RETRACTED ARTICLE: Ensemble methods-based comparative study of Landsat 8 operational land imager (OLI) and sentinel 2 multi-spectral images (MSI) for smart farming crop classification

Agriculture has a significant worldwide impact in terms of generating employment opportunities and stimulating economic growth. In India, agriculture plays a crucial role in development of food sources, boost up individual income of farmer and employment of the whole country. In the agriculture domain, meticulous machine learning-enabled crop classification is essential for production. Nowadays, for meticulous crop classification satellite images are used together with Geographical Information System (GIS) and remote sensing. Proposed ensemble methods are commonly used to estimate and examine the accomplishment of advanced machine learning concepts in the remote sensing community. In this paper, authors describe a framework with the combination of Support vector machine (SVM), Decision tree (DT), K-nearest neighbor (KNN), and Random forest (RF) and proposed ensemble method named as “SVM-DT-KNN-RF” that investigates the potential of crop mapping used to compare different architectures of machine learning as logistic regression (LR), RF, DT, KNN, SVM, bagging as well as boosting. The classifiers are tested on two remotely sensed datasets, one is Landsat 8 OLI (L8) and another is Sentinel 2 MSI (S2). The three primary findings based on our experiments are first, voting model proved to be the most accurate classifier. Second, bagging and boosting offer good accuracy in classification results. Finally, the results with two satellites i.e., S2 as well as L8 are compared. In the S2 dataset, the proposed ensemble method with a combination of two models i.e., SVM-DT, SVM-KNN and SVM-RF gave 89.1%, 89.8% and 89.7% results respectively, and the combination of four models i.e., SVM-DT-KNN-RF (for voting) is the better performer with 91.10% accuracy. In the L8 dataset, the proposed ensemble method which combines all four techniques SVM-DT-KNN-RF gave better results with a score of 90% while the worst performance was achieved by the decision tree with 79.58% accuracy. For KNN, the accuracy is 85.96%; LR has an 81.28% classification accuracy; SVM recorded an accuracy of 87.66%; and RF has an 87.37% accuracy. This study suggests that S2 provides more accuracy compared to L8.