ERROR while making a LULC map classification in Google Earth Engine

Question

I am relatively new to utilizing the Google Earth Engine (GEE) platform, although I possess some experience in generating Land Use and Land Cover (LULC) maps using GIS software. Recently, I encountered challenges while attempting to create a LULC map using Landsat 5 and Landsat 8 imagery within Google Earth Engine (GEE).

I specified six classes for the classification, yet the resulting classified images only display four.

var images= L5.filterBounds(roi)
              .filterMetadata('CLOUD_COVER','less_than',10)
              .filterDate('2000-01-01', '2000-12-31')
              .sort('CLOUD_COVER', true);
              
              
              
  print(images)
var image = images.median().clip(roi);
var visualization = {
  bands: ['B3', 'B2', 'B1'],
  min: 0.0,
  max: 0.4, 
  gamma: 1.40,
};
 Map.centerObject(roi, 10);
 Map.addLayer(image, visualization, 'True Color (321)');
 


// Band map for index calculation
var bandMap = {
  BLUE: image.select('B1'),
  GREEN: image.select('B2'),
  RED: image.select('B3'),
  NIR: image.select('B4'),
  SWIR1: image.select('B5'),
  SWIR2: image.select('B7')
};


// eternal bands
var indices = ee.Image([
  { name: 'EVI', formula: '(2.5 * (NIR - RED)) / (NIR + 6 * RED - 7.5 * BLUE + 1)' },
  { name: 'NBR', formula: '(NIR - SWIR2) / (NIR + SWIR2)' },
  { name: 'NDMI', formula: '(NIR - SWIR1) / (NIR + SWIR1)' },
  { name: 'NDWI', formula: '(GREEN - NIR) / (GREEN + NIR)' },
  { name: 'NDBI', formula: '(SWIR1 - NIR) / (SWIR1 + NIR)' },
  { name: 'NDBaI', formula: '(SWIR1 - SWIR2) / (SWIR1 + SWIR2)' },
].map(function(dict){
  var indexImage = image.expression(dict.formula, bandMap).rename(dict.name);
  return indexImage;
}));

// Add index & SRTM to image
image = image.addBands(indices).addBands(srtm.clip(roi));

// samples
  
var training = Water1.merge(Builtup1).merge(Barrenland1).merge(Marsh_ricefield1).merge(Natural_plantation_forest1).merge(Floodedvegetation1);
// Split samples to train and test per class

var bands = ['B1','B2','B3','B4','B5','B6','B7', 'EVI', 'NBR', 'NDMI', 'NDWI', 'NDBI', 'NDBaI', 'elevation'];
var input = image.select(bands);
var label = 'Class';
var trainImage= input.sampleRegions({
  collection:training, 
  // properties:[label], 
  scale:30});
print(training);

var trainingData = trainImage.randomColumn();
var trainSet = trainingData.filter(ee.Filter.lessThan('random',0.8));
var testSet= trainingData.filter(ee.Filter.greaterThanOrEquals('random',0.8));

// classification 

// var  classifier = ee.Classifier.smileCart().train(trainSet, label, bands);
var classifier = ee.Classifier.smileRandomForest(64).train({features:trainSet,
  classProperty: 'Class',
  inputProperties:bands
  
});
//classify the landsat image
var classified = image.classify(classifier);

// difine visulization


// Map.addLayer(classified,{min:0, max:4, palette:['#0b9fd6','#d6d6d6','#2eb708','#d63000','#eae81e','#b7ff19','#d6b054','#ffa37e']},'Study 2000' );

// Map.addLayer(classified,{min:0, max:4, palette:['#08a8d6', 'F08080', 'D2B48C', '90EE90',  '228B22', '808000']},'Study 2000' );

Map.addLayer(classified,{min:0, max:4, palette:['blue', 'blue', 'red', 'brown',  'yellow', 'green']},'Study 2000' );

Answer 1

Your current visualization parameters are only set to view min: 0 to max:4 classes. Could you try to expand that range and visualize again:

  Map.addLayer(classified, 
             {min: 0, max: 6, 
              palette:['blue', 'blue', 'red', 'brown',  'yellow', 'green']},'Study 2000' );