Accomplishments
Performance Evaluation of RF and SVM for Sugarcane Classification using Sentinel-2 Time Series NDVI
- Abstract
Sentinel-2 optical time-series images obtained at high resolution are creditable for cropland mapping which is the key for sustainable agriculture. The presented work conducted in a heterogeneous region in Sameerwadi with an aim to classify sugarcane crops, with mainly two groups so as to provide sugarcane field map, using Sentinel-2 NDVI time series data. The potential of two better-known ML classifiers, random forest (RF) and support vector machine (SVM), was investigated to identify 7 classes including sugarcane, early sugarcane, maize, waterbody, fallow land, built up, bare land, and a sugarcane crop map is produced. Both the classifiers were able to effectively classify sugarcane areas and other land covers from the time series data. Our results show that the RF achieved higher overall accuracy (88.61 %) than the SVM having an overall accuracy of 81.86%.s This study demonstrated that utilizing Sentinel-2 NDVI time series with RF and SVM successfully classified sugarcane crop fields.