%0 Journal Article %T Hourly Flood Forecasting Using Hybrid Wavelet-SVM %J Journal of Soft Computing in Civil Engineering %I Pouyan Press %Z 2588-2872 %A Shada, Baheerah %A Chithra, N.R. %A Thampi, Santosh G. %D 2022 %\ 04/01/2022 %V 6 %N 2 %P 1-20 %! Hourly Flood Forecasting Using Hybrid Wavelet-SVM %K Artificial Neural Networks %K Denoising %K Peak Discharge %K performance rating criteria %K Support Vector Machine %R 10.22115/scce.2022.317761.1383 %X The floods of 2018 and 2019 have underlined the urgent need for development and implementation of efficient and robust flood forecasting models for the major rivers in the State of Kerala, India. In this paper, the development and application of two hourly flood forecasting models are presented – one using Support Vector Machine (SVM) and the other based on hybrid wavelet-support vector machine (WSVM). The study was performed on the Achankovil River in Kerala. Wavelet technique was used to denoise the input signal (rainfall and water level) and the effective components of the input signal obtained after denoising were input to the SVM/ WSVM models for forecasting. These models' performance was assessed using standard performance rating criteria. Further, the performance of these models was compared with that of a flood forecasting model based on hybrid wavelet-artificial neural network (WANN) developed for this river in a previous study. Results of this study demonstrated the ability of the WSVM model to predict floods reasonably well. It was observed that the WSVM model performed better when compared to the WANN model. The WSVM model was able to accurately estimate peak discharge magnitude and time to peak, both of which are critical inputs in many water resource design and management applications. %U https://www.jsoftcivil.com/article_147504_37fd136484200abae56727186fab006b.pdf