基于CV-XGBoost的水下分流河道砂体厚度预测及应用  

Sand Body Thickness Prediction of Underwater Distributary Channel Based on CV-XGBoost Method

作　　者：白青林 刘烜良 张军华[2] 王福金[1] 刘中伟[1] 焦红岩[1] Bai Qinglin;Liu Xuanliang;Zhang Junhua;Wang Fujin;Liu Zhongwei;Jiao Hongyan(Xianhe Oil Production Plant,Shengli Oilfield Company,SINOPEC,Dongying 257068,Shandong,China;School of Geosciences,China University of Petroleum,Qingdao266580,Shandong,China)

机构地区：[1]中国石化胜利油田分公司现河采油厂,山东东营257068 [2]中国石油大学(华东)地球科学与技术学院,山东青岛266580

出　　处：《吉林大学学报（地球科学版）》2023年第5期1602-1610,共9页Journal of Jilin University：Earth Science Edition

基　　金：国家自然科学基金项目(42072169);胜利油田科研攻关项目(YKY2106)。

摘　　要：针对水下分流河道砂体单层厚度薄,叠置、交叉严重,横向非均质性强,井震关系一致性不好等问题,研究了一种基于交叉验证的极限梯度提升(CV-XGBoost)储层厚度预测方法。先用相关分析与多重共线性评价去除冗余属性,然后进行模型训练与参数集寻优,最后用验证集进行厚度预测。结果表明:1)对于较少样本的储层预测,有必要做交叉验证,以提高储层预测精度;2)XGBoost用具有二阶偏导的正则项来控制模型收敛进度,预测精度好于常规的LASSO(least absolute shrinkage and selection operator)回归、GBDT(gradient boosting decision tree)和SVM(support vector machine)方法;3)验证集占比较低的储层预测可用来了解砂体宏观展布,较高的验证集占比则有助于提高砂体描述的精度;4)本研究区平均振幅、平均能量、弧长、主频为厚度预测贡献度较大的属性。Aiming at the problems of underwater distributary channel sand body,such as thin single layer thickness,serious superimposition and crossing,strong lateral heterogeneity,and poor consistency of well seismic relationship,this study presents a prediction method of CV-XGBoost reservoir thickness based on cross validation.Firstly,correlation analysis and multicollinearity evaluation are used to remove redundant attributes,then the model training and parameter set optimization are carried out,and finally thickness prediction is carried out with verification set.The results show that:1)For reservoir prediction with few samples,it is necessary to do cross validation to improve the accuracy of reservoir prediction;2)XGBoost uses a regular term with the second order partial derivative to control the convergence progress of the model,and its prediction accuracy is better than that of conventional LASSO(least absolute shrinkage and selection operator)regression,GBDT(gradient boosting decision tree)and SVM(support vector machine)methods;3)The reservoir prediction results with low verification set ratio can be used to understand the macro distribution of sand body,and the higher verification set ratio is helpful to improve the accuracy of sand body description;4)The average amplitude,average energy,arc length and dominant frequency in this study area are the attributes that contribute greatly to thickness prediction.

关 键 词：交叉验证 极限梯度提升 属性优化 砂体厚度预测 

分 类 号：P631.4[天文地球—地质矿产勘探]