Wessels, Gert JBotha, NatashaKoen, Hildegarde SVan Eden, Beatrice2023-01-172023-01-172022-11Wessels, G.J., Botha, N., Koen, H.S. & Van Eden, B. 2022. Towards better flood risk management using a Bayesian network approach. http://hdl.handle.net/10204/12579 .https://doi.org/10.1051/matecconf/202237007001http://hdl.handle.net/10204/12579After years of drought, the rainy season is always welcomed. Unfortunately, this can also herald widespread flooding which can result in loss of livelihood, property, and human life. In this study a Bayesian network is used to develop a flood prediction model for a Tshwane catchment area prone to flash floods. This causal model was considered due to a shortage of flood data. The developed Bayesian network was evaluated by environmental domain experts and implemented in Python through pyAgrum. Three what-if scenarios are used to verify the model and estimation of probabilities which were based on expert knowledge. The model was then used to predict a low and high rainfall scenario. It was able to predict no flooding events for a low rainfall scenario, and flooding events, especially around the rivers, for a high rainfall scenario. The model therefore behaves as expected.FulltextenFlood prediction modelTshwane catchment areaFloodingIndustrial AIConference PresentationWessels, G. J., Botha, N., Koen, H. S., & Van Eden, B. (2022). Towards better flood risk management using a Bayesian network approach. http://hdl.handle.net/10204/12579Wessels, Gert J, Natasha Botha, Hildegarde S Koen, and Beatrice Van Eden. "Towards better flood risk management using a Bayesian network approach." <i>23rd Annual International RAPDASA Conference joined by RobMech, PRASA and CoSAAMI, Somerset-West, Cape Town, 9-11 November 2022</i> (2022): http://hdl.handle.net/10204/12579Wessels GJ, Botha N, Koen HS, Van Eden B, Towards better flood risk management using a Bayesian network approach; 2022. http://hdl.handle.net/10204/12579 .TY - Conference Presentation AU - Wessels, Gert J AU - Botha, Natasha AU - Koen, Hildegarde S AU - Van Eden, Beatrice AB - After years of drought, the rainy season is always welcomed. Unfortunately, this can also herald widespread flooding which can result in loss of livelihood, property, and human life. In this study a Bayesian network is used to develop a flood prediction model for a Tshwane catchment area prone to flash floods. This causal model was considered due to a shortage of flood data. The developed Bayesian network was evaluated by environmental domain experts and implemented in Python through pyAgrum. Three what-if scenarios are used to verify the model and estimation of probabilities which were based on expert knowledge. The model was then used to predict a low and high rainfall scenario. It was able to predict no flooding events for a low rainfall scenario, and flooding events, especially around the rivers, for a high rainfall scenario. The model therefore behaves as expected. DA - 2022-11 DB - ResearchSpace DP - CSIR J1 - 23rd Annual International RAPDASA Conference joined by RobMech, PRASA and CoSAAMI, Somerset-West, Cape Town, 9-11 November 2022 KW - Flood prediction model KW - Tshwane catchment area KW - Flooding KW - Industrial AI LK - https://researchspace.csir.co.za PY - 2022 T1 - Towards better flood risk management using a Bayesian network approach TI - Towards better flood risk management using a Bayesian network approach UR - http://hdl.handle.net/10204/12579 ER -26371