An innovated integrated model using Singular Spectrum Analysis and Support Vector Regression optimized by intelligent algorithm for rainfall forecasting

Journal: Journal of Autonomous Intelligence DOI: 10.32629/jai.v2i1.37

Weide Li, Juan Zhang

Lanzhou University

Abstract

Rainfall forecasting is becoming more and more significant and precipitation anomalies would lead to droughts and floods disasters. However, because of the complexity and non-stationary of rainfall data, it is difficult to forecast. In this paper, a novel hybrid model to forecast rainfall is developed by incorporating singular spectrum analysis (SSA) and dragonfly algorithm (DA) into support vector regression (SVR) method. Firstly, SSA is used for extracting the trend components of the hydrological data. Then, SVR is utilized to deal with the volatility and irregularity of the precipitation series. Finally, the parameter of SVR is optimized by DA. The proposed SSA-DA-SVR method is used to forecast the monthly precipitation for Songbai, Panshui, Lanma and Jiulongchi stations. To validate the efficiency of the method, four compared models, DA-SVR, SSA-GWO-SVR, SSA-PSO-SVR, SSA-CS-SVR are established. The result shows the proposed method has the best performance among all five models, and its prediction has high precision and accuracy.

Keywords

Prediction ; Precipitation ; Singular Spectrum Analysis ; Support Vector Regression ; Intelligent Algorithm

References

1. J. Wu. A Novel Artificial Neural Network Ensemble Model based on K--Nearest Neighbor Nonparametric Estimation of Regression Function and Its Application for Rainfall Forecasting[C]// International Joint Conference on Computation Sciences and Optimization. IEEE, 2009, 2, 44-48.

2. CM. Tseng, CD. Jan, JS. Wang and CM. Wang. Application of artificial neural network in typhoon surge forecasting. Ocean Engineering. 2007, 34, 1757-1768.

3. P. Narayanna, A. Basistha, S. Sarkar, S. Kamna. Trend analysis and ARIMA modelling of pre-monsoon rainfall data for western India. Comptes Rendus Geoscience. 2013, 345, 22-27.

4. S. Chattopadhyay, G. Chattopadhyay. Univariate modelling of summer-monsoon rainfall time series: Comparison between ARIMA and ARNN. Comptes Rendus Geoscience. 2010, 342, 100-107.

5. S. Afshin, H. Fahmi, A. Alizadeh, H. Sedghi, F. Kaveh. Long term rainfall forecasting by integrated artificial neural network-fuzzy logic-wavelet model in Karoon basin. Scientific Research and Essays. 2011, 6, 1200-1208.

6. C. Jareanpon, W. Pensuwon, RJ. Frank and N. Davey. An Adaptive RBF network optimised using a genetic algorithm applied to rainfall forecasting. International Symposion on Communications and Information Technologies. IEEE, 2004, 2, 1005-1010.

7. M. Anwer, K. Khan, S. Banik, FH. Chanchary. Forecasting Bangladesh Monsoon Rainfall Neural Network and Genetic Algorithm Approaches. World Journal of Microbology & Biotechnology. 2009, 2, 1-18.

8. M. Nasseri, K. Asghari, MJ. Abedini. Optimized scenario for rainfall forecasting using genetic algorithm coupled with artificial neural network. Expert Systems with Applications. 2008, 35, 1415-1421.

9. Riccardo Taormina, Kwok-Wing Chau. Data-driven input variable selection for rainfall-runoff modeling using binary-coded particle swarm optimization and Extreme Learning Machines. Journal of Hydrology. 2015, 529, 1617-1632.

10. CC. Young, WC. Liu, MC. Wu. A physically based and machine learning hybrid approach for accurate rainfall-runoff modeling during extreme typhoon events. Applied Soft Computing. 2017, 53, 205-216.

11. SM. Hosseini , N. Mahjouri. Integrating Support Vector Regression and a geomorphologic Artificial Neural Network for daily rainfall-runoff modeling. Applied Soft Computing. 2016, 38, 329-345.

