Use Distil to train a classifier than can predict land use from satellite imagery.

In this workflow, you’ll learn how to add labels to a Sentinel-2 satellite imagery dataset and train a classifier model to predict whether images match those labels. In this case, you’ll be training a model to recognize imagery containing snow so you can later remove them from a model used to detect urban development.

The workflow has two main steps:

  1. Build a set of labels
  2. Create candidate models
  3. Apply a model to a dataset