Volume XLII-5
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-5, 683-688, 2018
https://doi.org/10.5194/isprs-archives-XLII-5-683-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-5, 683-688, 2018
https://doi.org/10.5194/isprs-archives-XLII-5-683-2018
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

  19 Nov 2018

19 Nov 2018

CROP CLASSIFICATION ON SINGLE DATE SENTINEL-2 IMAGERY USING RANDOM FOREST AND SUPPOR VECTOR MACHINE

R. Saini1,2 and S. K. Ghosh2 R. Saini and S. K. Ghosh
  • 1Department of Computer Science, G. B. Pant Engineering College, Pauri, 246001, India
  • 2Geomatics Engineering Group, Department of Civil Engineering, IIT Roorkee, 247667, India

Keywords: Sentinel-2, Vegetation mapping, Crop classification, Machine learning, Support Vector Machine, Random Forest

Abstract. Mapping of the crop using satellite images is a challenging task due to complexities within field, and having the similar spectral properties with other crops in the region. Recently launched Sentinel-2 satellite has thirteen spectral bands, fast revisit time and resolution at three different level (10m, 20m, 60m), as well as the free availability of data, makes it a good choice for vegetation mapping. This study aims to classify crop using single date Sentinel-2 imagery in the Roorkee, district Haridwar, Uttarakhand, India. Classification is performed by using two most popular and efficient machine learning algorithms: Random Forest (RF) and Support Vector Machine (SVM). In this study, four spectral bands, i.e., Near Infrared, Red, Green, and Blue of Sentinel-2 satellite are stacked for the classification. Results show that overall accuracy of the classification achieved by RF and SVM using Sentinel-2 imagery are 84.22% and 81.85% respectively. This study demonstrates that both classifiers performed well by setting an optimal value of tuning parameters, but RF achieved 2.37% higher overall accuracy over SVM. Analysis of the results states that the class specific accuracies of High-Density Forest attain the highest accuracy whereas Fodder class reports the lowest accuracy. Fodder achieve lowest accuracy because there is an intermixing of pixels among Wheat and Fodder crops. In this study, it is found that RF shows better potential in classifying crops more accurately in comparison to SVM and Sentinel-2 has great potential in vegetation mapping domain in remote sensing.