Interpolate Points (Raster Analysis)

Summary

Predicts values at new locations based on measurements from a collection of points. The tool takes point data with values at each point and returns a raster of predicted values.

Illustration

Interpolate Points tool

Usage

  • This raster analysis portal tool is available when you are signed in to an ArcGIS Enterprise Link to Understanding analysis in ArcGIS Enterprise portal that has an ArcGIS Image Server Link to What is ArcGIS Image Server configured for Raster Analysis Link to Configure and deploy raster analytics. When the tool is invoked, ArcGIS Pro serves as a client and the processing occurs in the servers federated with ArcGIS Enterprise. The portal tool accepts layers from your portal as input and creates output in your portal.

    The input feature layer can be a layer from the portal or a URI or URL to a feature service. While you can use local feature data and layers as input to this portal tool, best practice is to use layers from your portal as input.

  • The interpolation is performed by generating many local interpolation models that are merged together to create the final output raster. The number of points in each local model can be controlled with the Size of local models parameter.

  • The Empirical Bayesian Kriging tool is used to perform the underlying interpolation. This tool is part of the ArcGIS Geostatistical Analyst extension. Many parameters of the tool are exposed in Interpolate Points, but many are controlled automatically by the Optimize for parameter.

Parameters

LabelExplanationData Type
Input Point Features

The input point features you want to interpolate.

Feature Set
Interpolate Field

The field containing the data values you want to interpolate. The field must be numeric.

Field
Output Name

The name of the output raster service.

The default name is based on the tool name and the input layer name. If the layer name already exists, you will be prompted to provide another name.

String
Optimize For
(Optional)

Choose your preference for speed versus accuracy. More accurate predictions will take longer to calculate.

  • Speed — The operation is optimized for speed.
  • Balance — A balance between speed and accuracy. This is the default.
  • Accuracy —The operation is optimized for accuracy.
String
Transform Data to Normal Distribution
(Optional)

Choose whether to transform your data to a normal distribution before performing analysis. If your data values do not appear to be normally distributed (bell-shaped), it is recommended to perform a transformation.

  • Checked—A transformation to the normal distribution is applied.
  • Unchecked—No transformation is applied. This is the default.
Boolean
Size of Local Models
(Optional)

Choose the number of points in each of the local models. A larger value will make the interpolation more global and stable, but small-scale effects may be missed. Smaller values will make the interpolation more local, so small-scale effects are more likely to be captured, but the interpolation may be unstable.

Long
Number of Neighbors
(Optional)

The number of neighbors to use when calculating the prediction at a particular cell.

Long
Output Cell Size
(Optional)

Set the cell size and units of the output raster. If a prediction error raster is created, it will also use this cell size.

The units can be Kilometers, Meters, Miles, or Feet.

The default units are Meters.

Linear Unit
Output Prediction Error
(Optional)

Choose whether to output a raster of standard errors of the interpolated predictions.

Standard errors are useful because they provide information about the reliability of the predicted values. A simple rule of thumb is that the true value will fall within two standard errors of the predicted value 95 percent of the time. For example, suppose a new location gets a predicted value of 50 with a standard error of 5. This means that this task's best guess is that the true value at that location is 50, but it reasonably could be as low as 40 or as high as 60. To calculate this range of reasonable values, multiply the standard error by 2, add this value to the predicted value to get the upper end of the range, and subtract it from the predicted value to get the lower end of the range.

If a raster of standard errors for the interpolated predictions is requested, it will have the same name as the Result layer name but with Errors appended.

  • Unchecked—No output prediction error is generated. This is the default.
  • Checked—An output prediction error is generated.
Boolean

Derived Output

LabelExplanationData Type
Output Raster

The output raster.

Raster Layer
Output Error Raster

The output prediction error raster.

Raster Layer

arcpy.ra.InterpolatePoints(inputPointFeatures, interpolateField, outputName, {optimizeFor}, {transformData}, {sizeOfLocalModels}, {numberOfNeighbors}, {outputCellSize}, {outputPredictionError})
NameExplanationData Type
inputPointFeatures

The input point features you want to interpolate.

