Class change#
Overview#
Very often we want to build the class change map between 2 categorical map sharing the same legend. If the 2 images are taken at different time it will help us understand how the vegetation classification has evolved between these 2 dates. It can be a tidious exercise to build the new legend (forest -> forest, forest -> urban, …) and to manually write the rules to identify each class. Sepal will automatically build the legend of the rsulting categorical map from the initail legend and compute all the pixels automatically.
Note
This recipe is a very light computation, you can safely reuse the recipe without exporting in other recipes, it will not slow down the downstream processses.
Start#
Once the class chane recipe is selected, SEPAL will show you the process in a new tab (1). the parameter will open themselves at the bottom right side of your screen (2).
The first step is to change the name of the recipe. This name will be used to name your files and recipes in the SEPAL folders. Use the best-suited convention for your need. Simply double-click the tab and write a new name. It will default to Class_change_<now>.
Parameters#
In the bottom right corner, 4 tabs are available. They will allow the user to customize the class change to its needs.
FRM: the source categorical image
TO: the destination categorical image
LEG: the legend of the transition classes
OPT: the optional parameters of the recipe
Select images#
The first step is to select the 2 images to compare. FRM and TO have the same interface so we’ll describe them together.
You need to select a categorical image, this can be a classification recipe, or any categorical asset from your google earthengine account. In both cases you’ll need to select the band to use for the transition and the legend.
If the selected asset/recipe is a classification recipe (or its export) the legend will be automatically field with the metadata of the file. else you’ll need to updload it manually. click on fa-solid fa-pen-to-square to open the legend edition tool. It’s the same as the one described in the classification recipe. Please refer to Classification if you need extra information.
customize legend#
Once both from and to images are selected, SEPAL will build a transition classification legend based on the registered legend in the 2 parameter images. The color can be modified as well as the values.
options#
If the selected asset is from a SEPAL classification, it will embed a probability value for each classified pixel. SEPAL will proposed clever map transitionning based on these values.
For example a high confidence forest pixel changes in a low confidence non-forest piexl. the change will be taken into account only if the min confidence is reached by the “TO” pixel. By default no filtering is perform and the slider is set to 0.
Note
if the classified images are from other sources, the probability won’t be available and the transition will be applied without verification.
Analysis#
Export#
Important
You cannot export a recipe as an asset or a .tiff file without a small computation quota. If you are a new user see Manage your resources to know more.
Clicking on the tab will open the retrieve panel where the you can select the exportation parameters.
Bands#
You need to select the band to export in the recipe. You will have access to transition which is the new class change values and confidence if you selected classification recipe assets.
Scale#
You can set a custom scale for exportation by changing the value of the slider (m). Requesting a smaller resolution than images native resolution will not improve the quality of the output, just its size so keep in mind that Sentinel data native resolution is 10 m and Landsat is 30 m.
Destination#
You can export the image to sepal workspace or to ;guilabel:google earth engine asset. The same image will be exported but in the first case you will find it in .tif format in the downloads folder, in the second one the image will be exported to your GEE account asset list.
Warning
If google earth engine asset is not displayed, it means that your GEE account is not connected to SEPAL, please refer to Use Google Earth Engine (GEE) with SEPAL.
Click on apply to start the download process.
Exportation status#
Going to the task tab (bottom left corner using the or buttons —depending on the loading status—), you will see the list of the different loading tasks. The interface will provide you with information about the task progress and it will display an error if the exportation has failed. If you are unsatisfied with the way we present information, the task can also be monitored using the GEE task manager.
Tip
This operation is running between GEE and SEPAL servers in the background, you can thus close the SEPAL page without killing the process.
When the task is finished the frame will be displayed in green as shown on the second image.
