Climate change has had worst and extreme impacts all over the world. Due to rise in global temperature some region faces drought and then a sudden bout of excessive rainfall. Rainfall in excess causes one of the most destructive and dangerous natural hazard called flooding that causes serious damage to life and property on earth every year. There are several complexities in nature and pattern of floods which makes flooding an important and challenging task for the researcher. To solve this problem, there are three Artificial Neural Networks (ANNs) techniques namely Support Vector Machine (SVM), Back Propagation Neural Network (BPNN) and Radial Basis Function Network (RBFN). These techniques are capable of modelling nonlinear and complex systems. The capability of these techniques is presented in this paper. In this research, to measure the performance of models, three performance criteria, including a coefficient of determination (R2), mean square error and root mean square error are utilized. The result shows that the SVM model performs best among the three models and can be accepted as a suitable and appropriate method to predict flood.
CITATION STYLE
Sahoo, A., Singh, U. K., Kumar, M. H., & Samantaray, S. (2021). Estimation of Flood in a River Basin Through Neural Networks: A Case Study. In Lecture Notes in Networks and Systems (Vol. 134, pp. 755–763). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-5397-4_77
Mendeley helps you to discover research relevant for your work.