Comparative performance of support vector regressions for accurate streamflow predictions

Noraini Ibrahim, Norhaiza Ahmad

Abstract


Obtaining accurate streamflow predictions can be challenging due to the inherent variabilities and complex nonlinear nature in streamflow generation processes. Support vector regression model is an effective forecasting tool to forecast streamflow as it is able to capture the nonlinearity in the data and attain the global optimum parameters in the forecasted model. However, the efficiency of SVR might be hindered by noise that typically exists in any hydrological time series data through random influences and inaccuracies in recording. Thus, this condition could compromise the quality of input data into SVR. In this study, we investigate the effectiveness of forecasting monthly streamflow data using different settings of SVR in two ways. First, we use different variations of wavelet denoising technique using different selections of wavelet decomposition levels and mother wavelets in order to preserve information and reduce distortion of the original time series. For this purpose, we measured the impact of six different wavelets on SVR namely Daubechies of type db3, db4, db5, db6 and db7 with two different levels of decomposition which are level 3 and level 4. There is more information that may contribute to better performance of the model when the decomposition level is increase. Then, the data are applied using radial basis function (RBF) by performing K-fold cross-validation to obtain the optimal parameter for kernel function in forecasting streamflow. We illustrate the methods using the monthly streamflow data observed at Segamat River in the state of Johor. The results demonstrated that SVR based wavelet denoising for 1-month lead time streamflow forecasting of type db5 with level 3 give better results using Gaussian (RBF) kernel function based on K-fold cross-validation compared to regular SVR. This implies that reduced variance in the denoising procedure and obtain optimal parameter in kernel function may improve forecasting accuracy.

Keywords


Support vector regression; kernel functions; wavelet denoising; mother wavelets; wavelet decomposition levels.

Full Text:

PDF

References


Adamowski, J. and Chan, H. F. 2011. A wavelet neural network conjunction model for groundwater level forecasting. J. Hydrol. 407: 28–40.

Adamowski, J. and Sun, K. 2010. Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. J. Hydrol. 390 (1–2), 85–91.

Adamowski, J. 2013. Using support vector regression to predict direct runoff, base flow and total flow in a mountaineous watershed with limited data. Land Reclam. 45 (1): 71–83.

Bray, M. and Han, D. 2004. Identification of support vector machines for runoff modeling. J. Hydroinform. 6 (4): 265–280.

Brito, N. S. P., Souza, B. A. and Pires, F. A. C. 1998. Daubechies wavelets in quality of electrical power. The international conference on harmonics and quality of power. 511–515.

Cannas, B., Fanni, A., See, L and Sias, G. 2006. Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning. Phys. Chem. Earth. 31 (18): 1164–1171.

Cheng S. and Pecht, M. 2012. Using cross-validation for model parameter selection of sequencial probability ratio test, Expert Systems with Applications. 39: 8467-8473.

Chou, C.-M. and Wang, R.-Y. 2002. On-line estimation of unit hydrographs using the wavelet-based LMS algorithm. Hydrol. Sci. J. 47 (5): 721–738.

Cortes, C. and Vapnik, V. 1995, Support-vector networks. Machine Learning. 20(3): 273–297.

Coulibaly, P. and Burn, H.D. 2004. Wavelet analysis of variability in annual Canadian streamflows. Water Resour. Res. 40: W03105.

Daubechies, I. 1990. The wavelet transform, time–frequency localization and signal analysis. IEEE Trans. Inform. Theory. 36 (5): 6–7.

de Artigas, M.Z., Elias, A.G. and de Campra, P. F. 2006. Discrete wavelet analysis to assess long-term trends in geomagnetic activity. Phys. Chem. Earth. 31 (1–3):77–80.

Guo, J., Zhou, J., Qin, H., Zou, Q. and Li, Q. 2011. Monthly streamflow forecasting based on improved support vector machine model. Expert Systems with Applications. 38: 13073–13081. http://doi.org/10.1016/ j.eswa.2011.04.114

Guo, J., Zhou, J., Qin, H., Zou, Q. and Li, Q. 2011. Monthly streamflow forecasting based on improved support vector machine model. Expert Systems with Applications. 38: 13073–13081. http://doi.org/10.1016/ j.eswa.2011.04.114

Kalteh, A. M. 2013. Monthly River flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform. Comput. Geosci. 54: 1–8.

