Land Use Land Cover Change in the African Great Lakes Region: A Spatial-Temporal Analysis and Future Predictions for the Lake Kivu catchment, Rwanda.

Abstract

The African Great Lakes Region has experienced substantial Land Use Land Cover Change (LULCC) over the last decades. The main drivers of LULCC include an interplay of political, demographic, and socio-economic factors. This study focused on the Lake Kivu catchment in Rwanda, a critical ecosystem in the African Great Lakes Regions, exploring historical LULCC, their major drivers, and predicting future LULC for different development scenarios. The methodology involved image classification using seasonal composites and integrating spectral indices with topographic features to enhance the discrimination and capturing seasonal variations. The classification results demonstrated an overall accuracy and kappa exceeding 83%. Historical LULCC analysis showed significant changes, particularly the 1990–2000 decade, marked by forest loss ranging from 26.6–18.7% and an increase in agricultural land (from 27.7–43%). These changes were attributed to political conflicts in the region and population movements. Subsequent decades (2000–2010 and 2010–2020) witnessed forest recovery (24.8% by 2020). Artificial neural networks were used to predict future LULC scenarios, considering natural and socio-economic explanatory variables and historical LULC transitions. The analysis of explanatory variables highlighted the significant role of proximity to urban centers, population density, and terrain, in LULCC. River proximity drove agricultural and grassland expansion. The predicted future LULC for 2030 and 2050 indicate distinct trajectories likely to be influenced by demographic and socio-economic development trends. The findings of this study contribute to identifying opportunities for land restoration and conservation efforts, thereby ensuring the preservation of Lake Kivu catchment’s ecological integrity.