Rule 1

Label the Planet Imagery, not the Basemap.

For now, our labelling system works primarily with Planet imagery, which are the slightly coarser resolution true and false color images that are (usually) overlaid on the basemap. These Planet images are the ones that our machine learning algorithm processes, so we want to draw boundaries around the field we see in the Planet images, not on the basemap.

This is important because the fields in the Planet imagery are often different than what you see in the basemap. The basemap imagery is usually older than the Planet imagery, and so the fields often change between when the basemap and Planet image were taken. These changes will lead to errors in the algorithm that we want to avoid.

You can see these difference in the following images:

Planet growing season true color. The red arrows show locations where mappable crop fields exist, but don't appear in the underlying basemap image below. The blue arrow shows field expansion in the Planet image relative to the basemap below, but in this case these fields would not be mapped because they do not overlap our labelling target

Basemap image, with red and blue arrows pointing to places where fields exist within the Planet image above, but not in the basemap

Here’s how we would label this scene:

We label the fields that either fall entirely in or overlap this white box, our labelling target. Here we trace the boundaries of areas that look like cleared fields. Following [**Rule 2**](/mappingrules/docs/rule2.html), we used all the available images to help identify the boundaries

Main Menu Labelling Interface Rules