Next Article in Journal
WARCProcessor: An Integrative Tool for Building and Management of Web Spam Corpora
Next Article in Special Issue
Proposal of a Method to Determine the Correlation between Total Suspended Solids and Dissolved Organic Matter in Water Bodies from Spectral Imaging and Artificial Neural Networks
Previous Article in Journal
Early Identification of Herbicide Stress in Soybean (Glycine max (L.) Merr.) Using Chlorophyll Fluorescence Imaging Technology
Previous Article in Special Issue
Dimension Reduction Aided Hyperspectral Image Classification with a Small-sized Training Dataset: Experimental Comparisons
Open AccessArticle

Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery

by 1,2,* and 1
1
Cartography, GIS and Remote Sensing Department, Institute of Geography, University of Göttingen, Goldschmidt Street 5, 37077 Göttingen, Germany
2
Cartography and Geodesy Department, Land Management Faculty, Vietnam National University of Agriculture, Hanoi 100000, Vietnam
*
Author to whom correspondence should be addressed.
Sensors 2018, 18(1), 18; https://doi.org/10.3390/s18010018
Received: 20 November 2017 / Revised: 16 December 2017 / Accepted: 20 December 2017 / Published: 22 December 2017
(This article belongs to the Special Issue Analysis of Multispectral and Hyperspectral Data)
In previous classification studies, three non-parametric classifiers, Random Forest (RF), k-Nearest Neighbor (kNN), and Support Vector Machine (SVM), were reported as the foremost classifiers at producing high accuracies. However, only a few studies have compared the performances of these classifiers with different training sample sizes for the same remote sensing images, particularly the Sentinel-2 Multispectral Imager (MSI). In this study, we examined and compared the performances of the RF, kNN, and SVM classifiers for land use/cover classification using Sentinel-2 image data. An area of 30 × 30 km2 within the Red River Delta of Vietnam with six land use/cover types was classified using 14 different training sample sizes, including balanced and imbalanced, from 50 to over 1250 pixels/class. All classification results showed a high overall accuracy (OA) ranging from 90% to 95%. Among the three classifiers and 14 sub-datasets, SVM produced the highest OA with the least sensitivity to the training sample sizes, followed consecutively by RF and kNN. In relation to the sample size, all three classifiers showed a similar and high OA (over 93.85%) when the training sample size was large enough, i.e., greater than 750 pixels/class or representing an area of approximately 0.25% of the total study area. The high accuracy was achieved with both imbalanced and balanced datasets. View Full-Text
Keywords: Sentinel-2; Random Forest (RF); Support Vector Machine (SVM); k-Nearest Neighbor (kNN); classification algorithms; training sample size Sentinel-2; Random Forest (RF); Support Vector Machine (SVM); k-Nearest Neighbor (kNN); classification algorithms; training sample size
Show Figures

Graphical abstract

MDPI and ACS Style

Thanh Noi, P.; Kappas, M. Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors 2018, 18, 18.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map

1
Back to TopTop