Storm surge prediction is of great importance to disaster prevention and mitigation. In this study, four optimization algorithms including genetic algorithm (GA), particle swarm optimization (PSO), beetle antenna search (BAS), and beetle swarm optimization (BSO) are used to optimize the back propagation neural network (BPNN), and four optimized BPNNs for storm surge prediction are proposed and applied to Yulin station and Xiuying station at Hainan, China. The optimal model parameter combination is determined by trail-and-error method for the best prediction performance. Comparisons with the single BPNN indicate that storm surge can be efficiently predicted using the optimized BPNNs. BPNN optimized by BSO has the minimum prediction error, and BPNN optimized by BAS has the minimum time cost to reduce unit prediction error.
Study on the application of BP neural network optimized based on various optimization algorithms in storm surge prediction
2022-08-01
14 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Extreme Storm Surge Prediction Using Hydrodynamic Modelling and Artificial Neural Networks
BASE | 2014
|Extreme Storm Surge Prediction Using Hydrodynamic Modelling and Artificial Neural Networks
HENRY – Bundesanstalt für Wasserbau (BAW) | 2014
|Development of Real Time Storm Surge Forecasting Using Artificial Neural Network
HENRY – Bundesanstalt für Wasserbau (BAW) | 2014
|HENRY – Bundesanstalt für Wasserbau (BAW) | 2012
|Hurricane Gilbert Storm Surge DATA
HENRY – Bundesanstalt für Wasserbau (BAW) | 1990
|