Impacts of land use and land cover changes on hydrology of the Gumara catchment, Ethiopia

Land use and land cover (LULC) changes are continuous phenomena, often driven by natural and anthropogenic factors. In Ethiopia, a conversion of forest and grass lands into cultivated and urbanized lands has been reported. While such changes are known to have multidirectional impacts on river flows, erosion and sedimentation, and the socio-economic situation within a catchment, there is a lack of assessment on the scale and rate of these changes, and consequent impacts. This study quantifies the rate of LULC in the Gumara catchment (1413 km(2)), an important tributary to Lake Tana in northwest Ethiopia. Landsat images of three years (1986, 2001 and 2015) were processed using the supervised classification method. An extensive field survey generated over 150 ground truth points, which were used in the classification and accuracy assessment process. Then, a conceptual rainfall-runoff model (HBV) was calibrated and validated to assess the impacts of LULC changes on water balance components - evapotranspiration, soil moisture, groundwater recharge and runoff. Additionally, the decadal means and trends of precipitation and discharge were analysed to further examine and quantify the observed changes (if any). A reasonably reliable LULC classification was achieved, with an overall accuracy of 90%. The results indicated that the catchment area under forest and grass land was about 11 and 18%, respectively, in 1986, which reduced to 5 and 10%, respectively, in 2015. In contrast, cultivated land increased from 70% in 1986 to 82% in 2015. Contrary to the expected impact of these LULC changes on hydrology, the HBV model, indicated only a slight change in the water balance components (+/- 5%). Runoff and all other water balance components remained more or less stable despite considerable LULC changes. However, the uncertainties encountered in the modelling process (e.g. model structure, LULC representation) could have masked the LULC impacts on hydrology. This was supported by the significant increase in the observed discharge indicated by the statistical analysis, even in view of no substantial changes in precipitation. Therefore, LULC could cause considerable increase in discharge, which needs further testing (e.g. through physically based modelling with detailed inclusion of LULC processes).