Predicting the Peak Flow and Assessing the Hydrologic Hazard of Kessem Dam, Ethiopia using Machine Learning and RMC-RFA Software

Abstract Flooding due to overtopping during peak flow in embankment dams primarily causes dam failure. Kessem River watershed of the Awash basin in the Rift Valley of Afar region in Ethiopia has been studied intricately to predict the causes of Kessem dam safety using machine learning predictive models and Risk Management Centre-Reservoir Frequency Analysis (RMC-RFA). Recently developed Recurrent Neural Network (RNN) predictive models with hybrid with Soil Conservation Service Curve Number (SCS-CN) were used for simulation of the river flow. Peak daily inflow to the reservoir is predicted to be 467.72m3/s, 435.88m3/s, and 513.55m3/s in 2035, 2061, and 2090, respectively. The hydrologic hazard analysis results show 2,823.57m3/s and 935.21m, 2,126.3m3/s and 934.18m and 11,491.1m3/s and 942.11m 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 (AEP). 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. Hence, the dam requires further risk analysis study and dam safety modification to control this probable failure mode during the indicated time.