地学前缘 ›› 2021, Vol. 28 ›› Issue (6): 155-161.DOI: 10.13745/j.esf.sf.2021.1.51

• 钾盐探测新技术 • 上一篇    下一篇

基于人工智能的川东北三叠系杂卤石地震识别

慎国强1, 王玉梅1, 张繁昌2, 张洪1, 王希萍1, 陈松莉1   

  1. 1.中国石化胜利油田分公司 物探研究院, 山东 东营 257022;
    2.中国石油大学(华东) 地球科学与技术学院, 山东 青岛 266580
  • 收稿日期:2021-01-18 修回日期:2021-05-20 出版日期:2021-11-25 发布日期:2021-11-25
  • 作者简介:慎国强(1973—),男,博士,高级工程师,主要从事地震反演及储层综合研究。E-mail:shengq230.slyt@sinopec.com
  • 基金资助:
    国家重点研发计划项目(2017YFC0602804); 中石化科技攻关项目“高精度保真性三维叠前地震联合反演技术研究(P18051-5)”

Identification of Triassic polyhalite in Northeast Sichuan by AI-based seismic inversion

SHEN Guoqiang1, WANG Yumei1, ZHANG Fanchang2, ZHANG Hong1, WANG Xiping1, CHEN Songli1   

  1. 1. Geophysical Research Institute of Sinopec Shengli Oilfield Branch Co., Dongying 257022, China;
    2. School of Geosciences, China University of Petroleum (East China), Qingdao 266580, China;
  • Received:2021-01-18 Revised:2021-05-20 Online:2021-11-25 Published:2021-11-25

摘要: 作为钾肥的主要来源之一,杂卤石矿藏具有旺盛的需求。我国川东北地区三叠系海相地层中,杂卤石矿藏发育。但该地区杂卤石矿体埋藏较深、分布散乱,勘探难度极大。为降低开发成本,需要充分借助地震资料的优势,为钾盐储层的描述提供钻前支持。针对该地区杂卤石层地震反射特征复杂、常规波阻抗反演方法难以直接预测的问题,本文引入人工智能算法对地震资料进行数据挖掘。本方法首先通过模糊粗糙集属性约简,提取适合富钾地层表征的敏感地震属性;然后以极限学习机为数据挖掘工具,自主学习敏感地震属性和井中实测钾含量曲线的非线性映射关系,形成了基于极限学习机的杂卤石预测方法。应用结果证明:利用极限学习机人工智能方法成功地对川东北地区的杂卤石进行了预测,取得了预期的地质效果,为该地区利用地震数据探寻杂卤石提供了一条新的勘探思路。

关键词: 杂卤石, 人工智能, 极限学习机, 敏感属性, 富钾地层

Abstract: As one of the main sources of potash fertilizer, polyhalite resource is in huge demand. Polyhalite deposits are well developed in the Triassic marine beds of Northeast Sichuan. However, these polyhalite deposits are very difficult to identify since they are deeply buried and scattered. To cut down the cost, seismic data are extremely useful in identifying well locations in pre-drilling exploration. Considering the complex relation between polyhalite deposits and seismic reflection in this area, it is impossible to directly predict potassium-rich salt layers solely by traditional impedance inversion method, herein an artificial intelligence (AI) approach is introduced. First, sensitive attributes suitable for characterizing potassium-rich layers are extracted using a fuzzy rough optimization algorithm. Then, on the basis of nonlinear mapping of the extracted sensitive seismic attributes onto the potassium-content well log, a polyhalite layer prediction method is established by using extreme learning machine. Using this method the polyhalite distribution in Northeast Sichuan was successfully identified. The AI-based seismic inversion methodology provides an alternative approach for the exploration of polyhalite layers in this area.

Key words: polyhalite deposits, artificial intelligence, extreme learning machine, sensitive attributes, potassium⁃rich layer

中图分类号: