Flood Mitigation in Ethekwini Metropolitan Area – Empirical Evidence using Artificial Neural Network

Flood Mitigation in Ethekwini Metropolitan Area – Empirical Evidence using Artificial Neural Network

Caroline C. Olanrewaju , Maliga Reddy & Oludolapo A. Olanrewaju

Issue: Vol.6 No.15 Article 22 pp. 4520 – 4536
DOI: https://doi.org/10.38159/ehass.202561522| Published online 30th December, 2025
© 2025 The Author(s). This is an open access article under the CCBY license (http://creativecommons.org/licenses/by/4.0/).

54 Downloads

DOWNLOAD PDF

ABSTRACT

Knowledge of flood patterns is very crucial for developing mitigation strategies and flood risk management. Historical data for floods in the SADC region from 2000 to 2016 indicates 198 flood occurrences leading to total deaths of 3,974, injuries of 2,666, homelessness of 417,745, affected 16,142,359 and total damages of over USD 2.4 billion. The April 2022 flood disaster in the eThekwini Metropolitan Area was extremely devastating with high economic consequences. The loss to GDP since then is estimated to be about R737 million. Timely flood warnings can reduce or eliminate the devastating consequences of flood disasters by enabling effective evacuation and implementation of temporary flood mitigation measures. Accurate flood prediction can significantly lead to a precise mitigation of economic and physical damages and improve human safety. In this study, hydro-meteorological variables, which include rainfall (Intensity, duration, frequency, depth), temperature, wind speed, humidity, pressure and dewpoint, were used as input variables and flood was used as the output variable from 1985-2016 in the development of the Artificial Neural Network (ANN) model to forecast flood disasters in the eThekwini Metropolitan area. This was achieved by studying the relationship between the observed and predicted values. With the results obtained, it is possible to arrange the hydro-meteorological variables used in this study in order of importance, thus focusing on variables that are most significant when drawing up mitigation measures for floods in the study area. These measures, when implemented, can reduce floods and their consequences, reduce resources used to manage floods and improve flood management.

Keywords: Mitigation strategies, Flood management, hydro-meteorological, Artificial Neural Network, eThekwini Metropolitan Area

BIBLIOGRAPHY

Abbot, John, and Jennifer Marohasy. “Input Selection and Optimisation for Monthly Rainfall Forecasting in Queensland, Australia, Using Artificial Neural Networks.” Atmospheric Research 138 (March 2014): 166–78. https://doi.org/10.1016/j.atmosres.2013.11.002.

Berkhahn, Simon, Lothar Fuchs, and Insa Neuweiler. “An Ensemble Neural Network Model for Real-Time Prediction of Urban Floods.” Journal of Hydrology 575 (2019): 743–54.

Bhatia, I. “Understanding Wind Speed and Its Weather Impact,” 2025. https://luminwaves.com/articles/understanding-wind-speed-weather-impact/.

Bhatia, Ishan. “Understanding Wind Speed and Its Weather Impact,” 2025.

Bracken, L. J, N. J Cox, and J Shannon. “The Relationship between Rainfall Inputs and Flood Generation in South-East Spain.” Hydrological Processes 22 (2008): 683–96. https://doi.org/10.1002/hyp.

Climatemp. “Rainfall/Precipitation in Durban, South Africa,” 2017. http://www.durban.climatemps.com/precipitation.php.

Comins, L. “ KZN Floods: Economic Impact Update | Freight News.” Business Partners, 2022. https://www.freightnews.co.za/article/kzn-floods-economic-impact-update.

Costabile, Pierfranco, and Francesco Macchione. “Enhancing River Model Set-up for 2-D Dynamic Flood Modelling.” Environmental Modelling & Software 67 (May 2015): 89–107. https://doi.org/10.1016/j.envsoft.2015.01.009.

Daya, Salim. “Correlation Coefficient.” Evidence-Based Obstetrics and Gynecology 6, no. 2 (2004): 48–50. https://doi.org/10.1016/j.ebobgyn.2004.04.015.

