摘要
传统的沉积相识别方法依赖地质专家的先验知识,利用地震和测井数据,借助计算机的存储和计算能力定性分析沉积环境。地震相的识别以地震数据为基础,因需大量的人工解释,准确率和效率均不甚理想。如何从地震数据中表征沉积微相的地质特征,实现沉积微相的三维空间刻画仍有待研究。近年来,知识图谱(KG)在地学领域中引起广泛关注,通过构建KG进行约束也可改进传统沉积相识别方法,但是KG、深度学习(DL)与沉积相地震技术识别需进一步融合,研发基于KG约束的沉积微相精细识别技术是目前亟需解决的技术难题。为此,将地质先验知识引入KG,构建了地下复杂沉积模式的计算机高层语义认知系统,利用KG对地质先验知识的计算机表征,作为约束条件和质控手段引导沉积微相的识别与建模,形成了KG引导的沉积微相智能识别技术。利用所提方法将地质先验知识数字化之后,刻画了四川盆地川中地区灯影组碳酸盐岩微生物丘滩体以及多期次前积体沉积相微相的空间分布,预测结果与目标工区的特定地质情况契合。所提方法适用于深层岩性圈闭预测和井位论证,为储层预测提供了有效依据,具有较好的工业化应用、推广价值。
Relying on the prior knowledge of geological experts,the traditional identification methods for sedi⁃mentary facies use seismic and logging data to conduct a qualitative analysis of sedimentary environments with the aid of the storage and computation capacity of computers.As sedimentary facies identification based on seis⁃mic data requires a lot of manual interpretation,the accuracy and efficiency are not ideal.How to characterize the geological characteristics of sedimentary microfacies from seismic data and realize the three⁃dimensional spa⁃tial characterization of sedimentary microfacies remains to be studied.In recent years,the knowledge graph has attracted wide attention in the field of geoscience,and the traditional identification method for sedimentary fa⁃cies can be improved by constructing the knowledge graph as a constraint.However,it is an urgent technical problem to further integrate the knowledge graph,deep learning,and seismic identification technology of sedi⁃mentary facies to form a fine identification technology of sedimentary microfacies constrained by the knowledge graph.By introducing geological prior knowledge into the knowledge graph,this paper constructs a high⁃level semantic cognition system for complex underground sedimentary patterns.The knowledge graph is used for computer representation of geological prior knowledge,which can serve as constraint conditions and quality con⁃trol measures to guide the identification and modeling of sedimentary microfacies.It ultimately forms an intelli⁃gent identification and modeling technology for sedimentary microfacies guided by the knowledge graph.After digitizing geological prior knowledge,the presented method characterizes the spatial distribution of carbonate microbial mound⁃beach complexes and multi⁃stage foreset bodies in the Dengying Formation of the central Sichuan Basin.The predicted results are in line with the geological condition of the target area.The proposed method is suitable for deep lithologic trap identification and well demonstration,providing an effective basis for reservoir prediction and has good industrial application value.
作者
杨存
孟贺
叶月明
曹晓初
雍学善
YANG Cun;MENG He;YE Yueming;CAO Xiaochu;YONG Xueshan(Research Institute of Geology,Research Institute of Exploration and Development,PetroChina,Hangzhou,Zhejiang 310023,China;Northwest Branch,Research Institute of Exploration and Development,PetroChina,Lanzhou,Gansu 730020,China)
出处
《石油地球物理勘探》
EI
CSCD
北大核心
2024年第1期38-50,共13页
Oil Geophysical Prospecting
基金
国家自然科学基金项目“面向海洋深水资料的全波场最小二乘偏移方法研究”(41874164)
中国石油集团前瞻性基础性项目“物探岩石物理与前沿储备技术研究”(2021DJ3505)联合资助。
关键词
知识图谱(KG)
深度学习
沉积相
地震相
标签
智能识别
knowledge graph
deep learning
sedimentary facies
seismic facies
label
intelligent identification