A Particle Swarm Optimization-Neural Network Prediction Model for Typhoon Intensity Based on Isometric Mapping Algorithm

Author

Jin, Long ; Huang, Ying

Author_Institution

Guangxi Climate Center, Nanning, China

fYear

2012

fDate

23-26 June 2012

Firstpage

857

Lastpage

861

Abstract

In terms of the Particle Swarm Optimization-Neural Network (PSO-NN), a new prediction model has been developed using the stepwise regression method combined with the feature extraction technique of Isometric Mapping (ISOMAP) algorithm to treat the Climatology and Persistence (CLIPER) predictors. The model is validated with forecasts of ten years of typhoon intensity formed and numbered in the Western Pacific Ocean over May-October, 2001-2010. Using identical sample cases, predictions of the PSO-NN model based on ISOMAP algorithm are compared with the CLIPER model widely used in China and overseas, and it has been proven experimentally that the former is more accurate.

Keywords

climatology; feature extraction; geometry; geophysics computing; neural nets; particle swarm optimisation; prediction theory; regression analysis; storms; CLIPER model; CLIPER predictor; China; ISOMAP algorithm; PSO-NN model; climatology and persistence predictor; feature extraction; isometric mapping algorithm; particle swarm optimization-neural network prediction model; stepwise regression method; typhoon intensity; western Pacific ocean; Analytical models; Artificial neural networks; Computational modeling; Data models; Prediction algorithms; Predictive models; Typhoons; Climatology and Persistence method; Isometric Mapping algorithm; Particle Swarm Optimization-Neural Network; typhoon intensity;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Sciences and Optimization (CSO), 2012 Fifth International Joint Conference on

Conference_Location

Harbin

Print_ISBN

978-1-4673-1365-0

Type

conf

DOI

10.1109/CSO.2012.193

Filename

6274857