Using a support vector machine method to predict the development indices of very high water cut oilfields

• Published in: Petroleum science Vol. 7; no. 3; pp. 379 - 384
• Main Authors: Zhong, Yihua, Zhao, Lei, Liu, Zhibin, Xu, Yao, Li, Rong
• Format: Journal Article
• Language: English
• Published: Beijing China University of Petroleum (Beijing) 01-09-2010; School of Sciences,Southwest Petroleum University,Chengdu,Sichuan 610500,China%Sichuan Forestry Cadre School,Chengdu,Sichuan 610066,China
• Subjects: Earth and Environmental Science; Earth Sciences; Economics and Management; Energy Policy; Industrial and Production Engineering; Industrial Chemistry/Chemical Engineering; Mineral Resources; 中国东部; 历史数据; 支持向量回归; 支持向量机方法; 模型预测; 油田开发指标; 特高含水开发阶段; 高含水油田; support vector regression; time series; Oilfield development indices; oilfield performance; high water cut; oilfieid performance
• ISSN: 1672-5107; 1995-8226
• DOI: 10.1007/s12182-010-0081-1

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.