Kim, G. and Barros, A.P. 2001. Quantitative flood forecasting using multisensor data and neural networks. J. Hydrol. 246: 45–62.

Kisi, O. and Cimen, M. 2011. A wavelet-support vector machine conjunction model for monthly streamflow forecasting. J. Hydrol. 399: 132–140.

Kisi, O. and Cimen, M. 2012. Precipitation forecasting by using wavelet-support vector machine conjunction model. Eng. Appl. Artif. Intell. 25: 783–792.

Kisi, O. 2009. Neural networks and wavelet conjunction model for intermittent stream flow forecasting. J Hydrol Eng. 14(8):773–782.

Kisi, O. 2008. Stream flow forecasting using neuro-wavelet technique. Hydrol Process. 22:4142–4152.

Li, L. 2011. Water resource requirement prediction based on the wavelet– bootstrap–Svm hybrid model. J. Inf. Comput. Sci. 8 (13):2563–2568.

Lin, J. Y., Cheng, C. T. and Chau, K. W. 2006. Using support vector machines for long-term discharge prediction. Hydrol. Sci. J. 51 (4): 599–612.

Liong, S. and Sivapragasam, C. 2002. Flood stage forecasting with support vector machines. J. Am. Water Resour. Assoc. 38 (1): 173–186.

Liu, F., Zhou, J. Z., Qiu, F. P., Yang, J. J. and Liu, L. 2006. Nonlinear hydrological time series forecasting based on the relevance vector regression. Neural information processing, LNCS II. 4233: 880-889.

Liu, Z., Zhou, P., Chen, G. and Guo, L. 2014. Evaluating a coupled discrete wavelet transform and support vector regression for daily and monthly streamflow forecasting. Journal of Hydrology. 519: 2822–2831. http://

doi.org/10.1016/j.jhydrol.2014.06.050.

Lu, R.Y. 2002. Decomposition of interdecadal and interannual components for North China rainfall in rainy season. Chinese J. Atmos. 26:611–624.

Makkeasorn, A., Chang, N. B. and Zhou, X. 2008. Short-term streamflow forecasting with global climate change implications—a comparative study between genetic programming and neural network models. J. Hydrol. 352: 336–354.

McKerchar, A. I. and Delleur, J. W. 1974. Application of seasonal parametric linear stochastic models to monthly flow data. Water Resour. Res. 10: 246–255.

Milne, A. E., Macleod, C. J. A., Haygarth, P. M., Hawkins, J. M. B. and Lark, R. M. 2009. The wavelet packet transform: A technique for investigating temporal variation of river water solutes. J. Hydrol. 379 (1–2): 1–19.

Mohsen, B., Keyvan, A., Morteza, E. and Palhang, M. 2009. Generalization performance of support vector machines and neural networks in runoff modeling. Expert Systems with Applications. 36(4):7624–7629.

Nalley, D., Adamowski, J. and Khalil, B. 2012. Using discrete wavelet transforms to analyze trends in streamflow and precipitation in Quebec and Ontario (1954– 2008). J. Hydrol. 475: 204–228.

Nourani V, Komasi, M. and Mano, A. 2009. A multivariate ANN-wavelet approach for rainfall-runoff modeling. Water Resour Manag. 23(14):2877–2894.

Nourani, V., Kisi, O. and Komasi, M. 2011. Two hybrid artificial intelligence approaches for modeling rainfall–runoff process. J. Hydrol. 402 (1–2): 41–59.

Partal, T. and Kucuk, M. 2006. Long-term trend analysis using discrete wavelet components of annual precipitations measurements in Marmara region (Turkey). Phys. Chem. Earth. 31: 1189–1200.

Popivanov, I. and Miller, R.J. 2002. Similarity search over time-series data using wavelets. Proceedings 18th International Conference on Data Engineering .212–221.

Pramanik, N., Panda, R. K., Singh, A. 2010. Daily river flow forecasting using wavelet ANN hybrid models. J. Hydroinform. 13 (1): 49–63.

