Supervised classification is arguably the most important classical
machine learning techniques in remote sensing. Applications range from
generating Land Use/Land Cover maps to change detection. Google Earth
Engine is unique suited to do supervised classification at scale. This module covers basic supervised
classification workflow and accuracy assessment.
After this module you're able to:
Collect training and test areas
Apply the random forest supervised classification
Assess the accuracy of a classified image
The code for these exercises can be found in this repository under Module 5.