12. MC. Wu , GF. Lin, HY. Lin. Improving the forecasts of extreme streamflow by support vector regression with the data extracted by self-organizing map. Hydrological Processes. 2012, 28, 386-397.

13. WC. Wang, KW. Chau, L. Qiu, YB. Chen. Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition. Environmental Research. 2015, 139, 46-54.

14. KW. Chau, CL. Wu. A hybrid model coupled with singular spectrum analysis for daily rainfall prediction. Journal Hydroinformatics. 2010, 12, 458-473.

15. KS. Kasiviswanathan , R. Cibin , KP. Sudheer , I. Chaubey. Constructing prediction interval for artificial neural network rainfall runoff models based on ensemble simulations. Journal of Hydrology. 2013, 499, 275–288.

16. Nasseri M, Asghari K, Abedini M. Optimized scenario for rainfall forecasting model using genetic algorithm coupled with artificial neural network. Expert Systems with Applications. 2008, 35, 1415-1421.

17. J. Wu, J. Long, M. Liu. Evolving RBF neural networks for rainfall prediction using hybrid particle swarm optimization and genetic algorithm. Neurocomputing. 2015, 148, 136-142.

18. Mingfei Niu, Shaolong Sun, Jing Wu, Lean, Jianzhou Wang. An innovative integrated model using the singular spectrum analysis and nonlinear multi-layer perception network optimized by hybrid intelligent algorithm for short-term load forecasting. Applied Mathematical Modelling. 2016, 40, 4079-4093.

19. Y. Wang, J. Wang, X. Wei. A hybrid wind speed forecasting model based on phase space reconstruction theory and Markov model : A case study of wind farms in northwest China. Energy. 2013, 91, 556-572.

20. Y. Xu, W. Yang, J. Wang. Air quality early-warning system for cities in China. Atmospheric Environment. 2017, 148, 239-257.

21. M. Abdollahzade , et al. A new hybrid enhanced local linear neruo-fuzzy model based on the optimized singular spectrum analysis nonlinear and chaotic time series forecasting. Information Sciences. 2015, 295, 107-125.

22. N. Golyandina, V. Nekrutkin, A. Zhigljavsky, Analysis of Time Series Structure: SSA and Related Techniques, CRC Press, 2001.
23. S. Mirjalili. Dragonfly algorithm: a new meta-heuristic
optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Computing & Applications. 2016, 27, 1053-1073.

24. V. Vapnik , S. Golowich , A. Smola . Support vector method for function approximation, regression estimation, and signal processing. In:Mozer MC , Jordan MI, Petsche T, editors. Neural information processing systems. 1997, 9, 281-287.

25. D. Basak , DC. Patranabis , S. Pal . Support vector regression. Neural Information Processing- Letters Reviews. 2007, 11, 203-224.

26. WC. Hong, YC. Dong, WY. Zhang, LY. Chen, BK. Panigrahi. Cyclic electric load forecasting by seasonal SVR with chaotic genetic algorithm . Electr Power Energy Syst. 2013, 44, 604-614.

27. AJ. Smola, B. Scholkopf. A tutorial on support vector regression. Statist. Comput. 2004, 14, 199-222.

28. WD. Li, DM. Kong, JR. Wu. A novel hybrid model based on extreme learning machine, k-nearest neighbor regression and wavelet denoising applied to short-term electric load forecasting. Energies. 2017; 10, 694; doi: 10.3390/en10050694.

29. K. Dragomiretskiy, D. Zosso. Variational Mode Decomposition. Transaction on signal processing. 2014, 62, 531-544.

30. MA. Colominas, G. Schlotthauer, ME. Torres. Improved complete ensemble EMD: A suitable tool for biomedical signal processing. Biomedical Signal Processing and control. 2014, 14, 19-29.

Copyright © 2019 Weide Li, Juan Zhang

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License