Abstract
Land-use and land-cover (LULC) changes have become a crucial issue that urgently needs to be addressed due to global environmental change. Many studies have employed remote sensing data for assessing LULC changes, however, the investigation of fragmentation probability modeling is still scarce in the existing literature. Thus, the coupling of bagging, random forest (RF), random subspace (RSS), and their ensemble model with multitemporal datasets within the GIS environment makes it possible to model the fragmentation probability of LULC in the Teesta River Basin (TRB), Bangladesh. The number of patch (NP), edge density (ED), largest patch index (LPI), contagion index (%) (CONTAG), aggregation index (AI), perimeter area ratio (P/A ratio), the class area (CA), percentage of landscape (PLAND), patch density (PD), total edge (TE), largest shape index (LSI) and total core area (TCA) were the landscape and class matrices, which were derived from the LULC maps using FRAGSTATS software. The machine learning-based sensitivity models, such as decision tree and support vector machine-based feature selection techniques were implemented to explore the influence of the parameters for fragmentation probability modeling. The results showed that water bodies and barren land were substantially decreased by (6.21%), and (14.59%) respectively while the built-up areas increased by 1.45% from 2010 to 2019. Results revealed that the dominance of the agricultural area has been increased as human interference has been elevated in the TRB. However, twelve class-level and landscape matrices were used to delineate the fragmentation probability zone with the aid of bagging, RF, and RSS algorithms. LULC images and fragmentation probability models were validated using the kappa coefficient and the area under curve (AUC) of the receiver operating characteristics (ROC). The validation outcomes depicted that the three models such as bagging (AUC = 0.864), RF (AUC = 0.819), RSS (AUC = 0.859), and ensemble model (AUC = 0.912) have a good capability to appraise the fragmentation probability, and ensemble model has the highest precision level among three models. Nearly 49% (1789 km2) of the LULC was under a high to very high fragmentation potential zone that requires to be protected with direct measures. The results of sensitivity analysis showed that the number of patches significantly influenced the fragmentation probability model, while the largest patch index was the least sensitive parameter for modeling.