Citation :

Abdikafi Elmi Abdishakur, Abdullahi Mohamed Abdi, "Evaluating Machine Learning Models for Flood Forecasting in Baladweyn City, Somalia," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 8, pp. 413-421, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I8P127

Abstract

Baladweyne City is a city in the central part of Somalia that has experienced disruptions due to flooding over the years. The flooding has always affected the transport and general operations in the Shabelle River floodplain. The main aim of the research is to evaluate the performance of the Support Vector Regression approach in flood forecasting in Baladweyne, with specific emphasis on the dependence of the kernel, the possibility of overfitting and underfitting, and the overall improvement in the accuracy of the results over the benchmark models. The Support Vector Regression approach was implemented using the LIBSVM toolbox with the scaling and normalization of the data and the overall configuration of the input for the models. The results of the Support Vector Regression approach were compared with the results of the transfer function, trend, and naïve persistence models. The results of the research showed that the accuracy of the results of the benchmark models decreased significantly with the increase in the forecast period. For example, the best RMSE of the benchmark models for the first lead time was 170, while the RMSE for the sixth lead time was 1010, showing a deterioration of 494% in the accuracy of the results. On the other hand, the Support Vector Regression approach showed significant improvements in the accuracy of the results over the results of the benchmark models. For example, the Support Vector Regression approach showed improvements of 2.9% in the accuracy of the results for the first lead time and improvements of up to 17.3% for the longer lead times. The results of the Support Vector Regression approach showed that the linear kernels were more robust in the conditions where the rainfall for the future period is not available, while the RBF kernels showed better accuracy when the rainfall for the future period is available. The results of the Support Vector Regression approach showed that the approach is capable of capturing the time of the major flood peaks with minimal relative deviation, while the results of the rainfall-response experiment showed a scaling from low rainfall of 0-4 mm to high rainfall of 50-100 mm.

Keywords

Baladweyne, Flood early warning, Support Vector Regression, Shabelle river, Kernel sensitivity.

References

[1] Vijendra Kumar et al., “The State of the Art in Deep Learning Applications, Challenges, and Future Prospects: A Comprehensive Review of Flood Forecasting and Management,” Sustainability, vol. 15, no. 13, pp. 1-33, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Amir Mosavi, Pinar Ozturk, and Kwok-wing Chau, “Flood Prediction using Machine Learning Models: Literature Review,” Water, vol. 10, no. 11, pp. 1-40, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Long Ho, and Peter Goethals, “Machine Learning Applications in River Research: Trends, Opportunities and Challenge,” Methods in Ecology and Evolution, vol. 13, no. 11, pp. 2603-2621, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Zaher Mundher Yaseen, “A New Benchmark on Machine Learning Methodologies for Hydrological Processes Modelling: A Comprehensive Review for Limitations and Future Research Directions,” Knowledge-based Engineering and Sciences, vol. 4, no. 3, pp. 65-103, 2023.
[Google Scholar]

