引导模糊C均值聚类算法在联合反演综合解释中的应用  

Application of guided fuzzy C⁃means clustering algorithm in joint inversion comprehensive interpretation

作　　者：陈易周 刘江 涂齐催 李炳颖 娄敏 CHEN Yizhou;LIU Jiang;TU Qicui;LI Bingying;LOU Min(Research Institute of Shanghai Branch,CNOOC Limited,China,Shanghai 200335,China)

机构地区：[1]中海石油(中国)有限公司上海分公司研究院,上海200335

出　　处：《石油地球物理勘探》2024年第4期865-874,共10页Oil Geophysical Prospecting

基　　金：中国海洋石油有限公司“十四五”重大科技项目“潜山油气成藏理论与勘探关键技术”(KJGG2022-0302);“地层岩性油气藏高效识别与精细评价技术”(KJGG2022-0303)联合资助。

摘　　要：不同地球物理方法的反演结果常常存在差异,根据不同方法的联合反演结果得到最终合理解释是了解地下结构的关键。为此,提出了一种引导式模糊C均值(FCM)聚类算法,即在FCM聚类算法的基础上,结合现有地质认识,引入先验约束信息指导聚类中心的确定,对地球物理联合反演结果进行综合定量解释,旨在降低传统人工解释的主观性和局限性。模型测试表明,与传统FCM聚类技术相比,引导FCM聚类技术效果更好,特别是处理复杂地质结构的反演数据时,能够有效地区分不同地质体。实际数据的应用结果证明了引导FCM聚类技术在多属性地球物理联合反演结果综合解释中的应用潜力较大。该技术不仅提升了地球物理数据解释的科学性,而且为地下资源勘探提供了一个更可靠和精确的工具。There are differences in the inversion results of different geophysical methods,and the key to obtain⁃ing accurate underground knowledge is a final reasonable interpretation based on the joint inversion results of dif⁃ferent methods.A guided fuzzy C⁃means(FCM)clustering algorithm is proposed for this purpose,and based on the fuzzy C⁃means(FCM)clustering algorithm,this paper includes the existing geologic understanding,in⁃troduces prior constraint information to guide the determination of the clustering centers,and provides a compre⁃hensive quantitative interpretation of the results of the geophysical joint inversion,aiming at reducing the subjec⁃tivity and limitations of traditional manual interpretation.The model test shows that the guided FCM clustering technology is more effective than the traditional FCM clustering technologies,especially its ability to effectively distinguish different geological bodies when processing inversion data of complex geological structures.The re⁃sults of practical data applications demonstrate the great potential of the guided FCM clustering technology in the comprehensive interpretation of multi⁃attribute geophysical joint inversion results.This technology not only makes geophysical data interpretation more scientific but also provides a more reliable and accurate tool for un⁃derground resource exploration.

关 键 词：模糊C均值聚类 联合反演 综合解释 先验约束信息 多属性 

分 类 号：P631[天文地球—地质矿产勘探]