Doswell, Charles A., Harold E. Brooks, and Robert A. Maddox. “Flash Flood Forecasting: An Ingredients-Based Methodology.” Weather and Forecasting 11, no. 4 (December 1996): 560–81. https://doi.org/10.1175/1520-0434(1996)011<0560:FFFAIB>2.0.CO;2.

El-Shafie, A, Muhammad Mukhlisin, Ali A Najah, and Mohd Raihan Taha. “Performance of Artificial Neural Network and Regression Techniques for Rainfall-Runoff Prediction.” International Journal of Physical Sciences 6, no. 8 (2011): 1997–2003.

Gazzaz, Nabeel M., Mohd Kamil Yusoff, Ahmad Zaharin Aris, Hafizan Juahir, and Mohammad Firuz Ramli. “Artificial Neural Network Modeling of the Water Quality Index for Kinta River (Malaysia) Using Water Quality Variables as Predictors.” Marine Pollution Bulletin 64, no. 11 (November 2012): 2409–20. https://doi.org/10.1016/j.marpolbul.2012.08.005.

Grecu, M., and W. F. Krajewski. “A Large-Sample Investigation of Statistical Procedures for Radar Based Short-Term Quantitative Precipitation Forecasting.” Journal of Hydrology 239, no. 1–4 (2000): 69–84. https://doi.org/10.1016/S0022-1694(00)00360-7.

Guha, Sreeparna, Rabin K Jana, and Manas K Sanyal. “Artificial Neural Network Approaches for Disaster Management: A Literature Review.” International Journal of Disaster Risk Reduction 81 (2022): 103276.

Hlahla, Sithabile, and Trevor R. Hill. “Responses to Climate Variability in Urban Poor Communities in Pietermaritzburg, KwaZulu-Natal, South Africa.” Sage Open 8, no. 3 (July 18, 2018). https://doi.org/10.1177/2158244018800914.

Honert, Robin C. Van den, and John McAneney. “The 2011 Brisbane Floods: Causes, Impacts and Implications.” Water 3, no. 4 (December 9, 2011): 1149–73. https://doi.org/10.3390/w3041149.

Hsu, C.-C, and C.-Y Chen. “Regional Load Forecasting in Taiwan-Applications of Artificial Neural Networks. .” Energy Conversion and Management 44 (2003): 1941–49.

Hung, N. Q., M. S. Babel, S. Weesakul, and N. K. Tripathi. “An Artificial Neural Network Model for Rainfall Forecasting in Bangkok, Thailand.” Hydrology and Earth System Sciences 13, no. 8 (August 7, 2009): 1413–25. https://doi.org/10.5194/hess-13-1413-2009.

Jaafar, Khairah, Nurlaila Ismail, Mazidah Tajjudin, Ramli Adnan, and Mohd Hezri Fazalul Rahiman. “A Review on Flood Modelling and Rainfall-Runoff Relationships.” In 2015 IEEE 6th Control and System Graduate Research Colloquium (ICSGRC), 158–62. IEEE, 2015. https://doi.org/10.1109/ICSGRC.2015.7412484.

Jeba, G. Selva, and P. Chitra. “Flood Prediction through Hydrological Modeling of Rainfall Using Conv1D-SBiGRU Algorithm and RDI Estimation: A Hybrid Approach.” Stochastic Environmental Research and Risk Assessment 38, no. 9 (September 20, 2024): 3587–3606. https://doi.org/10.1007/s00477-024-02768-2.

Karl, Anil Kumar, and Anil Kumar Lohani. “Development of Flood Forecasting System Using Statistical and ANN Techniques in the Downstream Catchment of Mahanadi Basin, India.” Journal of Water Resource and Protection 02, no. 10 (2010): 880–87. https://doi.org/10.4236/jwarp.2010.210105.

