Generate Multidimensional Anomaly

The Generate Multidimensional Anomaly tool computes the anomaly for each slice in an existing multidimensional raster to generate a new multidimensional raster. An anomaly is the deviation of an observation from its standard or average value.

Note:

To run this tool, the portal must be configured for raster analysis.

If you do not see this tool in Map Viewer, contact your portal administrator. Your portal may not be configured for raster analysis, or you may not have the privileges required to run the tool.

Workflow diagram

Example

• Given monthly ocean temperature data, collected every 1 meter of depth up to 100 meters, calculate the temperature anomalies as deviations from the yearly mean at each depth.
• Given yearly precipitation data, collected over 50 years, determine the years with the lowest precipitation values compared to the average over time.

Usage notes

This tool calculates anomalies over time for one or more variables in a multidimensional raster. An anomaly is the deviation of an observation from its standard, mean, or median value.

For information on how to publish multidimensional imagery layers, see Publish multidimensional imagery layers.

The input multidimensional imagery layer must have a time dimension. If you have a non-time dimension in addition to the time dimension, the anomaly will be calculated at each step in the additional dimension.

Anomalies can be calculated using either the mean or the median values as the definition of the average. If the data distribution is skewed, the mean can be highly influenced by outliers, so the median value or z-score method may be better suited for this type of data. The mathematical methods for calculating anomaly values are listed below.

• Difference from mean = x - µ
  • x = pixel value in a slice
  • µ = mean of that pixel's values over the given time interval
• Percent difference from mean = |x - µ| / [(x + µ)/2]
  • x = pixel value in a slice
  • µ = mean of that pixel's values over the given time interval
  • |x - µ| = absolute value of the difference between the value and the mean
• Percent of mean = x / µ
  • x = pixel value in a slice
  • µ = mean of that pixel's values over the given time interval
• Difference from median = x - ß
  • x = pixel value in a slice
  • ß = median of that pixel's values over the given time interval
• Percent difference from median = |x - ß| / [(x + ß)/2]
  • x = pixel value in a slice
  • ß = median of that pixel's values over the given time interval
  • |x - ß| = absolute value of the difference between the value and the median
• Percent of median = x / ß
  • x = pixel value in a slice
  • ß = median of that pixel's values over the given time interval
• Z-score = (x - µ) / S
  • x = pixel value in a slice
  • µ = mean of that pixel's values over the given time interval
  • S = the standard deviation of the pixel's values over the given time interval

If Use current map extent is checked, variables of the layer that are visible within the current map extent will be analyzed. If it is not checked, variables of the full layer will be analyzed, even if they are outside the current map extent.

The parameters for this tool are listed in the following table:

Parameter	Explanation
Choose multidimensional imagery layer to generate anomaly	The input multidimensional imagery layer to analyze.
Choose variable(s) for which anomalies will be generated	The variable or variables for which anomalies will be calculated. If no variable is specified, all variables with a time dimension will be analyzed.
Choose method to generate anomaly	Specifies the method that will be used to calculate the anomaly. Difference From Mean—The difference between a pixel value and the mean of that pixel's value across slices defined by the interval will be calculated. This is the default. Percent Difference From Mean—The percent difference between a pixel value and the mean of that pixel's value across slices defined by the interval will be calculated. Percent of Mean—The percent of the mean will be calculated. Z Score—The z-score for each pixel will be calculated. A z-score of 0 indicates that the pixel's value is identical to the mean. A z-score of 1 indicates that the pixel's value is 1 standard deviation from the mean. If a z-score is 2, the pixel's value is 2 standard deviations from the mean, and so on. Difference From Median—The difference between a pixel value and the mathematical median of that pixel's values across slices defined by the interval will be calculated. Percent Difference From Median—The percent difference between a pixel value and the mathematical median of that pixel's values across slices defined by the interval will be calculated. Percent of Median—The percent of the mathematical median will be calculated.
Choose temporal interval to calculate the mean	Specifies the temporal interval that will be used to calculate the mean. All—The mean across all slices for each pixel will be calculated. Yearly—The yearly mean for each pixel will be calculated. Recurring Monthly—The monthly mean for each pixel will be calculated. Recurring Weekly—The weekly mean for each pixel will be calculated. Recurring Daily—The daily mean for each pixel will be calculated. Hourly—The hourly mean for each pixel will be calculated. External Raster—An existing raster dataset that contains the mean or median value for each pixel will be referenced.
Choose imagery layer of mean as a reference	Specifies the reference raster dataset that contains a previously calculated mean for each pixel. The anomalies will be calculated in comparison to this mean.
Ignore missing values in calculation	Specifies whether missing values are ignored in the analysis. Checked—The analysis will include all valid pixels along a given dimension and ignore any NoData pixels. This is the default. Unchecked—The analysis will result in NoData if there are any NoData values for the pixel along the given dimension.
Result layer name	The name of the layer that will be created in My Content and added to the map. The default name is based on the tool name and the input layer name. If the layer already exists, you will be prompted to provide another name. You can specify the name of a folder in My Content where the result will be saved using the Save result in drop-down box.

Environments

Analysis environment settings are additional parameters that affect a tool's results. You can access the tool's analysis environment settings by clicking the gear icon at the top of the tool pane.

This tool honors the following Analysis Environments:

• Output coordinate system—Specifies the coordinate system of the output layer.
• Extent—Specifies the area to be used for analysis.
• Snap Raster—Adjusts the extent of the output so it matches the cell alignment of the specified snap raster layer.
• Cell size—The cell size to use in the output layer.
• Mask—Specifies a mask layer, where only the cells that fall within the mask area will be used for analysis.
• Resampling method—The method to use to interpolate pixel values.
• Recycle interval of processing workers—Defines how many image sections to process before restarting worker processes.
• Parallel processing factor—Controls the raster processing CPU or GPU instances.
• Number of retries on failures—Defines how many retries a worker process will attempt when there is random failure processing a job.

Similar tools and raster functions

Use Generate Multidimensional Anomaly to calculate anomaly values for variables over time. Other tools may be useful in solving similar problems.

Map Viewer analysis tools and raster functions

The Find Outliers tool will determine if there are outliers in the spatial pattern of features in a feature service.

ArcGIS Pro analysis tools and raster functions

The Generate Multidimensional Anomaly geoprocessing tool is available in the Image Analyst and the Spatial Analyst toolboxes.

ArcGIS Enterprise developers resources

If you are working in ArcGIS REST API, use the Generate Multidimensional Anomaly task.

If you are working in ArcGIS API for Python, use Generate Multidimensional Anomaly from the arcgis.raster.analytics module.