RBF Prediction Model Based on EMD for Forecasting GPS Precipitable Water Vapor and Annual Precipitation

Abstract:

The forecast of precipitations is important in meteorology and atmospheric sciences. A new model is proposed based on empirical mode decomposition and the RBF neural network. Firstly, GPS PWV time series is broken down into series of different scales intrinsic mode function. Secondly, the phase space reconstruction is done. Thirdly, each component is predicted by RBF. Finally, the final prediction value is reconstructed. Next, the model is tested on annual precipitation sequence from 2001 to 2010 in northeast China. The result shows that predictive value is close to the actual precipitation, which can better reflect the actual precipitation change. From 2001 to 2010, the maximum deviation of the predicted values never exceeds 4%. The testing results show that the proposed model can increase precipitation forecasting accuracies not only in GPS PWV but also in annual precipitation.

• Periodical: Advanced Materials Research (Volumes 765-767)
• Pages: 2830-2834
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.765-767.2830
• Online since: September 2013
• Authors: Yan Ping Liu, Yong Wang, Zhen Wang
• Keywords: Empirical Mode Decomposition (EMD), GPS Precipitable Water Vapor, Precipitation, RBF Neural Network

References

[1] Zhou Pei-ling, Tao　Xiao-li, Fu　Zhong-qian, et al, Precipitation predicting based on improved radial basis function neural networks, Mini-micro System. 22(2001) 244-246.

[2] Fu Fei, Zhang Jian, Zhou Bao-qi, Forecasting of precipitation by RBF neural network and particle swarm optimization, 2010 International Conference on Computer Engineering and Technology Proceedings. 7(2010) 7391-7394.

DOI: 10.1109/iccet.2010.5485488

[3] Shien-Tsung Chen, Pao-Shan Yu, Bin-Wu Liu, Comparison of neural network architectures and inputs for radar rainfall adjustment for typhoon events, Journal of Hydrology. 405(2011) 150-160.

DOI: 10.1016/j.jhydrol.2011.05.017

[4] Song-shan Yang, Xiao-hua Yang, Rong Jiang, et al, New optimal weight combination model for forecasting precipitation, Mathematical Problems in Engineering. 2012, doi: 10. 1155/2012/376010.

DOI: 10.1155/2012/376010

[5] Wang Yong, Liu Lintao, Xiao Jianhua, et al, GPS Meteorology network in Wuhan region, Geomatics and Information Science of Wuhan University. 32(2007) 435-438.

[6] Norden E H, Shen Z, Long S R, et al, The empirical mode decomposition and the Hilbert Spectrum for nonlinear and non-stationary time series analysis, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences. 454(1998).

DOI: 10.1098/rspa.1998.0193

[7] Luo Fangqiong, Wu Jiansheng, Jin Long, Precipitation forecasting model based on least square support vector machine regression ensemble, Journal of Tropical Meteorology. 27(2011) 577-584.

[8] Xu Zonghuan, Zhang Rongyan, Xie Qingrong, A BP artificial neural network prediction model of spring's drought / flood in Fujian, Journal of Natural Disasters. 18(2009) 104-109.

[9] Qu Weilian, Cheng Lei, Disposal of boundary problem in EMD method applying RBF neural network, Journal of Huazhong University of Science and Technology, Urban Science Edition. 23(2006) 1-5.