融合储层纵向信息的机器学习岩性识别方法

A machine learning lithologic identification method combined with vertical reservoir information

测井资料中包含丰富的岩性信息,相比于取心资料,具有连续性强、成本低等优点。用机器学习方法探索测井曲线与实际取心段样本岩性之间的关系,实现储层岩性的自动识别,降低岩性识别成本,提高识别效率和准确性,可以为储层评价提供有效手段。基于岩性分类依据选择适合样本的分类方案,选取适合岩性分类问题的机器学习方法设计试验方案,提出了融合储层纵向信息的机器学习岩性识别方法,利用深度窗对常规测井数据和已知岩性数据进行了序列采样,生成了训练样本。用逻辑回归、支持向量机、随机森林、卷积神经网络和Stacking集成学习5种不同方法分别建立模型,对新疆某油田的强非均质岩层原始样本进行了岩性识别。结果表明,当深度窗宽度与岩层厚度相匹配时,在原始样本具有强非均衡性的情况下,用本方法对其进行预处理之后,各个机器学习方法获得的岩性识别准确率均有较大提高。深度窗的宽度决定了方法识别岩层厚度的精度,深度窗越小,识别精度越高;深度窗越大能够保留的纵向信息越多,对相应厚度的岩层识别准确率越高。本文的融合储层纵向信息的机器学习岩性识别方法能提升测井资料岩性识别的准确性,给非均质薄岩层的自动有效识别提供了经济有效的参考方案。

Compared with coring data,well logging data contain much lithologic information with the advantages of strong continuity and low cost.The machine learning method is applied to explore the correlation between the log curves and the lithology of the actual coring samples,realize the automatic identification of the lithology of the reservoirs,reduce the lithologic identification cost,improve the identification efficiency and accuracy and provides an effective tool for the evaluation of the reservoirs.Based on the lithology classification standard,the sample classification scheme is approximately selected and a machine learning lithologic identification method combined with the vertical reservoir information is proposed to design an experimental scheme.The depth window is used to carry out the sequence sampling of the conventional logging data and the known lithologic data to generate training samples.Logistic regression,support vector machine,random forest,convolutional neural networks and stacking ensemble learning are used to build machine learning models to identify the lithology of original samples of strongly heterogeneous rock formations in an oilfield in Xinjiang.The results show that when the width of the depth window matches the thickness of the rock layer well,the accuracy of lithologic identification obtained by each machine learning method is greatly improved after preprocessing the original strong non-equilibrium sample with the method in this paper.The width of the depth window determines the identification accuracy of the rock layer thickness.A thinner depth window can identify a thinner rock layer,while a thicker depth window contains more vertical information,which can obtain higher identification accuracy at the corresponding rock thickness.The machine learning lithologic identification method combined with vertical reservoir information is proposed,which provides an economical and effective reference solution for the automatic and effective identification of heterogeneous thin rock layers.