Predicting the peak flow and assessing the hydrologic hazard of the Kessem Dam, Ethiopia using machine learning and risk management centre-reservoir frequency analysis software

Abstract

Flooding due to overtopping during peak flow in embankment dams primarily causes dam failure. The Kessem River watershed of the Awash basin in the Rift Valley of the Afar region in Ethiopia was studied intricately to predict the causes of the Kessem Dam safety using machine learning predictive models and risk management centre-reservoir frequency analysis. Recently developed recurrent neural network predictive models with hybrid Soil Conservation Service Curve Number (SCS-CN) were used for simulation of river flow. Peak daily inflow to the reservoir is predicted to be 467.72, 435.88, and 513.55 m3/s in 2035, 2061, and 2090, respectively. The hydrologic hazard analysis results show 2,823.57 m3/s and 935.21 m; 2,126.3 m3/s and 934.18 m; and 11,491.1 m3/s and 942.11 m peak discharge and maximum reservoir water level during the periods of 2022–2050, 2051–2075, and 2076–2100, respectively, for 0.0001 annual exceedance probability. The Kessem Dam may potentially be overtopped by a flood with a return period of about 10,000 years during the period of 2076–2100. Quantitative hydrologic risk assessment of the dam is used for dam safety evaluation to decide whether the existing structure provides an adequate level of safety, and if not, what modifications are necessary to improve the dam's safety. HIGHLIGHT The importance of this study will contribute to enhancing the knowledge gap and can provide a piece of information for federal and regional policymakers and water resources implementing agencies about the upcoming flood frequency and its magnitude in the Kessem watershed on the infrastructure to control unexpected floods.;

Keywords

• dam safety
• hydrologic hazard analysis
• kessem dam
• machine learning
• peak flow prediction