Land cover change is a global problem but effects can be particularly severe in developing countries such as Namibia because it affects the social, cultural, and ecological functions of ecosystems, and can negatively affect sustainable development. Detailed studies on land cover change and the associated spatial drivers which are either directly or indirectly driving this change in the north-eastern parts of Namibia are limited. This is despite the area being part of the Kavango Zambezi Trans Frontier Conservation Area (KAZA-TFCA) which is the largest transboundary conservation area in the world. The purpose of this study was to determine the extent of land cover change during the period 1990 - 2016 in Kavango East Region, Namibia, as well as the spatial variables that may influence land cover change, their interactions and variability over time. Using Remote Sensing, GIS and Boosted Regression Trees, the study analysed the relationship between land cover change and the spatial variables, and evaluated the evolution of the spatial variables based on the statistical models during the 26-year period. The results showed that a large portion of the study has remained unchanged. The influence from the variables varied in each epoch. The predictor variables such as population density, distance to road, distance to river and distance to settlement were found to have the highest influence in the conversion of forest land to cropland. Human related predictor variables contributed more to model performance than natural factors. Further studies should use high resolution satellite imagery like Sentinel data, and other variables such as cattle density, game density, annual mean temperature, precipitation seasonality, NDVI, crown cover and slope to provide a comprehensive land cover change analysis including the variability of these predictor variables over time. The results from the models in this study may be used in a land cover change framework for environmental monitoring, spatial planning and situation analysis at local and national levels of government. Keywords: segmentation, classification, spatial variables, land cover change, boosted regression trees.