Land use/ land cover change causes unprecedented changes on the surrounding environment at different spatial and temporal scales. Muga watershed of the Abbay River Basin is characterized by deterioration with mismanagement of natural resources. Thus, this study was aimed at detecting the magnitude and pattern of land use/land cover changes and assessing drivers of changes over the last three decades (1985 to 2017) in the Muga watershed. Synergy of Landsat imageries (1985, 2002, and 2017), household survey, focus group discussion, key informant interview and field observation were used to detect changes and drivers of changes. Land use/land cover changes in the study watershed were detected using digital image analysis techniques, and their socioeconomic and biophysical drivers were analyzed using descriptive statistics. The change detection results exhibited a significant increasing trend of cultivated land and urban areas by 12 and 270%, respectively, from 1985 to 2017. In contrast, grasslands, forest lands, and shrub-bushlands showed a declining trend of about 40, 21 and 12%, respectively. The results from the household survey showed that the expansion of cultivated land, cutting of trees for fuelwood and construction purposes, population growth, land tenure policy and climate variability were the most influential drivers of land use/ land cover changes in the study watershed. Thus, alternative sources of income for youths and landless peasants and integrated watershed management, which has paramount importance in maintaining economic and ecological benefits were suggested to alleviate the adverse effects of LULC changes in Muga watershed. Soil erosion is one of the major threats in the Ethiopian highlands. In this study, soil erosion in the Muga watershed of the Abbay River Basin under historical and future climate and land use/ land cover (LULC) change was assessed. Future LULC was predicted based on LULC map of 1985, 2002, and 2017. LULC maps of the historical periods were delineated from Landsat images, and future LULC was predicted using the CA-Markov chain model. Precipitation for the future period was projected from six regional circulation models. The RUSLE model was used to estimate the current and future soil erosion rate in Muga watershed. The results of the study show that the average annual rate of soil erosion in the Muga watershed was increased from approximately 15 t ha -1 year -1 in 1985 to 19 t ha -1 year -1 in 2002 and 19.7 t ha -1 year -1 in 2017. If a proper measure against the LULC changes is not taken, the soil loss rate is expected to increase and reach about 20.7 t h -1 yr -1 in 2033. The results of the study also show that in the 2050s, soil erosion is projected to increase by 9.6% and 11.3% under RCP4.5 and RCP8.5, respectively compared with the baseline period. When both LULC and climate changes act together, the mean annual soil loss rate shows a rise of 13.2% and 15.7% in the future under RCP4.5 and RCP8.5, respectively, which is due to synergistic effects. The results of this study can be useful for formulating proper land use planning and investments to mitigate the adverse effect of LULC and climate change on soil loss. The study also demonstrated the importance of an integrated approach, assessing the combined impacts of LULC and climate change, for accurate estimation of soil losses.