Abstract
Because the oilfields in eastern China are in the very high water cut development stage, accurate forecast of oilfield development indices is important for exploiting the oilfields efficiently. Regarding the problems of the small number of samples collected for oilfield development indices, a new support vector regression prediction method for development indices is proposed in this paper. This method uses the principle of functional simulation to determine the input-output of a support vector machine prediction system based on historical oilfield development data. It chooses the kernel function of the support vector machine by analyzing time series characteristics of the development index; trains and tests the support vector machine network with historical data to construct the support vector regression prediction model of oilfield development indices; and predicts the development index. The case study shows that the proposed method is feasible, and predicted development indices agree well with the development performance of very high water cut oilfields.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Box G E P, Jenkins G M and Reinsel G C. Time Series Analysis Forecasting and Control. Beijing: People Post and Telecommunications Press. 2005. 89–118
Chapelle O, Vapnik V N, Bousquet O, et al. Choosing multiple parameters for support vector machines. Machine Learning. 2002a. 46(1–3): 131–159
Chapelle O, Vapnik V N and Bengio Y. Model selection for small sample regression. Machine Learning. 2002b. 48(1–3): 9–23
Chen M F and Lang Z X. Application of a modified gray model in oilfield production forecast. Xinjiang Petroleum Geology. 2003. 24(3): 246–248 (in Chinese)
Cheng J S, Yu D J and Yang Y. Application of support vector regression machines to the processing of end effects of Hilbert-Huang transform. Mechanical Systems and Signal Processing. 2007. 21: 1197–1211
Cherkassky V and Ma Y Q. Comparison of model selection for regression. Neural Computation. 2003. 15(7): 1691–1714
Chung K M, Kao W C, Sun C L, et al. Radius margin bounds for support vector machines with the RBF kernel. Neural Computation. 2003. 15(11): 2643–2681
Feng Z H and Yang J M. Practical selection of support vector machine parameters for SVM regression. Mechanical Engineering & Automation. 2007. (3):17–18 (in Chinese)
Goh A T C and Goh S H. Support vector machines: Their use in geotechnical engineering as illustrated using seismic liquefaction data. Computers and Geotechnics. 2007. 34: 410–421
Ito K and Nakano R. Optimizing support vector regression hyperparameters based on cross-validation. Proceedings of the International Joint Conference on Neural Networks. 2003. 2077–2082
Li Y and Liu Z B. The Application of Modern Optimization Technique in Oilfield Development. Beijing: Petroleum Industry Press. 2001. 58–63 (in Chinese)
Lin H T and Lin C J. A study of sigmoid kernels for SVM and the training of non-PSD kernels by SMO-type methods. http://www.csie.ntu.edu.tw/~cjlin/papers.html. 2003
Lin S W, Lee Z J, Chen S C, et al. Parameter determination of support vector machine and feature selection using simulated annealing approach. Applied Soft Computing. 2008. 8(4): 1505–1512
Liu Z B, Ren B S and Zhao M. A functional simulation for oilfield output forecast based on time-varying system. Journal of Southwest Petroleum University (Science & Technology Edition). 2008. 30(4): 181–184 (in Chinese)
Momma M and Bennett K P. A pattern search method for model selection of support vector regression. In: Kumar V, Mannila H and Motwani R. (eds) Proceedings of the Second Siam International Conference on Data Mining. SIAM, Philadelphia, USA. 2002
Steinwart I. On the influence of the kernel on the consistency of support vector machines. The Journal of Machine Learning Research. 2002. 2: 67–93
Sun W. Study of evaluation system and methods for oilfield development in high water-cut stage. Ph.D Thesis. China University of Petroleum (EastChina). 2006 (in Chinese)
Wang G S. Properties and construction methods of kernel in support vector machine. Computer Science. 2006. (6): 173–174 (in Chinese)
Wang M S and Chen X G. Multiple linear regression method applied in oil production forecasting. Oil-Gasfield Surface Engineering. 2004. 11(23): 25–28 (in Chinese)
Wang Z L and Hu Y H. Applied Time Series Analysis. Beijing: Science Press. 2007. 126–146 (in Chinese)
Yao J M, Yu B S, Che C B, et al. Application of the improved GM model to oil production forecasting of the Tarim Basin. Petroleum Geology & Oilfield Development in Daqing. 2007. 26(1): 92–96 (in Chinese)
Zhang C H. Optimization problems in support vector machines. Ph.D Thesis. China Agricultural University. 2004. 36–39 (in Chinese)
Zhong Y H. Analysis of predicting method of conventional development dynamic indices in oilfields with an ultra-high water cut. Petroleum Geology & Oilfield Development in Daqing. 2009. 28(3): 55–59 (in Chinese)
Zhu Y S, Li C H and Zhang Y Y. A practical parameters selection method for SVM. In: Advances in Neural Networks. Springer Berlin/Heidelberg. 2004. 518–523
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhong, Y., Zhao, L., Liu, Z. et al. Using a support vector machine method to predict the development indices of very high water cut oilfields. Pet. Sci. 7, 379–384 (2010). https://doi.org/10.1007/s12182-010-0081-1
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12182-010-0081-1