GEE Tutorial #38 - How to use Cloud Optimized GeoTIFF with Earth Engine

Subscribe to my newsletter and never miss my upcoming articles

This tutorial shows you load Cloud Optimized GeoTIFF as Earth Engine Image and ImageCollection. A Cloud Optimized GeoTIFF (COG) is a regular GeoTIFF file, aimed at being hosted on a HTTP file server, with an internal organization that enables more efficient workflows on the cloud. It does this by leveraging the ability of clients issuing HTTP GET range requests to ask for just the parts of a file they need. More information about COG can be found at

Some publicly available Cloud Optimized GeoTIFFs:





Step-by-step tutorial

Loading a Cloud Optimized GeoTIFF as an ee.Image

Note that only Cloud Optimized GeoTIFF hosted on Google Cloud Storage is supported. Other cloud storage providers (e.g., AWS) are not supported.

In this example, we are going to use the Planet Disaster Data.

import ee
import geemap
Map = geemap.Map()
URL = ''
# URL = 'gs://pdd-stac/disasters/hurricane-harvey/0831/20170831_172754_101c_3B_AnalyticMS.tif'
image = geemap.load_GeoTIFF(URL)
vis = {

Map.addLayer(image, vis, 'Cloud Image')
Map.centerObject(image.geometry(), 12)

Loading a list of Cloud Optimized GeoTIFFs as an ee.ImageCollection

In this example, we are going to use the Landsat data hosted on Google Cloud.

Map = geemap.Map()
B3 = 'gs://gcp-public-data-landsat/LC08/01/044/034/LC08_L1TP_044034_20131228_20170307_01_T1/LC08_L1TP_044034_20131228_20170307_01_T1_B3.TIF'
B4 = 'gs://gcp-public-data-landsat/LC08/01/044/034/LC08_L1TP_044034_20131228_20170307_01_T1/LC08_L1TP_044034_20131228_20170307_01_T1_B4.TIF'
B5 = 'gs://gcp-public-data-landsat/LC08/01/044/034/LC08_L1TP_044034_20131228_20170307_01_T1/LC08_L1TP_044034_20131228_20170307_01_T1_B5.TIF'
URLs = [B3, B4, B5]
collection = geemap.load_GeoTIFFs(URLs)
image = collection.toBands().rename(['Green', 'Red', 'NIR']).selfMask()
vis = {
    'bands': ['NIR', 'Red', 'Green'],
    'min': 100,
    'max': 12000,
    'gamma': 0.8

Map.addLayer(image, vis, 'Image')
Map.centerObject(image.geometry(), 8)
ndvi = image.normalizedDifference(['NIR', 'Red'])
ndvi_vis = {
    'min': 0, 
    'max': 1, 
    'palette': ['blue', 'green']
Map.addLayer(ndvi, {}, 'NDVI')

No Comments Yet