Kaur, Amanpreet, and Harpreet Singh. “Artificial Neural Networks in Forecasting Minimum Temperature.” International Journal of Electronics & Communication Technology 2, no. 3 (2011): 101–5.

Kim, Byunghyun, Brett F. Sanders, James S. Famiglietti, and Vincent Guinot. “Urban Flood Modeling with Porous Shallow-Water Equations: A Case Study of Model Errors in the Presence of Anisotropic Porosity.” Journal of Hydrology 523 (April 2015): 680–92. https://doi.org/10.1016/j.jhydrol.2015.01.059.

Kovithaa, S., and D. Naidoo. “Rainfall–Runoff Modelling Using Artificial Neural Networks in South Africa.” In Proceedings of the 14th Water Net/WARFSA/GWP-SA Symposium, Maputo, Mozambique, 2011.

Mekanik, F., M.A. Imteaz, S. Gato-Trinidad, and A. Elmahdi. “Multiple Regression and Artificial Neural Network for Long-Term Rainfall Forecasting Using Large Scale Climate Modes.” Journal of Hydrology 503 (October 2013): 11–21. https://doi.org/10.1016/j.jhydrol.2013.08.035.

Metropolitan SDF. “ Ethekwini Metropolitan KZN, COGTA,” 2021. https://www.cogta.gov.za/ddm/wp-content/uploads/2020/07/Metro-Profile_Ethekwini.pdf.

Michielsen, Astrid, Zahra Kalantari, Steve W. Lyon, and Eva Liljegren. “Predicting and Communicating Flood Risk of Transport Infrastructure Based on Watershed Characteristics.” Journal of Environmental Management 182 (November 2016): 505–18. https://doi.org/10.1016/j.jenvman.2016.07.051.

Mosavi, Amir, Pinar Ozturk, and Kwok-wing Chau. “Flood Prediction Using Machine Learning Models: Literature Review.” Water 10, no. 11 (October 27, 2018): 1536. https://doi.org/10.3390/w10111536.

Nash, David. “The 2022 Durban Floods Were the Most Catastrophic yet Recorded in KwaZulu-Natal.” Wits University, 2023.

Nayak, P. C., K. P. Sudheer, D. M. Rangan, and K. S. Ramasastri. “Short‐term Flood Forecasting with a Neurofuzzy Model.” Water Resources Research 41, no. 4 (April 5, 2005). https://doi.org/10.1029/2004WR003562.

Olanrewaju, Caroline C., and Maliga Reddy. “Assessment and Prediction of Flood Hazards Using Standardized Precipitation Index—A Case Study of EThekwini Metropolitan Area.” Journal of Flood Risk Management 15, no. 2 (2022): 1–12. https://doi.org/10.1111/jfr3.12788.

Olanrewaju, Caroline C, and Maliga Reddy. “Assessment and Prediction of Flood Hazards Using Standardized Precipitation Index — A Case Study of EThekwini Metropolitan Area.” J Flood Risk Management, no. January 2021 (2022): 1–12. https://doi.org/10.1111/jfr3.12788.

Olanrewaju, O A, A A Jimoh, and P A Kholopane. “Evaluating GHG Components Using Artificial Intelligence: Connection Weight Approach.” In 2012 IEEE International Conference on Industrial Engineering and Engineering Management, 1214–17. IEEE, 2012.

Olden, Julian D, and Donald A Jackson. “Illuminating the ‘Black Box’: A Randomization Approach for Understanding Variable Contributions in Artificial Neural Networks.” Ecological Modelling 154, no. 1–2 (2002): 135–50.

Pourazar, Elham. “Spaces of Vulnerability and Areas Prone to Natural Disaster and Crisis in Six SADC Countries.” International Organization for Migration, 2017, 1–132. https://doi.org/10.1016/j.compstruct.2016.09.063.

