基于改进型随机森林算法的页岩岩性识别——以准噶尔盆地芦草沟组为例

Shale Lithology Identification Based on Improved Random Forest Algorithm:A Case of Lucaogou Formation in Junggar Basin

在储集层岩性识别的应用中,特别是对页岩等非均质性较强的非常规储集层的岩性识别,机器学习算法的高效性、准确性和有效信息整合能力已经得到了充分验证。考虑到岩性识别的特征参数优选问题,优选自然伽马、T2几何平均值、结构指数、骨架密度指数、密度和深侧向电阻率,采用结合递归特征消除的随机森林算法,对准噶尔盆地中二叠统芦草沟组页岩储集层的主要岩性进行识别;利用传统的随机森林算法和支持向量机法,对同一套资料进行岩性预测,并与岩石薄片鉴定结果对比。结合递归特征消除的随机森林算法只需选择一半的测井参数,便能够达到更好的效果,而且通过优选特征参数,缩短了算法的运行时间。因此,结合递归特征消除的随机森林算法能够实现测井特征参数的优选,提高页岩岩性识别的准确率,缩短运行时间,为复杂岩性识别和多参数选择提供了新的思路。

In the application of reservoir lithology identification,the efficiency,accuracy and effective information integration ability of machine learning algorithm have been fully verified,especially in unconventional reservoirs with strong heterogeneity such as shale.Based on the optimal selection of parameters such as natural gamma,T2 geometric mean,structural index,skeleton density index,density,and deep lateral resistivity,and using a random forest algorithm combined with recursive feature elimination(RF⁃RFE),major lithologies of the shale reservoirs in the Middle Permian Lucaogou formation in the Junggar basin were identified.Lithology prediction was conducted on the same dataset using conventional RF and support vector machine(SVM)algorithms,and the results were compared with those obtained from thinsection identifications.It is found that RF⁃RFE yields better results with only half of the logging parameters,and the parameters defined by optimal selection help reduce the algorithm’s running time.Thus,the use of RF⁃RFE algorithm can realize optimal selection of characteristic logging parameters,more accurate identification of shale lithology,and reduction of running time.The algorithm provides a new approach for complex lithology identification and multi⁃parameter selection.