Random forest classifier for remote sensing classification

TLDR

The study aims to compare the random forest classifier with support vector machines in terms of classification accuracy, training time, and user‑defined parameters. The authors used Landsat Enhanced Thematic Mapper Plus (ETM+) imagery of a UK area with seven land‑cover classes. The random forest classifier achieved a significant increase in land‑cover classification accuracy, matched SVM performance in accuracy and training time, and required fewer user‑defined parameters. The author thanks anonymous referees for their critical comments that improved the paper.

Abstract

Abstract Growing an ensemble of decision trees and allowing them to vote for the most popular class produced a significant increase in classification accuracy for land cover classification. The objective of this study is to present results obtained with the random forest classifier and to compare its performance with the support vector machines (SVMs) in terms of classification accuracy, training time and user defined parameters. Landsat Enhanced Thematic Mapper Plus (ETM+) data of an area in the UK with seven different land covers were used. Results from this study suggest that the random forest classifier performs equally well to SVMs in terms of classification accuracy and training time. This study also concludes that the number of user‐defined parameters required by random forest classifiers is less than the number required for SVMs and easier to define. Acknowledgment The author is grateful for the critical comments of two anonymous referees, whose advice has led to an improvement in the presentation of this paper.