Universal Code Hub Upgrade

GEE Code Hub

Google Earth Engine — every dataset, every recipe, every advanced workflow.

Dataset Code Explorer

Every dataset in the GEE Data Hub — with detailed metadata, ready-to-run JS & Python code, and advanced analysis methods.

GEE Code Library — Ready-to-Run Recipes

5 ready-to-run snippet(s) · curated with sample data, dataset sources & use cases

Vegetation🎓 Intermediate

Landsat 8/9 NDVI Annual TrendCompute mean NDVI per year for a region using Landsat 8/9 Collection 2 surface reflectance, and chart the trend.

#ndvi#landsat#time-series#vegetation

VegetationIntermediate

Landsat 8/9 NDVI Annual Trend

Compute mean NDVI per year for a region using Landsat 8/9 Collection 2 surface reflectance, and chart the trend.

🎯 Use Case

Monitor vegetation greening / browning, deforestation, or crop health across years.

👥 Audience

Remote sensing students, environmental researchers, agricultural analysts.

Data to use with this code

Landsat 8/9 C2 L2 (GEE Catalog) ↗

roi.txt · asset-id

USDOS/LSIB_SIMPLE/2017 (filter by country_na == "Bangladesh")

Or draw your own polygon in the Code Editor.

gee-js-ndvi-trend.js

// === Landsat 8/9 Annual NDVI Trend ===
var roi = ee.FeatureCollection('USDOS/LSIB_SIMPLE/2017')
  .filter(ee.Filter.eq('country_na', 'Bangladesh')).geometry();

var years = ee.List.sequence(2015, 2024);

function maskL89(img) {
  var qa = img.select('QA_PIXEL');
  var mask = qa.bitwiseAnd(1 << 3).eq(0).and(qa.bitwiseAnd(1 << 4).eq(0));
  return img.updateMask(mask).multiply(0.0000275).add(-0.2);
}

var ndviPerYear = ee.FeatureCollection(years.map(function (y) {
  y = ee.Number(y);
  var coll = ee.ImageCollection('LANDSAT/LC08/C02/T1_L2')
    .merge(ee.ImageCollection('LANDSAT/LC09/C02/T1_L2'))
    .filterBounds(roi)
    .filterDate(ee.Date.fromYMD(y, 1, 1), ee.Date.fromYMD(y, 12, 31))
    .map(maskL89);
  var ndvi = coll.map(function (i) {
    return i.normalizedDifference(['SR_B5', 'SR_B4']).rename('NDVI');
  }).mean();
  var mean = ndvi.reduceRegion({
    reducer: ee.Reducer.mean(), geometry: roi, scale: 300,
    bestEffort: true, tileScale: 4, maxPixels: 1e10
  }).get('NDVI');
  return ee.Feature(null, { year: y, ndvi: mean });
}));

print(ui.Chart.feature.byFeature(ndviPerYear, 'year', 'ndvi')
  .setOptions({ title: 'Mean Annual NDVI', hAxis: { format: '####' } }));

Map.centerObject(roi, 6);
Map.addLayer(ndviPerYear, {}, 'Year stats');

📤 Expected Outputs

Annual NDVI line chart
ROI map layer

#ndvi#landsat#time-series#vegetation

Climate🎓 Intermediate

MODIS LST — Urban Heat IslandMap mean day-time Land Surface Temperature and detect urban heat islands using MOD11A2.

#lst#modis#uhi#climate

ClimateIntermediate

MODIS LST — Urban Heat Island

Map mean day-time Land Surface Temperature and detect urban heat islands using MOD11A2.

🎯 Use Case

Urban planning, heat-wave studies, climate vulnerability mapping.

👥 Audience

Urban planners, climate researchers, MSc/PhD students.

Data to use with this code

MOD11A2 8-day LST ↗

city.geojson · asset-id

FAO/GAUL/2015/level2 (filter ADM2_NAME)

gee-js-lst-uhi.js

var city = ee.FeatureCollection('FAO/GAUL/2015/level2')
  .filter(ee.Filter.eq('ADM2_NAME', 'Dhaka')).geometry();

var lst = ee.ImageCollection('MODIS/061/MOD11A2')
  .filterDate('2023-04-01', '2023-09-30')
  .select('LST_Day_1km')
  .mean().multiply(0.02).subtract(273.15)
  .clip(city).rename('LST_C');

Map.centerObject(city, 10);
Map.addLayer(lst, { min: 28, max: 42, palette: ['blue','yellow','red'] }, 'Mean LST (°C)');

var stats = lst.reduceRegion({
  reducer: ee.Reducer.percentile([10, 50, 90]),
  geometry: city, scale: 1000, bestEffort: true, tileScale: 4, maxPixels: 1e9
});
print('LST percentiles', stats);

📤 Expected Outputs

LST map (°C)
P10/P50/P90 statistics

#lst#modis#uhi#climate

Hydrology🎓 Advanced

Sentinel-1 SAR Flood MappingDetect flood extent by differencing pre- and post-event Sentinel-1 VV backscatter.

