Prediction Analysis of Floods Using Machine Learning Algorithms (NARX & SVM)

  • Nadia Zehra Department of Computer Sciences, Allama Iqbal Open University, Islamabad, Pakistan
Keywords: flood, prediction, time series, NARX, SVM


The changing patterns and behaviors of river water levels that may lead to flooding are an interesting and practical research area. They are configured to mitigate economic and societal implications brought about by floods. Non-linear (NARX) and Support Vector Machine (SVM) are machine learning algorithms suitable for predicting changes in levels of river water, thus detection of flooding possibilities. The two algorithms employ similar hydrological and flood resource variables such as precipitation amount, river inflow, peak gust, seasonal flow, flood frequency, and other relevant flood prediction variables. In the process of predicting floods, the water level is the most important hydrological research aspect. Prediction using machine-learning algorithms is effective due to its ability to utilize data from various sources and classify and regress it into flood and non-flood classes. This paper gives insight into mechanism of the two algorithm in perspective of flood estimation.


G. Corani and G. Guariso, “Coupling fuzzy modeling and neural networks for river flood prediction,” IEEE Trans. on Systems Man and Cybernetics, vol.35, no.3, pp.382-390, Aug.2005.

A. Luchetta and S. Manetti, “A real time hydrological forecasting system using a fuzzy clustering approach,” Computers & Geosciences, vol.29, no.9, pp.1111-1117, Nov.2003.

Todini, E. (2004). Role and treatment of uncertainty in real‐time flood forecasting. Hydrological Processes, 18(14), 2743-2746.

Tienfuan Kerh and C.S. Lee, “Neural networks forecasting of flood discharge at an unmeasured station using river upstream information,” Adv. in Eng. Software, vol.37, no.8, pp.533-543, Aug.2006.

Antony, T., Raju, C. S., Mathew, N., & Moorthy, K. K. (2015). Flood Extent Analysis Over the Major River Basins in the Indian Subcontinent Using Satellite Microwave Radiometric Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(9), 4373-4378.

Iqbal, N., Hossain, F., Lee, H., & Akhter, G. (2016). Satellite gravimetric estimation of groundwater storage variations over Indus Basin in Pakistan. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(8), 3524-3534.

Khan, F., Memon, S., Jokhio, I. A., & Jokhio, S. H. (2015, November). Wireless sensor network based flood/drought forecasting system. In 2015 IEEE SENSORS (pp. 1-4). IEEE.

D.P. Lettenmaier and E.F. Wood, 1993, Hydrological Forecasting, Chapter 26 in Handbook of Hydrology. (D. Maidment, ed.), McGraw-Hill. D.P.

Adeli, H. (2001). Neural networks in civil engineering: 1989–2000. Computer‐Aided Civil and Infrastructure Engineering, 16(2), 126-142.

Benoudjit, A., & Guida, R. (2019). A Novel Fully Automated Mapping of the Flood Extent on SAR Images Using a Supervised Classifier. Remote Sensing, 11(7), 779.

Zhao, G., Pang, B., Xu, Z., Peng, D., & Xu, L. (2019). Assessment of urban flood susceptibility using semi-supervised machine learning model. Science of The Total Environment, 659, 940-949.

Bauer, B., & Kohler, M. (2019). On deep learning as a remedy for the curse of dimensionality in nonparametric regression. The Annals of Statistics, 47(4), 2261-2285.

Engle, R. F., D. F. Hendry, and J. F. Richard. 1983. Exogeneity. Econometrica 51:277-304

Ruslan, F. A., Samad, A. M., Zain, Z. M., & Adnan, R. (2013, August). Flood prediction using NARX neural network and EKF prediction technique: A comparative study. In 2013 IEEE 3rd International Conference on System Engineering and Technology (pp. 203-208). IEEE.

H. M. Noor, D. Ndzi, G. Yang and N. Z. M. Safar, "Rainfall-based river flow prediction using NARX in Malaysia," 2017 IEEE 13th International Colloquium on Signal Processing & its Applications (CSPA), Batu Ferringhi, 2017, pp. 67-72.

R. Adnan, A. M. Samad, Z. M. Zain and F. A. Ruslan, "5 hours flood prediction modeling using improved NNARX structure: case study Kuala Lumpur," 2014 IEEE 4th International Conference on System Engineering and Technology (ICSET), Bandung, 2014, pp. 1-5.

Q. A. Lukman, F. A. Ruslan and R. Adnan, "5 Hours ahead of time flood water level prediction modelling using NNARX technique: Case study terengganu," 2016 7th IEEE Control and System Graduate Research Colloquium (ICSGRC), Shah Alam, 2016, pp. 104-108.

F. A. Ruslan, A. M. Samad, Z. M. Zain and R. Adnan, "Flood prediction using NARX neural network and EKF prediction technique: A comparative study," 2013 IEEE 3rd International Conference on System Engineering and Technology, Shah Alam, 2013, pp. 203-208.

F. A. Ruslan, A. M. Samad, Z. M. Zain and R. Adnan, "Flood water level modeling and prediction using NARX neural network: Case study at Kelang river," 2014 IEEE 10th International Colloquium on Signal Processing and its Applications, Kuala Lumpur, 2014, pp. 204-207.

V. Vapnik, “An Overview of Statistical Learning Theory,” IEEE Trans. on Neural Networks, Vol.10, No.5, pp.988-999, 1999.

S. Gunn, “Support vector machines for classification and regression,” ISIS Technical Report ISIS-ı-eb, Image Speech & Intelligent Systems Research Group, University of Southapton, May 1998.

Liong, S. Y., & Sivapragasam, C. (2002). Flood stage forecasting with support vector machines 1. JAWRA Journal of the American Water Resources Association, 38(1), 173-186.

N. Theera-Umpon, S. Auephanwiriyakul, S. Suteepohnwiroj, J. Pahasha and K. Wantanajittikul, "River basin flood prediction using support vector machines," 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, 2008, pp. 3039-3043.

Han, D., Chan, L., & Zhu, N. (2007). Flood forecasting using support vector machines. Journal of hydroinformatics, 9(4), 267-276.

Yu, P. S., Chen, S. T., & Chang, I. F. (2006). Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 328(3-4), 704-716.

Ali, M., Qamar, A. M., & Ali, B. (2013). Data analysis, discharge classifications, and predictions of hydrological parameters for the management of Rawal Dam in Pakistan. In 2013 12th International Conference on Machine Learning and Applications.1, pp. 382-385. IEEE.