////////////////////////////////////////
///////////// PREPARE IMAGE ////////////
////////////////////////////////////////

// Center map on Guatemala study area
Map.centerObject(guatemala_mar);

// Establish function for masking clouds from Sentinel-2 image collection
function maskS2clouds(image) {
  var qa = image.select('QA60');

  // Bits 10 and 11 are clouds and cirrus, respectively.
  var cloudBitMask = 1 << 10;
  var cirrusBitMask = 1 << 11;

  // Both flags should be set to zero, indicating clear conditions.
  var mask = qa.bitwiseAnd(cloudBitMask).eq(0)
      .and(qa.bitwiseAnd(cirrusBitMask).eq(0));

  return image.updateMask(mask).divide(10000);
}

// Load image collection of Sentinel-2 surface reflectance data
var sentinel_collection = ee.ImageCollection('COPERNICUS/S2_SR')
                  .filterDate('2020-01-01', '2020-05-31')
                  // Pre-filter to get less cloudy granules.
                  .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 20))
                  .map(maskS2clouds);

// Establish variable for visualizing data on screen (true color)
var median_vis = {
  min: 0.0,
  max: 0.2,
  bands: ['B4_median', 'B3_median', 'B2_median'],
};

// Reduce Sentinel image collection to single image
var sentinel_image = sentinel_collection.reduce(ee.Reducer.median());

// Clip Sentinel image to Guatemala boundary
var guatemala_image = sentinel_image.clip(guatemala_mar);

// Display Guatemala image
Map.addLayer(guatemala_image, median_vis, "Guatemala Image");


////////////////////////////////////////
///////////// FILTER IMAGE /////////////
////////////////////////////////////////

// Create "NDWI" layer to mask out water features
var ndwi_layer = guatemala_image.normalizedDifference(['B3_median', 'B8_median']);

// Mask water out of Sentinel image using NDWI layer
var guatemala_ndwi = guatemala_image.updateMask(ndwi_layer.lte(0.0));
//Map.addLayer(guatemala_ndwi, median_vis, 'NDWI mask applied');

// Create "elevation" layer to mask out high-elevation features
var srtm = ee.Image('USGS/SRTMGL1_003');
var elevation_layer = srtm.select('elevation');

// Mask high elevations out of Sentinel image using elevation layer
var guatemala_elevation = guatemala_ndwi.updateMask(elevation_layer.lte(20.0));
//Map.addLayer(guatemala_elevation, median_vis, 'Elevation mask applied');

// Create "NDMI" layer to mask out non-mangrove candidates
var ndmi_layer = guatemala_image.normalizedDifference(['B12_median', 'B3_median']);

// Mask non-mangrove candidates out of Sentinel image using NDMI layer
var guatemala_ndmi = guatemala_elevation.updateMask(ndmi_layer.lte(0.1));
//Map.addLayer(guatemala_ndmi, median_vis, "NDMI mask applied");


////////////////////////////////////////
/////////// CLASSIFY IMAGE /////////////
////////////////////////////////////////

// Designate which spectral bands to include in the classification
var bands = ['B8_median', 'B4_median', 'B3_median', 'B2_median'];

// Train the classifier using the training points
var training = guatemala_image.select(bands).sampleRegions({
  collection: guatemala_training,
  properties: ['class'],
  scale: 10
});

// Establish the classifier
var classifier = ee.Classifier.smileRandomForest(200)
    .train({
      features: training,
      classProperty: 'class',
      inputProperties: bands
    });

// Classify the image
var guatemala_classified = guatemala_ndmi.select(bands).classify(classifier);

// Mask out all non-mangrove pixels from the classified thematic map
var guatemala_class_mask = guatemala_classified.updateMask(guatemala_classified.lte(0));

// Display the preliminary classified thematic map
//Map.addLayer(guatemala_class_mask, {palette: ('FF0000')}, 'Preliminary Guatemala Mangrove Classification');


////////////////////////////////////////
//////// REFINE CLASSIFICATION /////////
////////////////////////////////////////

// Display Bunting mangrove layer for reference
//var guatemala_bunting_2016 = guatemala_bunting.reduceToImage({
//    properties: ['pxlval'],
//    reducer: ee.Reducer.first()
//});
//Map.addLayer(guatemala_bunting_2016, {palette: ('00FF00')}, 'Bunting 2016');
//Map.addLayer(guatemala_mang_training, {palette: ('00FF00')}, 'Guatemala Mangrove Training Points');

// Make sure that the manual adjustment geometry is of type FeatureCollection
var guatemala_include = ee.FeatureCollection(guatemala_include);

// Dissolve the polygons in the Feature Collection, so the overlapping polygons
// don't "cancel each other out"
var guatemala_include = guatemala_include.union();

// Clip the classification to the Feature Collection of manual adjustments, and display
var guatemala_mangroves = guatemala_class_mask.clip(guatemala_include);
Map.addLayer(guatemala_mangroves, {palette: ('00FF00')}, 'Guatemala MAR Mangroves');


////////////////////////////////////////
//////////// CALCULATE AREA ////////////
////////////////////////////////////////

// Calculate mangrove area for Guatemala, and print to console
var guatemala_mangrove_area = guatemala_mangroves.reduceRegion({
    reducer: ee.Reducer.count(),
    geometry: guatemala_include,
    scale: 10,
    maxPixels: 1e9
});
var guatemala_mangrove_area = ee.Number(guatemala_mangrove_area.get('classification')).divide(10000);
var guatemala_mangrove_area = ee.Number(guatemala_mangrove_area).format();
print('Guatemala MAR mangrove area (km2) as of 2020:', guatemala_mangrove_area);


////////////////////////////////////////
////////////// EXPORT MAP //////////////
////////////////////////////////////////

// Convert Guatemala mangrove raster to polygon
var guatemala_mangroves_polygon = guatemala_mangroves.toInt().reduceToVectors({
  geometry: guatemala_include,
  crs: guatemala_mangroves.projection(),
  scale: 10,
  geometryType: 'polygon',
  eightConnected: false,
  maxPixels: 1e9
});

// Export Guatemala mangrove polygon to Google Drive
//Export.table.toDrive({
//  collection: guatemala_mangroves_polygon,
//  description:'guatemala_mar_mangroves',
//  fileFormat: 'KMZ'
//});


////////////////////////////////////////
////////////// VALIDATION //////////////
////////////////////////////////////////

// Generate random points for "mangrove presence" validation, and export to Google Drive
// I will generate "mangrove absence" buffer and points in GIS program
var guatemala_validation_points_presence = ee.FeatureCollection.randomPoints(guatemala_mangroves_polygon, 100);
//Export.table.toDrive({collection: guatemala_validation_points_presence, fileFormat: 'GeoJSON'});