Summary
Forecasts the future values of each location of a spacetime cube using curve fitting.
The tool fits a parametric curve to each location in the Input Space Time Cube and forecasts the time series by extrapolating this curve to future time steps. The curves can be linear, parabolic, Sshaped (Gompertz), or exponential. You can use the same curve type at each location of the spacetime cube or allow the tool to set which curve type best fits each location.
Illustration
Usage
This tool accepts netCDF files created by the Create Space Time Cube By Aggregating Points, Create Space Time Cube From Defined Features, and Create Space Time Cube from Multidimensional Raster Layer tools.
Compared to other forecasting tools in the Time Series Forecasting toolset, this tool is the most straightforward, and it is most appropriate for time series that follow a predictable trend that does not display strong seasonality. If your data follows a complex trend or displays strong seasonal cycles, use other forecasting tools.
Multiple forecasted spacetime cubes can be compared and merged using the Evaluate Forecasts by Location tool. This allows you to create multiple forecast cubes using different forecasting tools and parameters, and the tool will identify the best forecast for each location using either Forecast root mean square error (RMSE) or Validation RMSE.
For each location in the Input Space Time Cube, the tool builds two models that serve different purposes.
 Forecast model—This model is used to forecast future values of the spacetime cube by fitting a curve to the values of the time series and extrapolating this curve to future time steps. The fit of the forecast model to the values of the spacetime cube is measured by the Forecast RMSE value.
 Validation model—This model is used to validate the forecast model and test how accurately it can forecast future values. If a number greater than 0 is specified for the Number of Time Steps to Exclude for Validation parameter, this model is fitted to the time steps that were not excluded and is used to forecast the values of the time steps that were excluded. This allows you to see how well the chosen curve type can forecast future values. The fit of the forecasted values to the excluded values is measured by the Validation RMSE value.
Learn more about the forecast model, validation model, and RMSE statistics
The AutoDetect option of the Curve Type parameter will fit all four curve types at each location and identify the one with the smallest Validation RMSE. If no time steps are excluded for validation, the curve with the smallest Forecast RMSE is used.
The Output Features will be added to the Contents pane with rendering based on the final forecasted time step.

This tool creates geoprocessing messages and popup charts to help you understand and visualize the forecast results. The messages contain information about the structure of the spacetime cube and summary statistics of the RMSE values. Clicking a feature using the Explore navigation tool displays a line chart in the Popup pane showing the values of the spacetime cube, the curve used to forecast, and the forecasted values for that location.
Deciding how many time steps to exclude for validation is an important choice. The more time steps are excluded, the fewer time steps remain to estimate the validation model. However, if too few time steps are excluded, the Validation RMSE will be estimated using a small amount of data and may be misleading. It is recommended that you exclude as many time steps as possible while still maintaining sufficient time steps to estimate the validation model. It is also suggested that you withhold at least as many time steps for validation as the number of time steps you intend to forecast, if your spacetime cube has enough time steps to allow this.
Syntax
CurveFitForecast(in_cube, analysis_variable, output_features, {output_cube}, {number_of_time_steps_to_forecast}, {curve_type}, {number_for_validation})
Parameter  Explanation  Data Type 
in_cube  The netCDF cube containing the variable you want to forecast to future time steps. This file must have an .nc file extension and must have been created using the Create Space Time Cube By Aggregating Points, Create Space Time Cube From Defined Locations, or Create Space Time Cube From Multidimensional Raster Layer tools.  File 
analysis_variable 
The numeric variable in the netCDF file that will be forecasted to future time steps.  String 
output_features 
The output feature class of all locations in the spacetime cube with forecasted values stored as fields. The layer displays the forecast for the final time step and contains popups charts showing the time series and forecasts for each location.  Feature Class 
output_cube (Optional) 
A new spacetime cube (.nc file) containing the values of the input spacetime cube with the forecasted time steps appended. The Visualize Space Time Cube in 3D tool can be used to see all of the observed and forecasted values simultaneously.  File 
number_of_time_steps_to_forecast (Optional) 
A positive integer specifying the number of time steps to forecast. This value cannot be larger than 50 percent of the total time steps in the input spacetime cube. The default value is one time step.  Long 
curve_type (Optional)  Specifies the curve type that will be used to forecast the values of the input spacetime cube.
 String 
number_for_validation (Optional)  The number of time steps at the end of each time series to exclude for validation. The default value is 10 percent (rounded down) of the number of input time steps, and this value cannot be larger than 25 percent of the number of time steps. Provide the value 0 to not exclude any time steps.  Long 
Code sample
The following Python script demonstrates how to use the CurveFitForecast tool:
import arcpy
arcpy.env.workspace = "C:/Analysis"
# Forecast four time steps using a linear curve.
arcpy.stpm.CurveFitForecast("Population.nc","Pop_NONE_ZEROS",
"Analysis.gdb/Forecasts",
"outForecastCube.nc" 4,
"LINEAR", 5)
The following Python script demonstrates how to use the CurveFitForecast tool to forecast population:
# Forecast population levels using curve fitting.
# Import system modules.
import arcpy
# Set property to overwrite existing output.
arcpy.env.overwriteOutput = True
# Set workspace.
workspace = r"C:\Analysis"
arcpy.env.workspace = workspace
# Forecast three time steps using autodetect.
arcpy.stpm.CurveFitForecast("Population.nc","Pop_NONE_ZEROS",
"Analysis.gdb/Forecasts", "outForecastCube.nc"
3, "AUTO_DETECT", 5)
# Create a feature class visualizing the forecasts.
# Output can only be viewed in a Scene view.
arcpy.stpm.VisualizeSpaceTimeCube3D(r"outForecastCube.nc", "Pop_NONE_ZEROS",
"VALUE", "Analysis.gdb/ForecastsFC")
Environments
Licensing information
 Basic: Yes
 Standard: Yes
 Advanced: Yes