ee.ImageCollection.reduceToImage

  • reduceToImage transforms an image collection into a single image by applying a reducer to pixel-intersecting features.

  • It uses specified properties from each feature within the collection for the reduction process.

  • Users define a reducer (e.g., mean, median) to combine intersecting feature properties into a final pixel value in the output image.

  • This function is helpful for tasks like calculating mean cloud cover across a collection of satellite images, as shown in the provided example.

 Creates an image from a feature collection by applying a reducer over the selected properties of all the features that intersect each pixel.

UsageReturns
ImageCollection.reduceToImage(properties, reducer)Image
ArgumentTypeDetails
this: collectionFeatureCollectionFeature collection to intersect with each output pixel.
propertiesListProperties to select from each feature and pass into the reducer.
reducerReducerA Reducer to combine the properties of each intersecting feature into a final result to store in the pixel.

Examples

Code Editor (JavaScript)

var col = ee.ImageCollection('LANDSAT/LC08/C02/T1_TOA')
  .filterBounds(ee.Geometry.BBox(-124.0, 43.2, -116.5, 46.3))
  .filterDate('2021', '2022');

// Image visualization settings.
var visParams = {
  bands: ['B4', 'B3', 'B2'],
  min: 0.01,
  max: 0.25
};
Map.addLayer(col.mean(), visParams, 'RGB mean');

// Reduce the geometry (footprint) of images in the collection to an image.
// Image property values are applied to the pixels intersecting each
// image's geometry and then a per-pixel reduction is performed according
// to the selected reducer. Here, the image cloud cover property is assigned
// to the pixels intersecting image geometry and then reduced to a single
// image representing the per-pixel mean image cloud cover.
var meanCloudCover = col.reduceToImage({
  properties: ['CLOUD_COVER'],
  reducer: ee.Reducer.mean()
});

Map.setCenter(-119.87, 44.76, 6);
Map.addLayer(meanCloudCover, {min: 0, max: 50}, 'Cloud cover mean');

Python setup

See the Python Environment page for information on the Python API and using geemap for interactive development.

import ee
import geemap.core as geemap

Colab (Python)

col = (
    ee.ImageCollection('LANDSAT/LC08/C02/T1_TOA')
    .filterBounds(ee.Geometry.BBox(-124.0, 43.2, -116.5, 46.3))
    .filterDate('2021', '2022')
)

# Image visualization settings.
vis_params = {'bands': ['B4', 'B3', 'B2'], 'min': 0.01, 'max': 0.25}
m = geemap.Map()
m.add_layer(col.mean(), vis_params, 'RGB mean')

# Reduce the geometry (footprint) of images in the collection to an image.
# Image property values are applied to the pixels intersecting each
# image's geometry and then a per-pixel reduction is performed according
# to the selected reducer. Here, the image cloud cover property is assigned
# to the pixels intersecting image geometry and then reduced to a single
# image representing the per-pixel mean image cloud cover.
mean_cloud_cover = col.reduceToImage(
    properties=['CLOUD_COVER'], reducer=ee.Reducer.mean()
)

m.set_center(-119.87, 44.76, 6)
m.add_layer(mean_cloud_cover, {'min': 0, 'max': 50}, 'Cloud cover mean')
m