Land Use/Land Cover Mapping Using Multi-temporal Sentinel-2 Imagery—A Case Study from Ramganga River Sub-basin

Evaluation of river basins requires land-use and land-cover (LULC) change detection to determine hydrological and ecological conditions for sustainable use of their resources. This study investigates the changes in cropping patterns, classification accuracy, and land use patterns during the kharif and rabi seasons of 2018-19. The supervised classification, employing the maximum likelihood classifier method, was used to generate the classified LULC maps in the ERDAS Imagine. The classified images produced by this technique were evaluated for accuracy through matrix union using the statistical kappa coefficient and overall accuracy measures. Change detection for the periods 2018-19 was conducted using matrix union (intersection) to identify apparent changes in various LULC classes. The analysis shows a significant shift in cropping practices, particularly a notable transition from rice to wheat during the rabi season, with wheat cultivation increasing by 75.53%. Other crops such as mustard, vegetable pea, and sugarcane also saw significant changes in acreage, reflecting farmer’s responses to market and climatic conditions. Soybean, traditionally grown during the kharif season, shifted to wheat in the rabi season. The classification accuracy for both kharif and rabi crops was high, with overall accuracies of 92.95% and 94.02%, respectively, and Kappa coefficients of 89.98% and 92.81%, indicating reliable classification results. Key challenges included resolving spectral confusion between crops (e.g., wheat vs. mustard) and addressing cloud cover limitations in kharif-season imagery. The study’s contributions include: (1) a robust framework for high-resolution crop monitoring in heterogeneous landscapes, (2) quantification of rapid cropping system transitions, and (3) demonstration of Sentinel-2’s operational utility for precision agriculture. Results support evidence-based policymaking for sustainable water and land use in monsoon-dependent systems.