Predict Using Trend Raster (Image Analyst)

Available with Image Analyst license.

Summary

Computes a forecasted multidimensional raster using the output trend raster from the Generate Trend Raster tool.

Usage

• This tool uses the output from the Generate Trend Raster tool as the input multidimensional trend raster.

• This tool produces a multidimensional raster dataset in Cloud Raster Format (CRF). Currently, no other output formats are supported.

• By default, the multidimensional raster output will be compressed using the LZ77 compression type. However, it is recommended that you change the compression type to LERC and adjust the maximum error value based on the data. For example, if you expect the results of the analysis to be accurate to three decimal places, use 0.001 for the maximum error value. Avoid unnecessary accuracy requirements, as they will increase the processing time and storage size.

Parameters

Dialog

Label	Explanation	Data Type
Input Trend Raster	The input multidimensional trend raster from the Generate Trend Raster tool.	Raster Dataset; Raster Layer; Mosaic Dataset; Mosaic Layer; Image Service; File
Variables [Dimension Info] (Description) (Optional)	The variable or variables that will be predicted in the analysis. If no variables are specified, all variables will be used.	String
Dimension Definition (Optional)	Specifies the method used to provide prediction dimension values. By value—The prediction will be calculated for a single dimension value or a list of dimension values defined by the Values parameter (dimension_values in Python). This is the default.For example, you want to predict yearly precipitation for the years 2050, 2100, and 2150. By interval—The prediction will be calculated for an interval of the dimension defined by a start and an end value.For example, you want to predict yearly precipitation for every year between 2050 and 2150.	String
Values (Optional)	The dimension value or values to be used in the prediction. The format of the time, depth, and height values must match the format of the dimension values used to generate the trend raster. If the trend raster was generated for the StdTime dimension, the format would be YYYY-MM-DDTHH:MM:SS, for example 2050-01-01T00:00:00. Multiple values are separated with a semicolon. This parameter is required when the Dimension Definition parameter is set to By value.	String
Start (Optional)	The start date, height, or depth of the dimension interval to be used in the prediction.	String
End (Optional)	The end date, height, or depth of the dimension interval to be used in the prediction.	String
Value Interval (Optional)	The number of steps between two dimension values to be included in the prediction. The default value is 1. For example, to predict temperature values every five years, use a value of 5.	Double
Unit (Optional)	Specifies the unit that will be used for the interval value. This parameter only applies when the dimension of analysis is a time dimension. Hours—The prediction will be calculated for each hour in the range of time described by the Start, End, and Value Interval parameters. Days—The prediction will be calculated for each day in the range of time described by the Start, End, and Value Interval parameters. Weeks—The prediction will be calculated for each week in the range of time described by the Start, End, and Value Interval parameters. Months—The prediction will be calculated for each month in the range of time described by the Start, End, and Value Interval parameters. Years—The prediction will be calculated for each year in the range of time described by the Start, End, and Value Interval parameters.	String

Return Value

Label	Explanation	Data Type
Output Multidimensional Raster	The output Cloud Raster Format (CRF) multidimensional raster dataset.	Raster

Python

PredictUsingTrendRaster(in_multidimensional_raster, {variables}, {dimension_def}, {dimension_values}, {start}, {end}, {interval_value}, {interval_unit})

Name	Explanation	Data Type
in_multidimensional_raster	The input multidimensional trend raster from the Generate Trend Raster tool.	Raster Dataset; Raster Layer; Mosaic Dataset; Mosaic Layer; Image Service; File
variables [variables,...] (Optional)	The variable or variables that will be predicted in the analysis. If no variables are specified, all variables will be used.	String
dimension_def (Optional)	Specifies the method used to provide prediction dimension values. BY_VALUE—The prediction will be calculated for a single dimension value or a list of dimension values defined by the Values parameter (dimension_values in Python). This is the default.For example, you want to predict yearly precipitation for the years 2050, 2100, and 2150. BY_INTERVAL—The prediction will be calculated for an interval of the dimension defined by a start and an end value.For example, you want to predict yearly precipitation for every year between 2050 and 2150.	String
dimension_values [dimension_values,...] (Optional)	The dimension value or values to be used in the prediction. The format of the time, depth, and height values must match the format of the dimension values used to generate the trend raster. If the trend raster was generated for the StdTime dimension, the format would be YYYY-MM-DDTHH:MM:SS, for example 2050-01-01T00:00:00. Multiple values are separated with a semicolon. This parameter is required when the dimension_def parameter is set to BY_VALUE.	String
start (Optional)	The start date, height, or depth of the dimension interval to be used in the prediction.	String
end (Optional)	The end date, height, or depth of the dimension interval to be used in the prediction.	String
interval_value (Optional)	The number of steps between two dimension values to be included in the prediction. The default value is 1. For example, to predict temperature values every five years, use a value of 5.	Double
interval_unit (Optional)	Specifies the unit that will be used for the interval value. This parameter only applies when the dimension of analysis is a time dimension. HOURS—The prediction will be calculated for each hour in the range of time described by the start, end, and interval_value parameters. DAYS—The prediction will be calculated for each day in the range of time described by the start, end, and interval_value parameters. WEEKS—The prediction will be calculated for each week in the range of time described by the start, end, and interval_value parameters. MONTHS—The prediction will be calculated for each month in the range of time described by the start, end, and interval_value parameters. YEARS—The prediction will be calculated for each year in the range of time described by the start, end, and interval_value parameters.	String

Return Value

Name	Explanation	Data Type
out_multidimensional_raster	The output Cloud Raster Format (CRF) multidimensional raster dataset.	Raster

Code sample

PredictUsingTrendRaster example 1 (Python window)

This example generates the forecasted precipitation and temperature for January 1, 2050, and January 1, 2100.

# Import system modules
import arcpy
from arcpy.ia import *

# Check out the ArcGIS Image Analyst extension license
arcpy.CheckOutExtension("ImageAnalyst")

# Execute 
predictOutput = PredictUsingTrendRaster("C:/Data/LinearTrendCoefficients.crf",
	"temp;precip", "BY_VALUE", "2050-01-01T00:00:00;2100-01-01T00:00:00")
	
# Save output
predictOutput.save("C:/Data/Predicted_Temp_Precip.crf")

PredictUsingTrendRaster example 2 (stand-alone script)

This example generates the forecasted NDVI values for each month in year 2025.

# Import system modules
import arcpy
from arcpy.ia import *

# Check out the ArcGIS Image Analyst extension license
arcpy.CheckOutExtension("ImageAnalyst")

# Define input parameters
inFile = "C:/Data/HarmonicTrendCoefficients.crf"
variables = "NDVI"
dimension_definition = "BY_INTERVAL"
start = "2025-01-01T00:00:00"
end = "2025-12-31T00:00:00"
interval_value = 1
interval_unit = "MONTHS"

# Execute - predict the monthly NDVI in 2025 
predictOutput = PredictUsingTrendRaster(inFile, variables, 
	dimension_definition, '', start, end, interval_value, interval_unit)
	
# Save output
predictOutput.save("C:/data/predicted_ndvi.crf")

Environments

Cell Size, Compression, Current Workspace, Geographic Transformations, NoData, Output CONFIG Keyword, Output Coordinate System, Extent, Parallel Processing Factor, Pyramid, Raster Statistics, Resampling Method, Scratch Workspace, Snap Raster, Tile Size