Random forest
With random forest classification, we build a number of decision trees on training samples (sampling with replacement), and for each split on the tree, a random sample of predictors is chosen. Random forests generally perform very well with classifications. But, for our case, as we have only two predictors, we will not see any improvement. In practical cases, if we took more predictors of landslides, such as the normalized difference vegetation index (NDVI), aspect, and so on, this algorithm would show (for most cases) improved performance.
Similar to what we did with CART, we build the model on the training dataset and test its accuracy on the test dataset. Now, we build a random forest using the randomForest() function of ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access