Predict typhoon-induced storm surge deviation in a principal component back-propagation neural network model

To reduce typhoon-caused damages, numerical and empirical methods are often used to forecast typhoon storm surge. However, typhoon surge is a complex nonlinear process that is difficult to forecast accurately. We applied a principal component back-propagation neural network （PCBPNN） to predict the d...

Full description

Saved in:
Bibliographic Details
Published inChinese journal of oceanology and limnology Vol. 31; no. 1; pp. 219 - 226
Main Author 过仲阳 戴晓燕 栗小东 叶属峰
Format Journal Article
LanguageEnglish
Published Heidelberg SP Science Press 2013
Springer Nature B.V
Subjects
Back propagation networks
BP神经网络
case studies
China
Coastal zone management
Deviation
Earth and Environmental Science
Earth Sciences
Empirical analysis
Estuaries
Hurricanes
Marine
Mathematical models
Neural networks
Numerical methods
Oceanography
Physics
prediction
principal component analysis
Principal components analysis
Storm surges
Storms
Typhoons
主成分分析
偏差
台风暴潮
台风风暴潮
引发
模型预测
非线性过程
Yangtze River Delta
China
China, People's Rep
INW, China, People's Rep., Shanghai
typhoon
Changjiang (Yangtze) River estuary
storm surges forecasts
principal component back-propagation neural networks (PCBPNN)
Online AccessGet full text
ISSN0254-4059
2096-5508
1993-5005
2523-3521
DOI10.1007/s00343-013-2048-8

Cover

More Information
Summary:To reduce typhoon-caused damages, numerical and empirical methods are often used to forecast typhoon storm surge. However, typhoon surge is a complex nonlinear process that is difficult to forecast accurately. We applied a principal component back-propagation neural network （PCBPNN） to predict the deviation in typhoon storm surge, in which data of the typhoon, upstream flood, and historical case studies were involved. With principal component analysis, 15 input factors were reduced to five principal components, and the application of the model was improved. Observation data from Huangpu Park in Shanghai, China were used to test the feasibility of the model. The results indicate that the model is capable of predicting a 12-hour warning before a typhoon surge.
Bibliography:GUO Zhongyang , DAI Xiaoyan YE Shufeng ,LI Xiaodong , Department of Geography, Key Laboratory of Geographic Information Science, Ministry of Education, East China Normal University, Shanghai 200062, China 2 Key Laboratory of Wave Scattering and Remote Sensing Information, Fudan University, Shanghai 200433, China 3 Key Laboratory of Marine Integrated Monitoring and Applied Technologies of Harmful Algal Blooms, State Oceanic Administration, Shanghai 200090, China 4 East China Sea Center of Standard and Metrology, State Oceanic Administration, Shanghai 200080, China
To reduce typhoon-caused damages, numerical and empirical methods are often used to forecast typhoon storm surge. However, typhoon surge is a complex nonlinear process that is difficult to forecast accurately. We applied a principal component back-propagation neural network （PCBPNN） to predict the deviation in typhoon storm surge, in which data of the typhoon, upstream flood, and historical case studies were involved. With principal component analysis, 15 input factors were reduced to five principal components, and the application of the model was improved. Observation data from Huangpu Park in Shanghai, China were used to test the feasibility of the model. The results indicate that the model is capable of predicting a 12-hour warning before a typhoon surge.
typhoon; storm surges forecasts; principal component back-propagation neural networks（PCBPNN）; Changjiang （Yangtze） River estuary
37-1150/P
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0254-4059
2096-5508
1993-5005
2523-3521
DOI:10.1007/s00343-013-2048-8