Abstract
In this paper, kernel principle component analysis (KPCA) is employed to extract the features of multiple precipitation factors. The extracted principle components are considered as the characteristic vector of support vector machine (SVM) to build the SVM precipitation forecast model. We calculate the SVM parameters using particle swarm optimization (PSO) algorithm, and build the cooperative model of KPCA and the SVM with PSO to predict the precipitation in Guangxi province. The simulation results show that the prediction outcome, resulting from the combination of KPCA and the SVM with PSO, is consistent with the actual precipitation. Comparisons with other models also demonstrate that our model has advantages in fitting and generalizing in comparison other models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Toda, Y., Abe, F.: Prediction of precipitation sequences within grains in 18Cr-8Ni austenitic steel by using system free energy method. ISIJ Int. 49(3), 439–445 (2009)
Ouyang, Q., Wenxi, L., Dong, H., et al.: Study on precipitation prediction based on SVM regression analysis. Water-Saving Irrig. 9, 38–41 (2014)
Ni, Y.: Study on Donggang precipitation prediction model based on SVM. Water Conservancy 2, 133–134 (2014)
Teng, W., Shanxian, Y., Bo, H., et al.: Application research of SVM regression in flood and drought prediction in flood season. J. Zhejiang Univ. (Science) 35(3), 343–347 (2008)
Yang, L., Xiwen, L., Liu, P., et al.: Time sequence analysis and the application of Monte Carlo in precipitation prediction. Environ. Sci. Technol. 34(5), 108–112 (2011)
Sun, M., Kong, X., Geng, W., et al.: Time sequence analysis on shandong monthly precipitation based on ARIMA model. J. Ludong Univ. (Natural Science) 29(3), 244–249 (2013)
Zhou, Z., Xie, B.: Application of BP neural net in Zhenzhou drought prediction and strategies of disaster reduction and prevention. Chin. Rural Water Conservancy Hydroelectricity 12, 97 (2011)
Tao, W., Hui, Q., Li, P., et al.: Application of weighting Markov chain in precipitation prediction of Yinchuan area. South-to-North Water Divers. Water Sci. Technol. 8(1), 78–81 (2010)
Liu, D., Fu, W.: Prediction test of least squares SVM in precipitation of flood season. In: The 33rd Annual Meeting of Chinese Meteorological Society S1 Supervision, Analysis and Prediction of Disaster Whether. Publishing House, Xi’an, pp. 929–934 (2016)
Gao, X.: Kernel feature extraction method and its application research. Nanjing University of Aeronautics and Astronautics (2010)
Luo, F., Jiansheng, W., Jin, L.: Integrated precipitation prediction model based on least squares SVM. J. Tropic. Meteorol. 27(3), 577–584 (2011)
Luo, F.: Optimize RBF neural net precipitation prediction model based on LLE. Comput. Digit. Eng. 41(5), 749–752 (2013)
He, X., Wang, Y., Wen, B.: Quantitative research on special engineering costs based on PSO SVM. Electricity Grid Clean Energy 31(12), 27–30 (2015)
Li, T., Zeng, X.: Simulation of flow and sediment of yanhe basin based on PSO SVM. J. Basis Sci. Eng. 23(7), 79–87 (2015)
Meng, J.: Study on long-term precipitation prediction model for arid region based on PSO-LSSVM. J. Yangtze River Sci. Res. Inst. 10, 36–40 (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Luo, F., Wang, G., Zhang, Y. (2019). Precipitation Prediction Based on KPCA Support Vector Machine Optimization. In: Liu, S., Yang, G. (eds) Advanced Hybrid Information Processing. ADHIP 2018. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 279. Springer, Cham. https://doi.org/10.1007/978-3-030-19086-6_42
Download citation
DOI: https://doi.org/10.1007/978-3-030-19086-6_42
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19085-9
Online ISBN: 978-3-030-19086-6
eBook Packages: Computer ScienceComputer Science (R0)