#sar#sentinel-1#flood#disaster

HydrologyAdvanced

Sentinel-1 SAR Flood Mapping

Detect flood extent by differencing pre- and post-event Sentinel-1 VV backscatter.

🎯 Use Case

Rapid flood damage assessment, disaster response, insurance.

👥 Audience

Disaster response teams, hydrologists, humanitarian GIS analysts.

Data to use with this code

Sentinel-1 GRD ↗

gee-js-flood-sar.js

var roi = ee.Geometry.Rectangle([89.0, 23.5, 90.5, 24.7]);
var before = ee.ImageCollection('COPERNICUS/S1_GRD')
  .filterBounds(roi).filterDate('2022-06-01','2022-06-15')
  .filter(ee.Filter.eq('instrumentMode','IW'))
  .filter(ee.Filter.listContains('transmitterReceiverPolarisation','VV'))
  .select('VV').median();
var after = ee.ImageCollection('COPERNICUS/S1_GRD')
  .filterBounds(roi).filterDate('2022-06-25','2022-07-05')
  .select('VV').median();

var diff = before.subtract(after);
var flood = diff.gt(3);  // tune threshold

Map.centerObject(roi, 9);
Map.addLayer(before, {min:-25,max:0}, 'Before VV');
Map.addLayer(after,  {min:-25,max:0}, 'After VV');
Map.addLayer(flood.updateMask(flood), {palette:['cyan']}, 'Flooded');

📤 Expected Outputs

Pre/post backscatter layers
Binary flood mask

#sar#sentinel-1#flood#disaster

Classification🎓 Advanced

Random Forest LULC ClassificationSupervised LULC mapping with Sentinel-2 bands and a Random Forest classifier (50 trees).

#classification#random-forest#sentinel-2#lulc

ClassificationAdvanced

Random Forest LULC Classification

Supervised LULC mapping with Sentinel-2 bands and a Random Forest classifier (50 trees).

🎯 Use Case

Land use/land cover mapping, change detection baselines.

👥 Audience

Researchers familiar with supervised ML and training-sample collection.

Data to use with this code

Sentinel-2 SR Harmonized ↗

gee-js-lulc-rf.js

// Add training points beforehand: Urban=0, Veg=1, Water=2, Bare=3 (FeatureCollection 'training')
var roi = training.geometry().bounds();
var img = ee.ImageCollection('COPERNICUS/S2_SR_HARMONIZED')
  .filterBounds(roi).filterDate('2024-01-01','2024-12-31')
  .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 15))
  .median().select(['B2','B3','B4','B8','B11','B12']);

var samples = img.sampleRegions({collection: training, properties: ['class'], scale: 10});
var rf = ee.Classifier.smileRandomForest(50).train(samples, 'class', img.bandNames());
var classified = img.classify(rf);
Map.addLayer(classified, {min:0,max:3,palette:['red','green','blue','tan']}, 'LULC');

📤 Expected Outputs

LULC raster (4 classes)

#classification#random-forest#sentinel-2#lulc

Visualization🎓 Beginner

geemap Quick Sentinel-2 MapInitialize Earth Engine, fetch a cloud-free Sentinel-2 composite, and view in geemap.

#geemap#sentinel-2#colab

VisualizationBeginner

geemap Quick Sentinel-2 Map

Initialize Earth Engine, fetch a cloud-free Sentinel-2 composite, and view in geemap.

🎯 Use Case

Quick visual reconnaissance of an area before deeper analysis.

👥 Audience

Beginners moving from JS GEE to Python Colab.

gee-py-quickmap.py

!pip install -q earthengine-api geemap
import ee, geemap
ee.Authenticate(); ee.Initialize(project='your-project')

roi = ee.Geometry.Rectangle([90.3, 23.7, 90.5, 23.9])
img = (ee.ImageCollection('COPERNICUS/S2_SR_HARMONIZED')
       .filterBounds(roi).filterDate('2024-01-01','2024-12-31')
       .filter(ee.Filter.lt('CLOUDY_PIXEL_PERCENTAGE', 10))
       .median())

m = geemap.Map(); m.centerObject(roi, 12)
m.addLayer(img, {'bands':['B4','B3','B2'],'min':0,'max':3000}, 'S2 RGB')
m

📤 Expected Outputs

Interactive RGB map in Colab

#geemap#sentinel-2#colab

Dataset CatalogSentinel, Landsat, MODIS, GEDI Use CasesTemplates by application Flood ModellingSAR + DEM hydrology

All Credit @ Al Jubaer | aljubaer.com