Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (8): 2453-2459.DOI: 10.11772/j.issn.1001-9081.2020101867

Special Issue: 第八届CCF大数据学术会议(CCF Bigdata 2020)

• CCF Bigdata 2020 • Previous Articles     Next Articles

Multi-granularity temporal structure representation based outlier detection method for prediction of oil reservoir

MENG Fan1, CHEN Guang1, WANG Yong2, GAO Yang1, GAO Dequn2, JIA Wenlong3   

  1. 1. Department of Computer Science and Technology, Nanjing University, Nanjing Jiangsu 210023, China;
    2. Geophysical Prospecting Research Institute, Jiangsu Oilfield Company, Sinopec Group, Nanjing Jiangsu 210046, China;
    3. Nanjing Tach Communication Technology Industry Company Limited, Nanjing Jiangsu 210019, China
  • Received:2020-10-29 Revised:2020-12-30 Online:2021-08-10 Published:2021-01-27

基于多粒度时序结构表示的异常检测算法在储层含油性检测中应用

孟凡1, 陈广1, 王勇2, 高阳1, 高德群2, 贾文龙3   

  1. 1. 南京大学 计算机科学与技术系, 南京 210023;
    2. 中国石油化工股份有限公司江苏油田分公司 物探技术研究院, 南京 210046;
    3. 南京天技通信技术实业有限公司, 南京 210019
  • 通讯作者: 高阳
  • 作者简介:孟凡(1988-),男,江苏南京人,高级工程师,博士研究生,CCF会员,主要研究方向:机器学习、无监督异常检测;陈广(1992-),男,江苏南京人,硕士研究生,主要研究方向:数据挖掘;王勇(1962-),男,河北吴桥人,教授级高级工程师,博士,主要研究方向:地震资料数据处理;高阳(1972-),男,江苏淮安人,教授,博士生导师,博士,CCF高级会员,主要研究方向:大数据分析、机器学习、多智能体系统、视频/图像处理;高德群(1970-),男,江苏泰州人,高级工程师,硕士,主要研究方向:石油地质勘探;贾文龙(1984-),男,陕西商洛人,工程师,主要研究方向:大数据、人工智能。

Abstract: The traditional methods for prediction of oil reservoir utilize the seismic attributes generated when seismic waves passing through the stratum and geologic drilling data to make a comprehensive judgment in combination with the traditional geophysical methods. However, this type of prediction methods has high cost of research and judgement and its accuracy strongly depends on the prior knowledge of the experts. To address the above issues, based on the seismic data of the Subei Basin of Jiangsu Oilfield, and considering the sparseness and randomness of oil-labeling samples, a multi-granularity temporal structure representation based outlier detection algorithm was proposed to perform the prediction by using the post-stack seismic trace data. Firstly, the multi-granularity temporal structures for the single seismic trace data was extracted, and the independent feature representations were formed. Secondly, based on extracting multiple granularity temporal structure representations, feature fusion was carried out to form the fusion representation of seismic trace data. Finally, a cost-sensitive method was utilized for the joint training and judgement to the fused features, so as to obtain the results of oil reservoir prediction for these seismic data. Experiments and simulations of the proposed algorithm were performed on an actual seismic data of Jiangsu Oilfield. Experimental results show that the proposed algorithm is improved by 10% on Area Under Curve (AUC) compared to both of the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms.

Key words: prediction of oil reservoir, outlier detection, multi-granularity, cost-sensitive, temporal structure

摘要: 传统储层含油性勘测方法利用地震波穿过地层时产生的相关地震属性和地质钻井资料结合传统地球物理方法进行综合研判,但该类勘测方法往往存在研判成本高且对专家先验知识依赖性强的问题。针对该问题,以江苏油田苏北盆地的地震资料为基础,并结合含油样本的稀疏性和随机性,提出了一种基于多粒度时序结构表示的异常检测算法,直接利用叠后地震道数据进行预测。该算法首先对于单个地震道数据提取多粒度时序结构并形成独立特征表示;其次,在提取多个粒度时序结构表示的基础上进行特征融合,以形成对地震道数据的融合表示;最后,通过对融合后的特征采用代价敏感方法进行联合训练和判别,从而得到对于该地震数据的含油性勘测结果。所提算法在江苏油田实际原始地震资料上进行了实验仿真,实验结果表明:所提算法相比长短期记忆(LSTM)和门控循环单元(GRU)算法在曲线下方的面积(AUC)指标上均提升了10%。

关键词: 含油性检测, 异常检测, 多粒度, 代价敏感, 时序结构

CLC Number: