Segmentation Output
Segmentation outputs a mask (iris.cube.Cube and in the future xarray.DataArray) with the same dimensions as the input field, where each segmented area has the same ID as its corresponding feature (see feature column in Feature Detection Output). Note that there are some cases in which a feature is not attributed to a segmented area associated with it (see Features without segmented areas).
Segmentation also outputs the same pandas dataframe as obtained by Feature Detection (see Feature Detection Basics) but with one additional column:
Variable Name |
Description |
Units |
Type |
---|---|---|---|
ncells |
Total number of grid points that belong to the segmented area associated with feature. |
n/a |
int64 |
One can optionally get the bulk statistics of the data points belonging to each segmented feature (i.e. either the 2D area or the 3D volume assigned to the feature). This is done using the statistics parameter when calling :ufunc:`tobac.segmentation.segmentation` . The user-defined metrics are then added as columns to the output dataframe, for example:
Variable Name |
Description |
Units |
Type |
---|---|---|---|
feature_mean |
Mean of feature data points |
same as input field |
float |
feature_max |
Maximum value of feature data points |
same as input field |
float |
feature_min |
Minimum value of feature data points |
same as input field |
float |
feature_sum |
Sum of feature data points |
same as input field |
float |
major_axis_length |
The length of the major axis of the ellipse that has the same normalized second central moments as the feature area |
number of grid cells, multiply by dx to get distance unit |
float |
feature_percentiles |
Percentiles from 0 to 100 (with increment 1) of feature data distribution |
same as input field |
ndarray |
Note that these statistics refer to the data fields that are used as input for the segmentation. It is possible to run the segmentation with different input (see transform segmentation) data to get statistics of a feature based on different variables (e.g. get statistics of cloud top temperatures as well as rain rates for a certain storm object).