| Summary: | 碩士 === 逢甲大學 === 土木及水利工程所 === 93 === Artificial intelligence has proven to be an efficient way for hydrological modeling and widely used for flood forecasting. Genetic programming is new science and technology for the artificial intelligence in recent years. In this study, we use genetic programming to model a Keelung river routing model. When training genetic programming, we use the idea of survival of the fittest to get better parse tree by reproduction, crossover and mutation. The Back-Propagation Network is the second method. It models river routing model very popularly. Because of improving the time-consuming definition process of membership function which usually concluded by trial-and-error approach, this study designated the membership function by artificial neural network (ANN) with either supervised or and unsupervised learning procedure.The third method is adaptive network based fuzzy inference system which combine with atrificial neural network and fuzzy theory.
In this study, we use genetic programming, Back-Propagation Network and adaptive network based fuzzy inference system modeling river routing model. To further investigate the model’s applicability, the Keelung River is used as case study. With the results of this study, the genetic programming has better perform in discharge simulation.
|
|---|
