MUET logo

A Lightweight SVM-Based Framework for Smart Urban Flood Prediction and Response

Authors

  • Muhammad Yasir Zaheen

    Department of Computer Engineering, Sir Syed University of Engineering & Technology, Pakistan
    Author

  • Muhammad Aamir

    Department of Telecommunication Engineering, Sir Syed University of Engineering & Technology, Pakistan
    Author

  • Abdul Moid Khan

    Department of Electronic Engineering, Sir Syed University of Engineering & Technology, Pakistan
    Author

  • Dure Jabeen

    Faculty of Engineering, Sciences and Technology, Iqra University, Pakistan
    Author

  • Ali Akbar Siddique

    Faculty of Engineering, Sciences and Technology, Iqra University, Pakistan
    Author

DOI:

https://doi.org/10.22581/0710

Keywords:

Urban Flood Forecasting, Support Vector Machine (SVM) , Lightweight ML, IoT and Edge Computing, Real-Time Alerting, Smart Cities

Abstract

Urban flooding poses significant risks to human life, urban systems, and the economies of affected communities. Recent flood-prediction studies increasingly employ deep learning, hybrid modelling, and IoT-based systems; however, their computational complexity, data requirements, and deployment constraints can limit their suitability for resource-constrained edge and IoT environments. This highlights the need for lightweight frameworks that can provide accurate multiclass flood-severity classification with low computational overhead. To address this need, this study proposes UFNet, a lightweight Support Vector Machine (SVM)-based framework for six-class urban flood-severity classification. UFNet uses hydrometeorological variables, including rainfall, temperature, humidity, and water-level measurements, to classify flood conditions into six severity levels. The model was evaluated on historical hydrometeorological data and achieved high class-wise classification performance, with precision ranging from 95.18% to 98.72%, recall from 92.50% to 100%, F1-score from 94.27% to 97.56%, and ROC-AUC values of 0.98 to 1.00, thus demonstrating strong class separability. Additionally, the Critical Success Index (CSI) and Composite Performance Index (CPI) further support the reliability of the obtained classification results, with CSI values from 0.892 to 0.952 and CPI values from 0.966 to 0.985. Computational evaluation shows an inference time of 5 ms and memory consumption of 10 MB, providing low computational cost compared to the tested machine-learning models. The results indicate that the UFNet framework achieves high classification performance with low computational cost and has potential for flood-severity classification in IoT and edge-computing environments.

Downloads

References

[1] V. Kumar, H. M. Azamathulla, K. V. Sharma, D. J. Mehta, and K. T. Maharaj, “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, 2023. Art. no. 10543.

[2] A. A. Kutty, G. M. Abdella, M. Kucukvar, N. C. Onat, and M. Bulu, “A system thinking approach for harmonizing smart and sustainable city initiatives with United Nations sustainable development goals,” Sustainable Development, vol. 28, no. 5, pp. 1347–1365, 2020.

[3] R. Fatima, S. Atif, M. Fort, and M. Azmat, “Channel morphology of the indus, and the growing risk of floods related damages in the indus river basin,” Natural Hazards, vol. 121, no. 13, pp. 15789– 15821, 2025.

[4] H. Chen, J. Xiong, P. Cui, X. Chen, Y. Ge, C. Fang, B. Zhang, T. Yang, and I. Khan, “Causes and dynamic change characteristics of the 2022 devastating floods in pakistan,” Natural Hazards, vol. 120, no. 11, pp. 9691–9711, 2024.

[5] L. Cea and P. Costabile, “Flood risk in urban areas: Modelling, management and adaptation to climate change. A review,” Hydrology, vol. 9, no. 3, 2022. Art. no. 50.

[6] G. Dharmarathne, A. O. Waduge, M. Bogahawaththa, U. Rathnayake, and D. P. P. Meddage, “Adapting cities to the surge: A comprehensive review of climate-induced urban flooding,” Results in Engineering, vol. 22, 2024. Art. no. 102123.

[7] A. Bagheri and G. J. Liu, “Climate change and urban flooding: assessing remote sensing data and flood modeling techniques: a comprehensive review,” Environmental Reviews, vol. 33, pp. 1–14, 2024.

[8] P. Gholap, R. Gore, D. D. Dharmadhikari, J. Deone, S. K. Patil, S. S. Chaudhari, A. Puri, and S. Y. Waware, “Machine Learning Models for Early Warning of Coastal Flooding and Storm Surges,” Sustainable Marine Structures, vol. 7, no. 3, pp. 136–156, 2025.

[9] H. M. Lyu and Z. Y. Yin, “Flood susceptibility prediction using tree-based machine learning models in the GBA,” Sustainable Cities and Society, vol. 97, 2023. Art. no. 104744.

[10] S. Miau and W. H. Hung, “River flooding forecasting and anomaly detection based on deep learning,” IEEE Access, vol. 8, pp. 198384–198402, 2020.

[11] B. Zeng, G. Huang, and W. Chen, “Research progress and prospects of urban flooding simulation: From traditional numerical models to deep learning approaches,” Environmental Modelling & Software, vol. 183, 2025. Art. no. 106213.

