Announcement: All noncommercial projects registered to use Earth Engine before
April 15, 2025 must
verify noncommercial eligibility to maintain Earth Engine access.
ee.FeatureCollection.kriging
Stay organized with collections
Save and categorize content based on your preferences.
Returns the results of sampling a Kriging estimator at each pixel.
| Usage | Returns | FeatureCollection.kriging(propertyName, shape, range, sill, nugget, maxDistance, reducer) | Image |
| Argument | Type | Details | this: collection | FeatureCollection | Feature collection to use as source data for the estimation. |
propertyName | String | Property to be estimated (must be numeric). |
shape | String | Semivariogram shape (one of {exponential, gaussian, spherical}). |
range | Float | Semivariogram range, in meters. |
sill | Float | Semivariogram sill. |
nugget | Float | Semivariogram nugget. |
maxDistance | Float, default: null | Radius which determines which features are included in each pixel's computation, in meters. Defaults to the semivariogram's range. |
reducer | Reducer, default: null | Reducer used to collapse the 'propertyName' value of overlapping points into a single value. |
Examples
Code Editor (JavaScript)
/**
* This example generates an interpolated surface using kriging from a
* FeatureCollection of random points that simulates a table of air temperature
* at ocean weather buoys.
*/
// Average air temperature at 2m height for June, 2020.
var img = ee.Image('ECMWF/ERA5/MONTHLY/202006')
.select(['mean_2m_air_temperature'], ['tmean']);
// Region of interest: South Pacific Ocean.
var roi = ee.Geometry.Polygon(
[[[-156.053, -16.240],
[-156.053, -44.968],
[-118.633, -44.968],
[-118.633, -16.240]]], null, false);
// Sample the mean June 2020 temperature surface at random points in the ROI.
var tmeanFc = img.sample(
{region: roi, scale: 25000, numPixels: 50, geometries: true}); //250
// Generate an interpolated surface from the points using kriging; parameters
// are set according to interpretation of an unshown semivariogram. See section
// 2.1 of https://doi.org/10.14214/sf.369 for information on semivariograms.
var tmeanImg = tmeanFc.kriging({
propertyName: 'tmean',
shape: 'gaussian',
range: 2.8e6,
sill: 164,
nugget: 0.05,
maxDistance: 1.8e6,
reducer: ee.Reducer.mean()
});
// Display the results on the map.
Map.setCenter(-137.47, -30.47, 3);
Map.addLayer(tmeanImg, {min: 279, max: 300}, 'Temperature (K)');
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)
# This example generates an interpolated surface using kriging from a
# FeatureCollection of random points that simulates a table of air temperature
# at ocean weather buoys.
# Average air temperature at 2m height for June, 2020.
img = ee.Image('ECMWF/ERA5/MONTHLY/202006').select(
['mean_2m_air_temperature'], ['tmean']
)
# Region of interest: South Pacific Ocean.
roi = ee.Geometry.Polygon(
[[
[-156.053, -16.240],
[-156.053, -44.968],
[-118.633, -44.968],
[-118.633, -16.240],
]],
None,
False,
)
# Sample the mean June 2020 temperature surface at random points in the ROI.
tmean_fc = img.sample(region=roi, scale=25000, numPixels=50, geometries=True)
# Generate an interpolated surface from the points using kriging parameters
# are set according to interpretation of an unshown semivariogram. See section
# 2.1 of https://doi.org/10.14214/sf.369 for information on semivariograms.
tmean_img = tmean_fc.kriging(
propertyName='tmean',
shape='gaussian',
range=2.8e6,
sill=164,
nugget=0.05,
maxDistance=1.8e6,
reducer=ee.Reducer.mean(),
)
# Display the results on the map.
m = geemap.Map()
m.set_center(-137.47, -30.47, 3)
m.add_layer(
tmean_img,
{'min': 279, 'max': 300, 'min': 279, 'max': 300},
'Temperature (K)',
)
m
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2023-10-06 UTC.