[5] Amir Zalnezhad et al., “Comparing Performance of ANN and SVM Methods for Regional Flood Frequency Analysis in South-East Australia,” Water, vol. 14, no. 20, pp. 1-18, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Zhibin He et al., “A Comparative Study of Artificial Neural Network, Adaptive Neuro Fuzzy Inference System and Support Vector Machine for Forecasting River Flow in the Semiarid Mountain Region,” Journal of Hydrology, vol. 509, pp. 379-386, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Shahaboddin Shamshirband et al., “Comparative Analysis of Hybrid Models of Firefly Optimization Algorithm with Support Vector Machines and Multilayer Perceptron for Predicting Soil Temperature at Different Depths,” Engineering Applications of Computational Fluid Mechanics, vol. 14, no. 1, pp. 939-953, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Khameis Mohamed Al Abdouli et al., “Real-Time Flood Forecasting in Amo Chhu using Machine Learning Model and Internet of Things and Internet of Things,” Cogent Engineering, vol. 11, no. 1, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Francesco Cappelli et al., “Feature Importance Measures for Flood Forecasting System Design,” Hydrological Sciences Journal, vol. 69, no. 4, pp. 438-455, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Mahmoud F. Maghrebi, and Sajjad M. Vatanchi, “Comparison of Different Machine Learning Methods in River Streamflow Estimation using Isovel Contours and Hydraulic Variables,” International Journal of River Basin Management, vol. 24, no. 3, pp. 457-474, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Sackdavong Mangkhaseum, “Flood Susceptibility Mapping Leveraging Open-Source Remote-Sensing Data and Machine Learning Approaches in Nam Ngum River Basin (NNRB), Lao PDR,” Geomatics, Natural Hazards and Risk, vol. 15, no. 1, pp. 1-26, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Mohanned S. Al-Sheriadeh, and Mohammad A. Daqdouq, “Robustness of Machine Learning Algorithms to Generate Flood Susceptibility Maps for Watersheds in Jordan,” Geomatics, Natural Hazards and Risk, vol. 15, no. 1, pp. 1-33, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Bernard Ladouche, Jean-Christophe Marechal, and Nathalie Dorfliger, “Semi-Distributed Lumped Model of a Karst System Under Active Management,” Journal of Hydrology, vol. 509, pp. 215-230, 2014.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Jakub Langhammer, “Flood Simulations using a Sensor Network and Support Vector Machine Model,” Water, vol. 15, no. 11, pp. 1-27, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Mohammad Roohi et al., “A Hybrid Approach for Enhanced Flood Prediction and Assessment: Leveraging Physical Models, Deep Learning and Satellite Remote Sensing,” Big Earth Data, vol. 9, no. 3, pp. 439-472, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Shuchi Mishra et al., “Dynamic Flood Risk Prediction in Houston: A Multi- Model Machine Learning Approach,” Geocarto International, vol. 39, no. 1, pp. 1-32, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Yogesh Bhattarai et al., “Leveraging Machine Learning and Open-Source Spatial Datasets to Enhance Flood Susceptibility Mapping in Transboundary River Basin,” International Journal of Digital Earth, vol. 17, no. 1, pp. 1-25, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Durlav Sonowal et al., “Streamflow Forecast Model using ANN,” Journal of Applied Water Engineering and Research, vol. 12, no. 3, pp. 311-321, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Juliana G. Rabelo et al., “Karstification and Fluid Flow in Carbonate Units Controlled by Propagation and Linkage of Mesoscale Fractures, Jandaíra Formation, Brazil,” Geomorphology, vol. 357, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Mohammad Mahdi Rajabi, Behzad Ataie-Ashtiani, and Craig T. Simmons, “Model-Data Interaction in Groundwater Studies: Review of Methods, Applications and Future Directions,” Journal of Hydrology, vol. 567, pp. 457-477, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Vilde Dimmen et al., “Quantifying Structural Controls on Fluid Flow: Insights from Carbonate- Hosted Fault Damage Zones on the Maltese Islands,” Journal of Structural Geology, vol. 101, pp. 43-57, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Beibei Shen et al., “Spatial Variations and Controls on the Hydrochemistry of Surface Waters Across the Ili-Balkhash Basin, Arid Central Asia,” Journal of Hydrology, vol. 600, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Daniel F. Menezes et al., “Subsidence Rings and Fracture Pattern Around Dolines in Carbonate Platforms – Implications for Evolution and Petrophysical Properties of Collapse Structures,” Marine and Petroleum Geology, vol. 113, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Amin Gharehbaghi, “Explicit and Implicit Forms of Differential Quadrature Method for Advection – Diffusion Equation with Variable Coefficients in Semi-Infinite Domain,” Journal of Hydrology, vol. 541, pp. 935-940, 2016.
[CrossRef] [Google Scholar] [Publisher Link]