Abstract:
Land use/land cover (LULC) change evaluation and prediction via spatiotemporal data are cru-cial for environmental monitoring and better planning and management of land use. The main objective of this study is to evaluate land use/land cover changes from 1991–2022 and predict future changes via the CA-ANN model in the upper Omo-Gibe River Basin. Landsat-5 TM data for 1991, 1997 and 2004, Landsat-7 ETM+ data for 2010, and Landsat-8 (OLI) data for 2016 and 2022 were downloaded from the USGS Earth Explorer Data Center. A random forest machine learning algorithm was employed for LULC classification. The LULC classification results were evaluated via an accuracy assessment technique to ensure the correctness of the classification method employing the kappa coefficient. Kappa coefficient values of the classification indicate that there was strong agreement between the classified and reference data. The coupled cellular automata (CA) - Artificial neural network (ANN) machine learning model was employed for LULC change modelling and prediction via the QGIS MOLUSCE plugin. Transition potential modelling was computed, and future LULC changes were predicted via the CA-ANN model. An overall ac-curacy of 86.53% and an overall kappa value of 0.82 were obtained by comparing the actual data from 2022 with the simulated LULC data from the same year. The study findings revealed that between 2022 and 2037, agricultural land (63.09%) and shrub land (5.74%) significantly in-creased, and forest (-48.10%) and grassland (-0.31%) significantly decreased. From 2037-2052, the built-up area (2.99%) showed a significant increase, and forest and agricultural land (-2.55%) showed a significant decrease. From 2052–2067, the projected LULC simulation results revealed that agricultural land (3.15%) and built-up areas (0.32%) increased and that forest (-1.59%) and shrubland (-0.56%) significantly decreased. According to the findings of this study, the main driver of LULC change is the expansion of built-up areas and agricultural land, which calls for a thor-ough investigation using additional data and models to provide planners and policymakers with clear information on LULC change and its environmental effects
