| 基于改进随机森林的火山岩测井岩性识别 |
| |
| 引用本文： | 黄安,蔡文渊,魏新路,李瑶,段高山,刘迪仁.基于改进随机森林的火山岩测井岩性识别[J].科学技术与工程,2023,23(9):3696-3704. |
| |
| 作者姓名： | 黄安 蔡文渊 魏新路 李瑶 段高山 刘迪仁 |
| |
| 作者单位： | 长江大学 地球物理与石油资源学院;中国石油集团测井有限公司华北分公司;中国石油集团测井有限公司辽河分公司 |
| |
| 基金项目： | 国家重点研发计划项目子课题 |
| |
| 摘 要： | 准噶尔盆地石炭系火山岩岩性复杂，在某种岩性薄片、岩心等资料数量明显少于其他岩性时，常规方法划分岩性存在困难。为了解决上述问题，提高火山岩岩性识别精度，运用合成少数类过采样技术(synthetic minority oversampling technique, SMOTE)算法增加少数岩性类别样本数量，解决数据不均衡问题；通过网格搜索和K折交叉验证法确定最优参数组合，开展基于改进随机森林的火山岩岩性识别研究。通过分析火山岩岩心、薄片、测井响应特征等资料，建立了岩性交会图版，确定了研究区对岩性敏感的测井参数重要性程度。实例资料应用表明，改进的随机森林算法有效地解决了传统随机森林算法受岩性样本类型不均衡及数据量较小的影响，火山岩岩性识别准确率由87%提升到了94%,为不均衡样本情况下火山岩岩性识别提供借鉴。
|
| 关 键 词： | 随机森林 SMOTE算法 测井响应 火山岩 岩性识别 |
| 收稿时间： | 2022/7/26 0:00:00 |
| 修稿时间： | 2023/3/27 0:00:00 |
Lithology identification of volcanic logging based on improved random forest |
| |
| Huang An,Cai Wenyuan,Wei Xinlu,Li Yao,Duan Gaoshan,Liu Diren.Lithology identification of volcanic logging based on improved random forest[J].Science Technology and Engineering,2023,23(9):3696-3704. |
| |
| Authors: | Huang An Cai Wenyuan Wei Xinlu Li Yao Duan Gaoshan Liu Diren |
| |
| Affiliation: | College of Geophysics and petroleum resources,Yangtze University,Wuhan;North China branch of CNPC logging CO,LTD,Renqiu;Liaohe branch of CHINA PETROLEUM LOGGING CO,LTD,Panjin |
| |
| Abstract: | The lithology of carboniferous volcanic rocks in Junggar Basin is complicated. It is difficult to divide lithology by conventional methods when the number of thin sections and cores of one lithology is obviously less than that of other lithology. In order to solve the above problems and improve the accuracy of volcanic rock lithology identification, SMOTE algorithm is used to increase the number of samples of a few lithologic categories to solve the problem of data imbalance; The optimal parameter combination was determined by grid search and K-fold cross validation method, and the lithologic identification of volcanic rocks based on improved random forest was carried out. By analyzing the data of volcanic rock core, thin section and logging response characteristics, the lithologic crossplot is established, and the importance of logging parameters sensitive to lithology in the study area is determined. The application of case data shows that the improved random forest algorithm effectively solves the influence of the traditional random forest algorithm due to the unbalance of lithological sample types and the small amount of data, and the accuracy rate of volcanic rock lithology identification increases from 87% to 94%, which provides reference for the lithology identification of volcanic rock in the case of unbalanced samples. |
| |
| Keywords: | random forest Smote algorithm Logging response volcanic rock lithology identification |
|
| 点击此处可从《科学技术与工程》浏览原始摘要信息 |
|
点击此处可从《科学技术与工程》下载全文 |
|
