Creating multilayered classification map on Google Earth Engine?

Question

I've been working on a classification scheme, and have 6 different classes i wish to map. Everything has been already done in terms of finding the classifications. the only thing I am struggling on now is how to import all 6 classes (6 classes but 7 vars) onto the same map, without them going on top of one another.

My end goal is for it to look like this:

Code used:

var image = ee.Image(landsat.filterDate ('2018-01-01', '2018-03-01').filterBounds(point).sort('CLOUD_COVER').first());

//print image 
print('a landsat scene', image);

//define parameters

var green = image.select('B3');
var swi = image.select('B6');
var mndwi = green.subtract(swi).divide(green.add(swi)).rename('MNDWI');

var mndwipara = {min: 0, max: 0.7, palette: ['white', 'blue']};


Map.addLayer(mndwi, mndwipara, 'MNDWI');


//apply threshold to select only positive pixels 
var lake_mask= mndwi.gt(0);
Map.addLayer(lake_mask);

//image reducer
var meanDictionary =image.reduceRegion({
reducer: ee.Reducer.mean(),
geometry: image.geometry(),
scale: 30,
maxPixels: 1e9
});
// The result is a Dictionary.  Print it.
print(meanDictionary);

//classification attempt - scum
var scum=image.expression(
'(nir)*0 + (nir < 0.018)*1', {
'nir': image.select('B5'),
'red': image.select ('B4'),
'green': image.select('B3'),
});

 //classification attempt - sediment
var sediment=image.expression(
'(nir)*0 + (nir > 0.018 && red > green && green/nir < 1.3 && red/green> nir/red)*1', {
'nir': image.select('B5'),
'red': image.select ('B4'),
'green': image.select('B3'),
});

//classification attempt - lowbiomass
var lowbiomass=image.expression(
'(nir)*0 + (nir > 0.018 && red < green && green > 0.065 && nir < red)*1', {
'nir': image.select('B5'),
'red': image.select ('B4'),
'green': image.select('B3'),
});


//classification attempt-scum
var scum=image.expression(
'(nir)*0 + (nir > 0.018 && red < green && green > 0.065 && nir > red && nir/red > 4.07)*1', {
'nir': image.select('B5'),
'red': image.select ('B4'),
'green': image.select('B3'),
  });

 //classifcation attempt bleached scum
  var bleached_scum=image.expression(
  '(nir)*0 + (nir > 0.018 && red > green && green/nir > 1.3 && green > 0.065)*1', {
'nir': image.select('B5'),
'red': image.select ('B4'),
'green': image.select('B3'),
});

//classification attempt - microphytobenthos
var microphytobenthos=image.expression(
'(nir)*0 + (nir > 0.018 && red > green && green/nir < 1.3 && red/green< nir/red)*1', {
'nir': image.select('B5'),
'red': image.select ('B4'),
'green': image.select('B3'),
});

//classification attempt - highbiomass
var highbiomass=image.expression(
'(nir)*0 + (nir > 0.018 && red < green && green > 0.065 && nir > red && nir/red < 4.07)*1', {
'nir': image.select('B5'),
'red': image.select ('B4'),
'green': image.select('B3'),
 });

Answer 1

You should try to create images with classification values and reduce them to a unique image. Something like:

/*
lake = 1
scum = 2
bleached scum = 3
microphytobenthos = 4
highbiomass = 5
*/

var lake_mask_ = ee.Image(1).mask(lake_mask).toInt();
var scum_ = ee.Image(2).mask(lake_mask.mask(scum)).toInt();
var bleached_scum_ = ee.Image(3).mask(lake_mask.mask(bleached_scum)).toInt();
var microphytobenthos_ = ee.Image(4).mask(lake_mask.mask(microphytobenthos)).toInt();
var scum_ = ee.Image(5).mask(lake_mask.mask(highbiomass)).toInt();

var test = ee.ImageCollection([lake_mask_,scum_,bleached_scum_,microphytobenthos_,scum_]);

var test = test.reduce(ee.Reducer.max());

print(test);  
Map.addLayer(test,{min: 1, max: 5, palette: ['0000FF', 'F4FF0B','430081','FA0007','1BCFFF']},'Classification');

Link to example: https://code.earthengine.google.com/eb49d6959f5ac8f0711751ab01e87001

Also, mask clouds first