PredictUsingTrend

Summary

Computes a forecasted multidimensional raster object using the output trend raster from the GenerateTrend function.

Discussion

For more information about how this function works, see the Predict Using Trend raster function.

The referenced raster dataset for the raster object is temporary. To make it permanent, you can call the raster object's save method.

Syntax

PredictUsingTrend(raster, {dimension_definition_type}, {dimension_values}, {start}, {end}, {interval_value}, {interval_unit})

Parameter	Explanation	Data Type
raster	The input trend raster from the `GenerateTrend` function.	Raster
dimension_definition_type	Specifies the method to be 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 `dimension_values` argument. This is the default. `BY_INTERVAL`—The prediction will be calculated for an interval of the dimension defined by the `start` and `end` arguments. The default value is BY_VALUE.	String
dimension_values	The dimension value or list of values to be used in the prediction. The format of the value must match the format of the dimension in the input multidimensional raster. If the trend raster was generated for the StdTime dimension, the format will be YYYY-MM-DDTHH:MM:SS, for example, 2050-01-01T12:00:00. This argument is required when the `dimension_def` parameter is set to `BY_VALUE`. The default value is None.	String
start	The start date, height, or depth of the dimension interval to be used in the prediction. The format of the value must match the format of the dimension in the input multidimensional raster. The default value is None.	String
end	The end date, height, or depth of the dimension interval to be used in the prediction. The format of the value must match the format of the dimension in the input multidimensional raster. The default value is None.	String
interval_value	The number of steps between two dimension values to be included in the prediction. The default value is 1. The default value is 1.	Double
interval_unit	Specifies the unit that will be used for the `interval_value` argument. This 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` arguments. `DAYS`—The prediction will be calculated for each day in the range of time described by the `start`, `end`, and `interval_value` arguments. `WEEKS`—The prediction will be calculated for each week in the range of time described by the `start`, `end`, and `interval_value` arguments. `MONTHS`—The prediction will be calculated for each month in the range of time described by the `start`, `end`, and `interval_value` arguments. `YEARS`—The prediction will be calculated for each year in the range of time described by the `start`, `end`, and `interval_value` arguments. The default value is HOURS.	String

Return value

Data Type	Explanation
Raster	The output raster.

Code sample

PredictUsingTrendRaster example

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

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

# Set the local variables
in_raster = "C:/Data/NDVI_Trend.crf"
dimension_def = "BY_INTERVAL"
dimension_values = "None"
start = "2025-01-01T00:00:00"
end = "2025-12-31T00:00:00"
interval_value = 1
interval_unit = "MONTHS"

# Apply PredictUsingTrendRaster function
predicted_raster = arcpy.ia.PredictusingTrend(in_raster, dimension_def,
                        dimension_values , start, end, interval_value, interval_unit)

# Save the output
predicted_raster.save("C:/arcpyExamples/outputs/predicted_NDVI.crf")