Title :
Study on inferring interwell connectivity of injection-production system based on decision tree
Author :
Maojun Cao ; Fuhua Shang
Author_Institution :
Sch. of Comput. & Inf. Technol., Northeast Pet. Univ., Daqing, China
Abstract :
Interwell connectivity of injection-production system is a kind of important information of reservoir performance analysis. It is largely significant for researching the distribution of remaining-oil and adjusting the oilfield development plan. In order to change the status quo of inferring interwell connectivity in NO.1 oil production plant of Daqing Oilfield, an automatic identification method based on decision tree is proposed in this paper, which used CART algorithm to construct a decision tree, analysized the data of oilfield development to extract potential knowledge and established the direct mapping between logging data and interwell connectivity of injection wells and production wells. According to the experimental results, this method has the advantages of simple operation and fast discriminant. It improved the efficiency of discrimination and meanwhile ensured a greater accuracy.
Keywords :
decision trees; hydrocarbon reservoirs; oil drilling; well logging; CART algorithm; Daqing oilfield development plan; decision tree; injection wells; injection-production system; interwell connectivity; logging data; production wells; reservoir performance analysis; Accuracy; Classification algorithms; Data mining; Decision trees; Reservoirs; Shafts; CART; Decision Tree; Injection-production System; Interwell Connectivity;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery (FSKD), 2013 10th International Conference on
Conference_Location :
Shenyang
DOI :
10.1109/FSKD.2013.6816343