Comparing the Effectiveness of Different Machine Learning Algorithms for Crop Cover Classification Using Sentinel 2

Crop cover mapping is an essential tool for controlling and enhancing agricultural productivity. By determining the spatial distribution of different crop types, solidified judgements regarding planning, management, risk management can be made. classification using optical data pose constraints in terms spectral resolution. With Sentinel – 2 providing ground information at 10m resolution, users may choose best band combinations temporal frame by analysing spectral-temporal crops. The categorization map Kallakurichi Villupuram districts were created this study Random Forest (RF) Decision tree (C5.0) classifiers. mainly focuses on comparing accuracy two classifiers figuring out with respect to area. truth collected, partitioned into calibration validation datasets resulted Overall Accuracy (OA) kappa coefficient 66%; 0.63 60%; 0.67 RF C5.0 algorithms, respectively. From results, it could concluded that classifier performed comparatively better than C5.0, thus making suitable classification.