Monitoring and Future Projection of Land Use Land Cover Dynamics in Northeastern Bangladesh Using Remote Sensing and CA-ANN Modeling

The northeastern hilly region of Bangladesh is characterized by subtropical evergreen hilly forests, haors, tea estates, and nationally designated protected areas and is undergoing rapid land-use transformation. This study analyzes spatiotemporal changes in land use and land cover (LULC) in Moulvibazar and Habiganj districts of Bangladesh over three decades (1994–2024) using Landsat imagery and supervised Maximum Likelihood Classification in QGIS and predicts future LULC for 2034, 2044, and 2054 using the Cellular Automata-Artificial Neural Network (CA-ANN) model in the MOLUSCE (Modules for Land Use Change Evaluation) plugin. Five major land cover classes were examined: croplands, water bodies, forests, tea gardens, and settlements. The classified LULC maps achieved overall accuracies of 85.23–90.67% with Kappa coefficients of 0.76–0.81, indicating strong classification reliability. Croplands declined substantially from 379,716.66 ha (72.07%) in 1994 to 303,873.97 ha (57.68%) in 2024, representing a decrease of 14.39% in their proportional coverage. Tea garden area increased from 28,523.84 ha (5.41%) in 1994 to 69,600.19 ha (13.21%) in 2024, representing an expansion of approximately 144% over the study period. Forests showed a non-linear trend, initially declining between 1994 and 2004 before increasing to 98,282.60 ha (18.65%) in 2024, while settlement areas expanded from 17,103.54 ha (3.25%) to 26,795.58 ha (5.09%). The simulated future LULC change was calibrated with the LULC changes from 2004 to 2014 and validated against the LULC map for 2024 (Kappa = 0.877). The validated model made projections for business-as-usual LULC scenarios until 2054, showing a reduction in cropland from 57.68% to 53.23% and an increase in settlements from 5.09% to 9.64%. The extent of forest cover has decreased moderately (18.65% to 17.47%), while that of tea gardens has remained fairly stable (~13%). The results indicate increasing land-use pressure on the hilly landscape under current transition trends.