Qatrinnada, Winona Fritzie Putri, Entin Hidayah, Gusfan Halik, and Retno Utami Agung Wiyono. “A Literature Review: Rainfall Thresholds as Flash Flood Monitoring for an Early Warning System.” Water Practice & Technology 19, no. 11 (November 1, 2024): 4486–98. https://doi.org/10.2166/wpt.2024.271.

Rakesh Tanty, and Tanweer S. Desmukh. “Application of Artificial Neural Network in Hydrology- A Review.” International Journal of Engineering Research And V4, no. 06 (June 10, 2015). https://doi.org/10.17577/IJERTV4IS060247.

Ratner, Bruce. “The Correlation Coefficient: Its Values Range between +1/−1, or Do They?” Journal of Targeting, Measurement and Analysis for Marketing 17, no. 2 (June 18, 2009): 139–42. https://doi.org/10.1057/jt.2009.5.

Riad, S., J. Mania, L. Bouchaou, and Y. Najjar. “Rainfall-Runoff Model Using an Artificial Neural Network Approach.” Mathematical and Computer Modelling 40, no. 7–8 (2004): 839–46. https://doi.org/10.1016/j.mcm.2004.10.012.

Ruslan, Fazlina Ahmat, Nur Khalidah Zakaria, and Ramli Adnan. “Flood Modelling Using Artificial Neural Network.” In 2013 IEEE 4th Control and System Graduate Research Colloquium, 116–20. IEEE, 2013. https://doi.org/10.1109/ICSGRC.2013.6653287.

Seo, Dong-Jun, and J. P. Breidenbach. “Real-Time Correction of Spatially Nonuniform Bias in Radar Rainfall Data Using Rain Gauge Measurements.” Journal of Hydrometeorology 3, no. 2 (April 2002): 93–111. https://doi.org/10.1175/1525-7541(2002)003<0093:RTCOSN>2.0.CO;2.

Seo, Dong Jun, and J. P. Breidenbach. “Real-Time Correction of Spatially Nonuniform Bias in Radar Rainfall Data Using Rain Gauge Measurements.” Journal of Hydrometeorology 3, no. 2 (2002): 93–111. https://doi.org/10.1175/1525-7541(2002)003<0093:RTCOSN>2.0.CO;2.

Shrestha, D. L., D. E. Robertson, Q. J. Wang, T. C. Pagano, and H. A. P. Hapuarachchi. “Evaluation of Numerical Weather Prediction Model Precipitation Forecasts for Short-Term Streamflow Forecasting Purpose.” Hydrology and Earth System Sciences 17, no. 5 (May 21, 2013): 1913–31. https://doi.org/10.5194/hess-17-1913-2013.

Thompson, S. A. Hydrology for Water Management. 1st ed. London: CRC Press, 2017.

Toth, E, A Brath, and A Montanari. “Comparison of Short-Term Rainfall Prediction Models for Real-Time Flood Forecasting.” Journal of Hydrology 239, no. 1–4 (2000): 132–47.

Turpie, Jane, Timm Kroeger, Raffaele De Risi, Francesco de Paola, Gwyneth Letley, Katherine Forsythe, and Liz Day. “Promoting Green Urban Development in Africa : Enhancing the Relationship between Urbanization ,.” The World Bank, 2017.

UNISDR. “The Human Cost of Weather Related Disasters 1995-2015.,” 2015.

Vetrimurugan, E., M.P. Jonathan, V.C. Shruti, and B.K. Rawlins. “A View on South Africa’s KwaZulu-Natal Coast: Stressors and Coastal Management.” In Coastal Management, 121–39. Elsevier, 2019. https://doi.org/10.1016/B978-0-12-810473-6.00009-1.

Weather-Atlas. “Weather Atlas Monthly Weather Forecast and Climate Durban, South Africa,” 2020. https://www.weather-atlas.com/en/south-africa/durban-climate.

Xie, Jiaqiang, Hao Chen, Zhenliang Liao, Xianyong Gu, Dajian Zhu, and Jin Zhang. “An Integrated Assessment of Urban Flooding Mitigation Strategies for Robust Decision Making.” Environmental Modelling & Software 95 (2017): 143–55.

