基于XGBoost算法的v_(P)/v_(S)预测及其在储层检测中的应用  

v_(P)/v_(S) prediction based on XGBoost algorithm and its application in reservoir detection

作　　者：田仁飞[1] 李山 刘涛 景洋 TIAN Renfei;LI Shan;LIU Tao;JING Yang(College of Geophysics,Chengdu University of Technology,Chengdu,Sichuan 610059,China;Hulunbuir Subsidiary of PetroChina Daqing Oilfield Co.Ltd.,Daqing,Heilongjiang 163712,China)

机构地区：[1]成都理工大学地球物理学院,四川成都610059 [2]中国石油大庆油田公司呼伦贝尔分公司,黑龙江大庆163712

出　　处：《石油地球物理勘探》2024年第4期653-663,共11页Oil Geophysical Prospecting

基　　金：国家自然科学基金项目“准噶尔盆地春光区块岩性油藏倒频域烃类检测方法研究”(41304080)资助。

摘　　要：鄂尔多斯盆地碳酸盐岩地层蕴含着丰富的油气资源。在勘探实践中发现,大牛地气田马家沟组断层发育、断距小,类型多样且成因复杂,给勘探、开发带来了较多挑战。为了应对这些挑战,提高储层预测的精度变得至关重要。在分析大牛地气田敏感弹性参数的基础上,建立地震属性与储层纵横波速度比(v_(P)/v_(S))的关系,提出一种基于XGBoost算法的地震多属性v_(P)/v_(S)预测方法。为了进一步提升XGBoost算法的预测精度和泛化能力,采用贝叶斯算法对XGBoost算法的超参数进行优化,从而找到最佳的超参数组合,以确保模型在训练集和测试集上的性能均能得到提升。将XGBoost算法应用于Marmousi 2模型进行横波速度预测,预测值与实际值相关系数超过0.88,而均方误差、平均绝对百分比误差分别低于6.55×10^(-7)和4%,验证了该方法的准确性和可靠性。在鄂尔多斯盆地大牛地气田,应用该方法获得的v_(P)/v_(S)成功识别出含气储层,结果与实际钻井数据一致。理论模型和实际数据应用结果表明,XGBoost作为一种强大的机器学习算法预测精度较高,为直接由叠后地震属性预测v_(P)/v_(S)提供了一种有效的途径。There are abundant oil and gas resources entrapped in the carbonate reservoirs of the Ordos Basin.However,exploration results showed that the Majiagou Formation in the Daniudi Gas Field had developed multiple kinds of faults with small fault throws due to complex origins,which brings many challenges to its exploration and development.To address these challenges,it is crucial to optimize the sensitive elastic parameters for reservoir prediction.Therefore,the relationship between seismic attributes and the velocity ratio of compressional to shear waves(v_(P)/v_(S))in the reservoir has been established,based on the analysis of elastic‑sensitive parameters in the Daniudi Gas Field.Then,a prediction method for the v_(P)/v_(S) based on the XGBoost algorithm and multiple seismic attributes is proposed.To further improve the performance and generalization ability of the model,the hyperparameters of the XGBoost algorithm are optimized by Bayesian algorithm.This approach aims to find the optimal combination of hyperparameters,ensuring improved performance of the model on both training and testing datasets.The XGBoost algorithm is applied to the Marmousi 2 model for predicting shear wave velocity,achieving a correlation coefficient between predicted and actual values exceeding 0.88.With root mean squared error and mean absolute percentage error below 6.55×10^(-7) and 4%respectively,the accuracy and reliability of the proposed method are demonstrated.The method applied in the Daniudi Gas Field of the Ordos Basin has successfully identified gas‑bearing reservoirs,and the results are consistent with actual drilling data.Both theoretical model and practical data indicate that XGBoost,as a powerful machine learning algorithm,exhibits high accuracy,which can provide an effective approach for directly predicting v_(P)/v_(S) from poststack seismic attributes.

关 键 词：横波速度 碳酸盐岩储层 地震属性 XGBoost算法 纵横波速度比(v_(P)/v_(S)) 

分 类 号：P631[天文地球—地质矿产勘探]