No abstract

In this study, Revised Universal Soil Loss Equation (RUSLE) model and Geographic Information System (GIS) platforms were successfully applied to quantify the annual soil loss for the protection of soil erosion in Fincha catchment, Ethiopia. The key physical factors such as rainfall erosivity ( R-factor), soil erodibility ( K-factor), topographic condition (LS-factor), cover management ( C-factor), and support practice ( P-factor) were prepared in GIS environment from rainfall, soil, Digital Elevation Model (DEM), Land use/Land cover (LULC) respectively. The RUSLE equation was used in raster calculator of ArcGIS spatial tool analyst. The individual map of the derived factors was multiplied in the raster calculator and an average annual soil loss ranges from 0.0 to 76.5 t ha−1 yr−1 was estimated. The estimated annual soil loss was categorized based on the qualitative and quantitative classifications as Very Low (0–15 t ha−1 yr−1), Low (15–45 t ha−1 yr−1), Moderate (45–75 t ha−1 yr−1), and High (>75 t ha−1 yr−1). It was found from the generated soil erosion severity map that about 45% of the catchment area was vulnerable to the erosion with an annual soil loss of (>75 t ha−1 yr−1), and this demonstrates that the erosion reduction actions are immediately required to ensure the sustainable soil resources in the study area. The soil erosion severity map generated based on RUSLE model and GIS platforms have a paramount role to alert all stakeholders in controlling the effects of the erosion. The results of the RUSLE model can also be further considered along with the catchment for practical soil loss protection practices.

This study presents an integrated machine-learning and HEC-RAS models for flood inundation mapping in Baro River Basin, Ethiopia. ANN and HEC-RAS models were integrated as a predictive hydrological and hydraulic model to generate runoff and the extent of flood, respectively. Daily rainfall and temperature data of 7-years (1999–2005), daily discharge (1999–2005) and 30 m × 30 m gridded Topographical Wetness Index (TWI) were used to train a predictive ANN hydrological model in RStudio. The predictive performance of the developed ANN hydrological model was evaluated in RStudio using Nash–Sutcliffe Efficiency (NSE) values of 0.86 and 0.88 during the training period (1999–2005) and testing period (2006–2008), respectively, with the corresponding observed daily discharge. The validated ANN predictive hydrological model was linked with HEC-RAS to generate the flood extent along the river course. The HEC-RAS model result was calibrated and validated using the water body delineated using Normal Difference Water Index (NDWI) from LANDSAT 8 imagery based on historical flood events of 2005 and 2008. It was found that about 96% of an agreement was made between the flood-prone areas generated in HEC-RAS and the water body delineated using NDWI. Therefore, it is logical to conclude that the integration of a machine-learning approach with the HEC-RAS model has improved the spatiotemporal uncertainties in traditional flood forecasting methods. This integrated model is powerful tool for flood inundation mapping to warn residents of this basin.

This study presents the novelty artificial intelligence in geospatial analysis for flood vulnerability assessment in Dire Dawa, Ethiopia. Flood-causing factors such as rainfall, slope, LULC, elevation NDVI, TWI, SAVI, K-factor, R-factor, river distance, geomorphology, road distance, SPI, and population density were used to train the ANN model. The weights were generated in the ANN model and prioritized. Initial values were randomly assigned to the NN and trained with the feedforward processes. Ground-truthing points collected from the historical flood events of 2006 were used as targeting data during the training. A rough flood hazard map generated in feedforward was compared with the actual data, and the errors were propagated back into the NN with the backpropagation technique, and this step was repeated until a good agreement was made between the result of the GIS-ANN and the historical flood events. The results were overlapped with ground-truthing points at 88.46% and 89.15% agreement during training and validation periods. Therefore, the application of the GIS-ANN for the assessment of flood vulnerable zones for this city and its catchment was successful. The result of this study can also be further considered along with the city and its catchment for practical flood management.

No abstract