[null,null,["Last updated 2023-10-06 UTC."],[[["\u003cp\u003e\u003ccode\u003ekriging()\u003c/code\u003e interpolates values across a FeatureCollection using specified Kriging parameters to generate an Image.\u003c/p\u003e\n"],["\u003cp\u003eIt estimates values for each pixel based on the spatial correlation of a numeric property within the input FeatureCollection.\u003c/p\u003e\n"],["\u003cp\u003eThe interpolation process is guided by a semivariogram model defined by \u003ccode\u003eshape\u003c/code\u003e, \u003ccode\u003erange\u003c/code\u003e, \u003ccode\u003esill\u003c/code\u003e, and \u003ccode\u003enugget\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eUsers can specify a search radius (\u003ccode\u003emaxDistance\u003c/code\u003e) and a reducer to handle overlapping points (\u003ccode\u003ereducer\u003c/code\u003e).\u003c/p\u003e\n"]]],["The `kriging` method interpolates a surface from a `FeatureCollection` by sampling a Kriging estimator at each pixel, returning an `Image`. Key parameters include: `propertyName` (numeric property to estimate), `shape` (semivariogram shape), `range`, `sill`, and `nugget` (semivariogram values). `maxDistance` limits feature inclusion in pixel calculations. An optional `reducer` handles overlapping points. Example demonstrates creating a temperature surface from sampled points, setting Kriging parameters, and visualizing the result.\n"],null,["# ee.FeatureCollection.kriging\n\nReturns the results of sampling a Kriging estimator at each pixel.\n\n\u003cbr /\u003e\n\n| Usage | Returns |\n|------------------------------------------------------------------------------------------------------|---------|\n| FeatureCollection.kriging`(propertyName, shape, range, sill, nugget, `*maxDistance* `, `*reducer*`)` | Image |\n\n| Argument | Type | Details |\n|--------------------|------------------------|------------------------------------------------------------------------------------------------------------------------------------|\n| this: `collection` | FeatureCollection | Feature collection to use as source data for the estimation. |\n| `propertyName` | String | Property to be estimated (must be numeric). |\n| `shape` | String | Semivariogram shape (one of {exponential, gaussian, spherical}). |\n| `range` | Float | Semivariogram range, in meters. |\n| `sill` | Float | Semivariogram sill. |\n| `nugget` | Float | Semivariogram nugget. |\n| `maxDistance` | Float, default: null | Radius which determines which features are included in each pixel's computation, in meters. Defaults to the semivariogram's range. |\n| `reducer` | Reducer, default: null | Reducer used to collapse the 'propertyName' value of overlapping points into a single value. |\n\nExamples\n--------\n\n### Code Editor (JavaScript)\n\n```javascript\n/**\n * This example generates an interpolated surface using kriging from a\n * FeatureCollection of random points that simulates a table of air temperature\n * at ocean weather buoys.\n */\n\n// Average air temperature at 2m height for June, 2020.\nvar img = ee.Image('ECMWF/ERA5/MONTHLY/202006')\n .select(['mean_2m_air_temperature'], ['tmean']);\n\n// Region of interest: South Pacific Ocean.\nvar roi = ee.Geometry.Polygon(\n [[[-156.053, -16.240],\n [-156.053, -44.968],\n [-118.633, -44.968],\n [-118.633, -16.240]]], null, false);\n\n// Sample the mean June 2020 temperature surface at random points in the ROI.\nvar tmeanFc = img.sample(\n {region: roi, scale: 25000, numPixels: 50, geometries: true}); //250\n\n// Generate an interpolated surface from the points using kriging; parameters\n// are set according to interpretation of an unshown semivariogram. See section\n// 2.1 of https://doi.org/10.14214/sf.369 for information on semivariograms.\nvar tmeanImg = tmeanFc.kriging({\n propertyName: 'tmean',\n shape: 'gaussian',\n range: 2.8e6,\n sill: 164,\n nugget: 0.05,\n maxDistance: 1.8e6,\n reducer: ee.Reducer.mean()\n});\n\n// Display the results on the map.\nMap.setCenter(-137.47, -30.47, 3);\nMap.addLayer(tmeanImg, {min: 279, max: 300}, 'Temperature (K)');\n```\nPython setup\n\nSee the [Python Environment](/earth-engine/guides/python_install) page for information on the Python API and using\n`geemap` for interactive development. \n\n```python\nimport ee\nimport geemap.core as geemap\n```\n\n### Colab (Python)\n\n```python\n# This example generates an interpolated surface using kriging from a\n# FeatureCollection of random points that simulates a table of air temperature\n# at ocean weather buoys.\n\n# Average air temperature at 2m height for June, 2020.\nimg = ee.Image('ECMWF/ERA5/MONTHLY/202006').select(\n ['mean_2m_air_temperature'], ['tmean']\n)\n\n# Region of interest: South Pacific Ocean.\nroi = ee.Geometry.Polygon(\n [[\n [-156.053, -16.240],\n [-156.053, -44.968],\n [-118.633, -44.968],\n [-118.633, -16.240],\n ]],\n None,\n False,\n)\n\n# Sample the mean June 2020 temperature surface at random points in the ROI.\ntmean_fc = img.sample(region=roi, scale=25000, numPixels=50, geometries=True)\n\n# Generate an interpolated surface from the points using kriging parameters\n# are set according to interpretation of an unshown semivariogram. See section\n# 2.1 of https://doi.org/10.14214/sf.369 for information on semivariograms.\ntmean_img = tmean_fc.kriging(\n propertyName='tmean',\n shape='gaussian',\n range=2.8e6,\n sill=164,\n nugget=0.05,\n maxDistance=1.8e6,\n reducer=ee.Reducer.mean(),\n)\n\n# Display the results on the map.\nm = geemap.Map()\nm.set_center(-137.47, -30.47, 3)\nm.add_layer(\n tmean_img,\n {'min': 279, 'max': 300, 'min': 279, 'max': 300},\n 'Temperature (K)',\n)\nm\n```"]]