Land use and land cover modification have been observed at an intense level in the Rupnarayan basin, West Bengal, India, due to the rapid expansion of fallow land and built-up area, and the decrease in water bodies and vegetation area. However, monitoring and quantifying the effects of rural catchment area modification is challenging. The heterogeneous landscape of the Rupnarayan catchment area was assessed using multispectral satellite data for 2000, 2010 and 2020 to identify land-cover change. Quantitative Evaluation of various Machine Learning techniques is adopted for the current research work, i.e., Support Vector Machine (SVM), Random Forest (RF) and Maximum Likelihood Classifier (MLC). The novelty of this work lies in benchmarking a parametric (MLC) classifier against two non-parametric classifiers (RF and SVM) within a single Google Earth Engine workflow and validating every annual map with both the Kappa statistic and AUC-ROC analysis for a previously unassessed rural reach of the basin. Five features have been taken for assessing the change detection over the region, i.e., built-up, agricultural land, fallow land, vegetation and water body. After performing each ML algorithm, SVM performed the best result among others with the overall accuracy rate of 97% (2000), 95% (2010) and 95% (2020) and a Kappa value of 0.95, while the other two scored in kappa 0.89 and 0.87 in MLC and RF, respectively. The analysis has been cross-checked by the AUC-ROC curve model. In 2000, the AUC value obtained 0.778 in MLC, RF AUC is 0.689, and SVM AUC is 0.946. In 2010, the MLC AUC is 0.875, the RF AUC value is 0.766, and the SVM value is obtained as 0.969. Finally, the 2020 map of each algorithm has been applied for the AUC curve, where the MLC curve value is 0.898, the RF value is 0.794, and the SVM obtained an AUC of 0.986. From the entire validation model, it has been revealed that SVM acquired the maximum AUC value for each year. This research will be beneficial for future researchers, policymakers, and land planners in enhancing management strategies for sustainable development.