[12] X. Hu, L. Chu, J. Pei, W. Liu, and J. Bian, “Model complexity of deep learning: A survey,” Knowledge and Information Systems, vol. 63, no. 10, pp. 2585–2619, 2021.

[13] N. Polson and V. Sokolov, “Deep learning: Computational aspects,” Wiley Interdisciplinary Reviews: Computational Statistics, vol. 12, no. 5, 2020. Art. no. e1500.

[14] M. S. B. M. Anik, C. An, and S. S. Li, “Evolution from the physical process-based approaches to machine learning approaches to predicting urban floods: a literature review,” Environmental Systems Research, vol. 14, no. 1, 2025. Art. no. 15.

[15] J. Langhammer, “Flood simulations using a sensor network and support vector machine model,” Water, vol. 15, no. 11, 2023. Art. no. 2004.

[16] D. M. Abdullah and A. M. Abdulazeez, “Machine learning applications based on SVM classification a review,” Qubahan Academic Journal, vol. 1, no. 2, pp. 81–90, 2021.

[17] Q. Shi and H. Zhang, “Fault diagnosis of an autonomous vehicle with an improved SVM algorithm subject to unbalanced datasets,” IEEE Transactions on Industrial Electronics, vol. 68, no. 7, pp. 6248–6256, 2020.

[18] C. Liu, W. Li, C. Hu, T. Xie, Y. Jiang, R. Li, and Y. Xu, “Research on runoff process vectorization and integration of deep learning algorithms for flood forecasting,” Journal of Environmental Management, vol. 362, 2024. Art. no. 121260.

[19] S. Wang and O. Xu, “Uncertainty forecasting model for mountain flood based on bayesian deep learning,” IEEE Access, vol. 12, pp. 47830–47841, 2024.

[20] N. H. Mamat, M. H. Othman, W. Z. Othman, and M. F. M. Noor, “Internet of things in flood warning system: An overview on the hardware implementation,” in Proceedings of the 1st International Conference on Electronics, Biomedical Engineering, and Health Informatics: ICEBEHI 2020, 8-9 October, Surabaya, Indonesia, (Singapore), pp. 269–279, Springer Singapore, Apr. 2021.

[21] A. Mansida and H. Bancong, “A Bibliometric Analysis of Trends in Rainfall-Runoff Modeling Techniques for Urban Flood Mitigation (20052024),” Results in Engineering, 2025. Art. no. 104927.

[22] T. Islam, E. B. Zeleke, M. Afroz, and A. M. Melesse, “A Systematic Review of Urban Flood Susceptibility Mapping: Remote Sensing, Machine Learning, and Other Modeling Approaches,” Remote Sensing, vol. 17, no. 3, 2025. Art. no. 524.

[23] F. Karim, M. A. Armin, D. Ahmedt-Aristizabal, L. Tychsen-Smith, and L. Petersson, “A review of hydrodynamic and machine learning approaches for flood inundation modeling,” Water, vol. 15, no. 3, 2023. Art. no. 566.

[24] S. Snikitha, G. P. Kumar, and G. S. Dwarakish, “A comprehensive review of cutting-edge flood modelling approaches for urban flood resilience enhancement,” Water Conservation Science and Engineering, vol. 10, no. 1, 2025. Art. no. 2.

[25] I. Yu, K. Park, and E. H. Lee, “Flood risk analysis by building use in urban planning for disaster risk reduction and climate change adaptation,” Sustainability, vol. 13, no. 23, 2021. Art. no. 13006.

[26] W. Zhang, Y. Liu, W. Tang, S. Chen, and W. Xie, “Rapid spatio-temporal prediction of coastal urban floods based on deep learning approaches,” Urban Climate, vol. 52, 2023. Art. no. 101716.

[27] A. Bhusal, B. Thakur, A. Kalra, R. Benjankar, and A. Shrestha, “Evaluating the effectiveness of best management practices in adapting the impacts of climate change-induced urban flooding,” Atmosphere, vol. 15, no. 3, 2024. Art. no. 281.

[28] V. Kumar, K. V. Sharma, T. Caloiero, D. J. Mehta, and K. Singh, “Comprehensive overview of flood modeling approaches: A review of recent advances,” Hydrology, vol. 10, no. 7, 2023. Art. no. 141.

[29] B. Liu, Q. Tang, G. Zhao, L. Gao, C. Shen, and B. Pan, “Physics-guided long short-term memory network for streamflow and flood simulations in the Lancang–Mekong river basin,” Water, vol. 14, no. 9, 2022. Art. no. 1429.

[30] Y. Wang, J. Liu, R. Li, X. Suo, and E. Lu, “Precipitation forecast of the Wujiang River Basin based on artificial bee colony algorithm and backpropagation neural network,” Alexandria Engineering Journal, vol. 59, no. 3, pp. 1473–1483, 2020.

Published

2026-10-01

Issue

Vol. 45 No. 4 (2026): October Issue

Section

Articles

License

Copyright (c) 2026 Mehran University Research Journal of Engineering and Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite

A Lightweight SVM-Based Framework for Smart Urban Flood Prediction and Response. (2026). Mehran University Research Journal of Engineering and Technology, 45(4), 112-124. https://doi.org/10.22581/0710

Most read articles by the same author(s)

Similar Articles

51-60 of 65

You may also start an advanced similarity search for this article.