Yevjevich, Vujica. “Classification and Description of Flood Mitigation Measures.” In Coping with Floods, 573–84. Springer, 1994.

ABOUT AUTHOR(S)

Caroline Olanrewaju, PhD, is a disaster and risk management scholar whose work focuses on strengthening community resilience, improving institutional preparedness, and advancing evidence‑based approaches to hazard mitigation. Her research integrates public management, resilience theory, and systems thinking to address the complex and evolving risks faced by vulnerable populations. She has developed analytical frameworks that support decision‑makers in planning for floods, climate‑related hazards, and other high‑impact events, with particular emphasis on equitable policy design and community‑centered interventions.

Dr Maliga Reddy is a Senior Academic and Associate Director in the Department of Public Management and Economics at the Durban University of Technology. With extensive experience in her field, Dr. Reddy plays a pivotal role in representing DUT on the various National, Provincial and Local structures both in a professional and academic capacity. She was part of the National Disaster Management Project Team that was instrumental in the development of the National Disaster Management Education and Training Framework for South Africa. Mal served on the USAID/North-West University Steering Committee responsible for the project on the Disaster Risk Reduction Knowledge Shop, creating, sharing and exchanging information and practices in Disaster Risk Reduction. She serves on the Professional Board for Disaster Management: Disaster Management Institute of Southern Africa (DMISA). Her professional achievement was her election as the President of the Disaster Management Institute of Southern Africa (2012-2014). She continues her involvement by serving on the Executive Committee/Council and Board of the Institute. Her areas of interest and research include Public Management, Leadership, Local Government Management, and Disaster Risk Management. She serves on the Editorial Board of JAMBA- Journal of Disaster Risk Studies and Reviews for various Journals, including: the Journal of Human Ecology (JHE) and Alternation: Interdisciplinary Journal for the Study of the Arts and Humanities in Southern Africa.

Oludolapo Akanni Olanrewaju is currently a Full Professor, Head of the Department of Industrial Engineering, and the Director of System Science at the Durban University of Technology, South Africa. He earned his BSc in Electrical Electronics Engineering and MSc in Industrial Engineering from the University of Ibadan, Nigeria and his Doctorate in Industrial Engineering from the Tshwane University of Technology, South Africa. His research interests are not limited to energy/greenhouse gas analysis/management, life cycle assessment, or the application of intelligence techniques. His contribution is on the various optimization strategies that aim to achieve sustainable development in the energy sector. He has developed integrated models to achieve this, which require steps to ensure that society is able to transition towards sustainability and the prevention of global warming. Such contributions assist to realize the United Nations Sustainable Development Goals (SDGs) on affordable and clean energy (SDG7) and climate action (SDG13), which are fundamental to facilitating such steps. Each of the models that make up the integrated model has the advantage of offsetting the bias of the others, making them compatible with one another. He has papers published in peer-reviewed journals, conferences and book chapters and is currently editing a book. He is a Guest Editor for Special Issues in Atmosphere and Sustainability and an Editorial Board Member of Renewable Energies (SAGE). He collaborates with some universities under BRICS, African Institutions and some North American Universities. His future interests include (1) engaging in solution development and testing: advancing development of emissions detection, (2) engaging in measurement informed inventory: applying stochastic modelling on a mechanistic air emissions simulator, and (3) engaging in pipeline emissions and safety: accelerating pipeline leak detection quantification solutions through transparent and rigorous scientific validation. He is a C2 NRF Rated Researcher.

TO CITE ARTICLE

Olanrewaju, Caroline C., Maliga Reddy, and Oludolapo A. Olanrewaju. “Flood Mitigation in Ethekwini Metropolitan Area – Empirical Evidence using Artificial Neural Network,” E-Journal of Humanities, Arts and Social Sciences 6, no. 15 (2025): 4520 – 4536, https://doi.org/10.38159/ehass.202561522.