碩士 / 中興大學 / 土木工程學系所 / 95 / Taiwan northern area is always attacked by typhoon frequently every year and induces the flood disasters. At present, Tamsui river territory has some unfavorable conditions including the basin low-lying and land subsidence to control the flood with storm-surge. Thus the accurate prediction of the storm-surge is an important issue for the area. However, it is quite complex for the prediction of storm-surge and use the numerical method or empirical formula to predict the phenomenon is not easily. Alternatively This paper applies the artificial networks including the supervised multilayer perception neural network and the radial basis function neural network, for the prediction of the storm-surge .
Based on the previous empirical formula of the maximum of storm-surge, it is only 0.565 to draw the correlation coefficient. This study chooses the stand atmosphere pressure variation, wind speed and wind direction parameters as the input neurons for the networks of typhoon about 22 groups and discuss the effect of each parameter on storm-surge forecast. The results agree well with the measured data of storm-surge, which all the correlation coefficient are more than 0.9.
The results of the predicted and test model show that the correlation coefficient values are larger than 0.85 in the situation of predicted model inputted the atmosphere pressure variation, wind speed, wind direction and storm-surge of last moment parameters into the time series of storm-surge. This result illustrates that time series model forecast well for the storm-surge of the time during the typhoon.
| Identifer | oai:union.ndltd.org:TW/095NCHU5015077 |
| Date | January 2007 |
| Creators | Chih-Yu You, 游智宇 |
| Contributors | Ching-Piao Tsai, 蔡清標 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 78 |
Page generated in 0.0152 seconds