Feature Set
interpolateField

The field containing the data values you want to interpolate. The field must be numeric.

Field
outputName

The name of the output raster service.

The default name is based on the tool name and the input layer name. If the layer name already exists, you will be prompted to provide another name.

String
optimizeFor
(Optional)

Choose your preference for speed versus accuracy. More accurate predictions will take longer to calculate.

  • SPEEDThe operation is optimized for speed.
  • BALANCEA balance between speed and accuracy. This is the default.
  • ACCURACYThe operation is optimized for accuracy.
String
transformData
(Optional)

Choose whether to transform your data to a normal distribution before performing analysis. If your data values do not appear to be normally distributed (bell-shaped), it is recommended to perform a transformation.

  • NO_TRANSFORMNo transformation is applied. This is the default.
  • TRANSFORMA transformation to the normal distribution is applied.
Boolean
sizeOfLocalModels
(Optional)

Choose the number of points in each of the local models. A larger value will make the interpolation more global and stable, but small-scale effects may be missed. Smaller values will make the interpolation more local, so small-scale effects are more likely to be captured, but the interpolation may be unstable.

Long
numberOfNeighbors
(Optional)

The number of neighbors to use when calculating the prediction at a particular cell.

Long
outputCellSize
(Optional)

Set the cell size and units of the output raster. If a prediction error raster is created, it will also use this cell size.

The units can be Kilometers, Meters, Miles, or Feet.

The default units are Meters.

Linear Unit
outputPredictionError
(Optional)

Choose whether to output a raster of standard errors of the interpolated predictions.

Standard errors are useful because they provide information about the reliability of the predicted values. A simple rule of thumb is that the true value will fall within two standard errors of the predicted value 95 percent of the time. For example, suppose a new location gets a predicted value of 50 with a standard error of 5. This means that this task's best guess is that the true value at that location is 50, but it reasonably could be as low as 40 or as high as 60. To calculate this range of reasonable values, multiply the standard error by 2, add this value to the predicted value to get the upper end of the range, and subtract it from the predicted value to get the lower end of the range.

If a raster of standard errors for the interpolated predictions is requested, it will have the same name as the Result layer name but with Errors appended.

  • OUTPUT_ERRORCreate a prediction error raster.
  • NO_OUTPUT_ERRORDo not create a prediction error raster. This is the default.
Boolean

Derived Output

NameExplanationData Type
outputRaster

The output raster.

Raster Layer
outputErrorRaster

The output prediction error raster.

Raster Layer

Code sample

InterpolatePoints example 1 (Python window)

This example interpolates a point feature service into an image service raster.

import arcpy

arcpy.InterpolatePoints_ra('https://MyPortal.esri.com/server/rest/services/Hosted/myPoints/FeatureServer/0',
                           'myField', 'outImgServ', 'SPEED', 'False', 50, 8, '10000 Meters', 'NO_OUTPUT_ERROR')
InterpolatePoints example 2 (stand-alone script)

This example interpolates a point feature service into an image service raster.

#-------------------------------------------------------------------------------
# Name: InterpolatePoints_example02.py
# Description: Interpolates a point feature service into an image service raster.
#
# Requirements: ArcGIS Image Server

# Import system modules
import arcpy

# Set local variables
inPoints = 'https://MyPortal.esri.com/server/rest/services/Hosted/myPoints/FeatureServer/0'
inField = 'myField'
outRaster = 'outImgServ'
optimizeFor = 'SPEED'
transform = 'False'
subsetSize = 50
numNeighbors = 8
outCellSize = '10000 Meters'
error = 'NO_OUTPUT_ERROR'

# Execute InterpolatePoints
arcpy.InterpolatePoints_ra(inPoints, inField, outRaster, optimizeFor, transform, 
                           subsetSize, numNeighbors, outCellSize, error)

Licensing information

  • Basic: Requires ArcGIS Image Server
  • Standard: Requires ArcGIS Image Server
  • Advanced: Requires ArcGIS Image Server

Related topics