摘要
识别扇三角洲沉积体对恢复古湖泊沉积体系和指导斜坡带岩性油气藏勘探有重要意义。以辽河东部凹陷铁匠炉地区沙一下亚段低渗透储层扇三角洲沉积为例,在岩心分析的基础上,通过单一地震属性分析、多属性聚类优选、机器学习等方法,构建了超限学习机算法驱动的地震多属性分析预测砂岩分布,进而识别扇三角洲沉积相展布的方法。研究表明:超限学习机算法在地震多属性预测砂岩分布方面具有良好的适用性;平均绝对振幅、能量半时和波谷数三种地震属性对砂岩分布表征有效;研究区沙一下亚段存在南物源,在古湖泊南岸发育一个小型扇三角洲,在古湖泊北岸发育两个大型扇三角洲,每个扇三角洲由两个朵叶体组成。研究为斜坡带扇三角洲砂体分布预测和沉积相表征提供了有效方法。
The identification of Fan Delta is of great significance to the rebuilding of paleolake sedimentary system and to the exploration of lithologic reservoirs in slope zone.Fan Delta of lower part in the1 st member of Shahejie Formation in Tiejianglu area,eastern sag of Liaohe Depression was taken as an example.On the basis of drilling core analysis,an extreme learning machine driven method of sandstone distribution prediction was built and then used in the characterization of Fan Delta sedimentary facies.The method was built based on a set of methods including single seismic attributes analysis,multi attribute clustering optimization,and machine learning.It is concluded that extreme learning machine can be used in multi seismic attributes analysis to predict sandstone distribution.Three seismic attributes including average absolute amplitude,energy half time,and number of trough are effective in the characterization of sandstone distribution.There is sediment-source from the south which formed a small Fan Delta on the south bank of the paleolake.Meanwhile,on the north bank of the paleolake,there deposited two large Fan Deltas each of which are formed by two lobes.An effective method for the distribution prediction and sedimentary facies characterization of fan delta sandbodies in slope zone is established.
作者
蔡国刚
杨光达
周艳
张东伟
解宝国
黄德榕
CAI Guo-gang;YANG Guang-da;ZHOU Yan;ZHANG Dong-wei;XIE Bao-guo;HUANG De-rong(Research Institute of Exploration and Development, Liaohe Oilfield Company, CNPC, Panjin 124010, China;School of Geosciences, China University of Petroleum (East China), Qingdao 266580, China)
出处
《科学技术与工程》
北大核心
2021年第29期12454-12460,共7页
Science Technology and Engineering
基金
“十三五”国家科技重大专项(2016ZX05006-005)
国家自然科学基金(41672129)。
关键词
地震多属性
超限学习机
扇三角洲
砂岩分布
multi-seismic attributes
extreme learning machine
Fan Delta
sandstone distribution