProperties: bandDescriptions,
  seriesProperty: 'class'
})
.setChartType('ScatterChart')
.setOptions(options);

print(chart)

var classChart = function(land_class, label, color) {
  var options = {
  title: 'Spectral Signatures for ' + label + ' Class',
  hAxis: {title: 'Bands'},
  vAxis: {title: 'Reflectance', 
    viewWindowMode:'explicit',
    viewWindow: {
        max:6000,
        min:0
    }},
  lineWidth: 1,
  pointSize: 4,  
  };

  var fc = training_Stratified.filter(ee.Filter.eq('land_class', land_class))
  var chart = ui.Chart.feature.byProperty({
  features: fc,
  xProperties: bandDescriptions,
  })
.setChartType('ScatterChart')
.setOptions(options);

print(chart)
}
classChart(0, 'Water')
classChart(1, 'Residential')
classChart(2, 'Agricultural')
classChart(3, 'Arbusti')
classChart(4, 'BoschiMisti')
classChart(5, 'Latifoglie')
classChart(6, 'Conifere')
classChart(7, 'BareSoil')

我收到错误信息:

生成图表时出错:图像。选择:图案“B1”与任何 乐队。

我不明白问题出在哪里,因为我之前使用了相同的脚本来绘制训练数据的直方图,而且效果很好。