Rasouli, K., Hsieh, W. W. and Cannon, A. J. 2012. Daily streamflow forecasting by machine learning methods with weather and climate inputs. J. Hydrol. 414– 415: 284–293.

Remesan, R., Shamim, M. A., Han, D. and Mathew, J. 2009. Runoff prediction using an integrated hybrid modelling scheme. J. Hydrol. 372: 48–60.

Sang, Y. F. 2013. A review on the applications of wavelet transform in hydrology time series analysis. Atmos. Res. 122: 8–15.

Shiri, J. and Kisi, O. 2010. Short-term and long-term stream flow forecasting using a wavelet and neuro-fuzzy conjunction model. J. Hydrol. 394 (3–4): 486–493.

Sivapragasam, C., 2001. Liong, S. Y. and Pasha, M. F. K. Rainfall and runoff forecasting with SSA–SVM approach. J. Hydroinform. 3 (3): 141–152.

Smith, L. C., Turcotte, D. L. and Isacks, B. 1998. Stream flow characterization and feature detection using a discrete wavelet transform. Hydrol. Process. 12:233–249.

Tiwari, M. K. and Chatterjee, C. 2010. Development of an accurate and reliable hourly flood forecasting model using wavelet–bootstrap–ANN (WBANN) hybrid approach. J. Hydrol. 1 (394): 458–470.

Torrence, C. and Compo, G. P. 1998. A practical guide to wavelet analysis. Bull. Am. Meteorol. Soc. 79: 61–78.

Vapnik, V. 1995. The Nature of Statistical Learning Theory. Springer Verlag, New York, USA.

Vapnik, V., Golwich, S. and Smola, A. J. 1997. Support vector method for function approximation, regression estimation, and signal processing. In: Mozer, M., Jordan, M., Petsche, T. (Eds.),

Advances in Neural Information Processing Systems 9. MIT Press,

Cambridge, Massachusetts, USA. 281–287.

Vapnik, V.N. 1999. An overview of statistical learning theory. IEEE Transactions on Neural Networks. 10 (5): 988–999.

Wang, W. C., Chau, K. W., Cheng, C. T. and Qiu, L. 2009. A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. J. Hydrol. 374 (3–4): 294–306.

Wu, C. H., Tzeng, H., and Lin, R. H. 2009. A novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression. Expert Systems with Applications. (36):4725-4735.

Wu, M. C., Lin, G. F. and Lin, H. Y. 2012. Improving the forecasts of extreme streamflow by support vector regression with the data extracted by self-organizing map. Hydrol. Process. http://dx.doi.org/10.1002/ hyp.9584.

Xingang, D., Ping, W. and Jifan, C. 2003. Multiscale characteristics of the rainy season rainfall and interdecadal decaying of summer monsoon in North China. Chinese Sci. Bull. 48: 2730–2734.

Xiong, J. Q. and Li, Z. Y. 2005. Sediment-carrying capacity forecasting based on support vector machine. Journal of Hydraulic Engineering. 36(10): 1171–1175.

Yu, G. R. and Xia, Z. Q. 2008. Prediction model of chaotic time series based on support vector machine and its application to runoff. Advances in Water Science. 19(1): 116–122.

Yu, P., Chen, S. and Chang, I. 2006. Support vector regression for real-time flood stage forecasting. 704–716. http://doi.org/10.1016/j.jhydrol.2006.01. 021.

Yu, P.S., Chen, S. T. and Chang, I. F. 2006. Support vector regression for real-time flood stage forecasting. J. Hydrol. 328 (3–4): 704–716.




DOI: https://doi.org/10.11113/mjfas.v13n4-1.876

Refbacks

  • There are currently no refbacks.


Copyright (c) 2017 noraini ibrahim, norhaiza ahmad

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


Copyright © 2005-2019 Penerbit UTM Press, Universiti Teknologi Malaysia. Disclaimer: This website has been updated to the best of our knowledge to be accurate. However, Universiti Teknologi Malaysia shall not be liable for any loss or damage caused by the usage of any information obtained from this website.