Create a probability map

using a random forest classifier

var referenceData = ee.FeatureCollection("users/servirmekong/cambodia/paddyRice");

var rice = referenceData.filter(ee.Filter.eq("land_class",1));
var nonrice = referenceData.filter(ee.Filter.eq("land_class",0));

// import feature collection
var table = ee.FeatureCollection("users/servirmekong/countries/KHM_adm1");
// import surface reflectance composite
var composites = ee.ImageCollection("projects/servir-mekong/yearlyComposites");

// filter for province
var province = "Batdâmbâng";

// select province from feature collection
var myProvince = table.filter(ee.Filter.eq("NAME_1","Batdâmbâng"));

// filter image for date
var image = ee.Image(composites.filterDate("2018-01-01","2018-12-31").first());

// add image to map
Map.addLayer(image.clip(myProvince),{min:0,max:3000,bands:"red,green,blue"},"2018");

Map.addLayer(rice.draw("yellow"),{},"rice");
Map.addLayer(nonrice.draw("black"),{},"non rice");

var trainingSample = image.sampleRegions(referenceData,["land_class"],30);

var bandNames = image.bandNames();
var classifier = ee.Classifier.randomForest(100,0).setOutputMode('PROBABILITY').train(trainingSample,"land_class",bandNames);

var classification = image.classify(classifier).multiply(100);

Map.addLayer(classification.clip(myProvince),{min:20,max:80,palette:"white,gray,black"},"primitive");

link