A new feature of the upcoming version 7 of the Semi-Automatic Classification Plugin (SCP) for QGIS will be the Random Forest classifier.
Machine Learning is a broad set of classification techniques that aim to build mathematical models based on training data. Random Forest is a particular machine learning technique, based on the iterative and random creation of decision trees (i.e. a set of rules and conditions that define a class).
Random Forest calculates several random decision trees, based on the following parameters:
- number of training samples: is the number of training data (pixels) randomly used to train the model;
- number of trees: is the number of decision trees; the more the number of trees, the more is the model accuracy, but it also increases the calculation time.
 |
| Random Forest |
Random Forest creates several decision trees randomly. Therefore, a model based on the decision trees is created and used to classify all the pixels.
A pixel is classified according to the majority vote of decision trees, for example a pixel is classified as class 1 if most decision trees evaluated it as class 1. Also, a confidence layer is produced, which measures the uncertainty of the model based on training data.
The classification is performed through ESA SNAP , therefore the installation of SNAP is required.
It will be possible to save the classifier and use it later to classify other data.
I'm continuing the development of SCP 7, adding several new functions that I'm going to illustrate in the next few weeks.
For any comment or question, join the Facebook group about the Semi-Automatic Classification Plugin.