A pattern recognition modeling approach based on the intelligent ensemble classifier: Application to identification and appraisal of water-flooded layers

• DOI: 10.1177/0959651818803725
• Publication Date: 2018-10-10T15:54:22Z
• Authors: Zhiqiang Geng; Xuan Hu; Ning Ding; Shanshan Zhao; Yongming Han
• Keywords: AdaBoost; Probabilistic classification

Since the actual chromatogram data of water-flooded layer have characteristics multiple dimension, complexity and noise, it is difficult to accurately identify appraise in oil gas reservoirs. Therefore, this article proposes a recognition modeling approach based on intelligent ensemble classifier, integrated model-free Bayesian AdaBoost algorithm support vector machine algorithm. The effective characteristic information can be obtained using curve fitting method. In order transform sparse classification problem into general problem, synthetic minority over-sampling technique used process an unbalanced training sample as sample. Moreover, algorithms are base classifiers train model. Compared traditional single approach, robustness effectiveness classifier model validated through standard source from UCI (University California at Irvine) repository. Finally, proposed applied identification appraisal layers complex system. prediction results provide more reliable information, guide reservoir exploration improve development efficiency.