Available with Image Analyst license.

Available with Spatial Analyst license.

## Summary

Creates a raster object that contains the anomaly pixel values of the input multidimensional raster based on a time dimension interval and the anomaly calculation method.

## Discussion

Use the Anomaly function to calculate pixel value anomalies for temporal variables in a multidimensional raster object. For example, if you have daily precipitation data, you can find the pixels that are highly different from the monthly average precipitation values throughout your dataset.

The three mathematical methods for calculating anomaly values with this function are as follows:

- Difference from mean = x - µ
- x = pixel value in a slice
- µ = mean of that pixel's values over a 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 a given time interval
- |x - µ| = absolute value of the difference between the value and the mean

- Percent of average = x / µ
- x = pixel value in a slice
- µ = mean of that pixel's values over a given time interval

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

## Syntax

Anomaly (in_raster, {dimension_name}, {anomaly_type}, {temporal_interval}, {ignore_nodata})

Parameter | Explanation | Data Type |

in_raster | The input multidimensional raster. | Raster |

dimension_name | The dimension name which the anomaly definition will be performed along. (The default value is StdTime) | String |

anomaly_type | Specifies the method used to calculate the anomaly. - DIFFERENCE_FROM_MEAN —Calculates the difference between a pixel value and the mean of that pixel's values across slices defined by the interval. This is the default.
- PERCENT_DIFFERENCE_FROM_MEAN —Calculates the percent difference between a pixel value and the mean of that pixel's values across slices defined by the interval.
- PERCENT_OF_MEAN —Calculates the percent of the mean.
(The default value is DIFFERENCE_FROM_MEAN) | String |

temporal_interval | Specifies the temporal interval to use to calculate the average. - None —Calculates the average across all slices for each pixel. This is the default.
- HOURLY —Calculates the hourly average for each pixel.
- DAILY —Calculates the daily average for each pixel.
- WEEKLY —Calculates the weekly average for each pixel.
- MONTHLY —Calculates the monthly average for each pixel.
- YEARLY —Calculates the yearly average for each pixel.
(The default value is None) | String |

ignore_nodata | Specified whether NoData values are ignored in the analysis. - True—The analysis will include all valid pixels along a given dimension and ignore any NoData pixels. This is the default.
- False—The analysis will result in NoData if there are any NoData values for the pixel along the given dimension.
(The default value is True) | Boolean |

Data Type | Explanation |

Raster | The output anomaly multidimensional raster. |

## Code sample

Calculate precipitation anomalies across all slices and for monthly values.

```
import arcpy
from arcpy.sa import *
arcpy.CheckOutExtension("Spatial")
in_raster = Raster("C:/sapyexamples/data/ClimateData_Daily.nc", True)
# Choose the precipitation variable
prcp_raster = Subset(in_raster, variables = 'prcp')
# Calculate percent of mean anomalies,
# where the mean_value is the mean of all slices
prcp_anomaly = Anomaly(prcp_raster, anomaly_type = 'PERCENT_OF_MEAN')
# Calculate the difference from mean,
# where the mean_value is the mean of each year
prcp_monthly_anomaly = Anomaly(prcp_raster, temporal_interval = 'YEARLY')
```