Random Forest Classification Scenarios for Benthic Habitat Mapping using Planetscope Image

We presented the use of Random Forest (RF) classification to map benthic habitat in two small islands using different parameter scenario, which are the number of trees, the function to determine the number of randomly selected features, and the function to determine the impurity in a node. The results indicated that RF is a consistent performer with accuracy difference of 1.3 and 5.8 for the two Islands. Furthermore, different scenarios also producing similar benthic habitat spatial distribution and misclassification pattern. © 2019 IEEE.