纵横波地震数据联合的河道自动识别方法

打开文本图片集

中图分类号：P631 文献标识码：A DOI：10.13810/j.cnki.issn.1000-7210.20240318

Jointautomaticchannelidentificationmethod using P- and S-wave seismic data

Chen Kang，Dai Juncheng，Ran Qi， Peng Haotian，Yang Guangguang，Yan Yuanyuan （Research Institute of Southwest Oil&.Gas Company，PetroChina，Chengdu，Sichuan 6lOo5l，China）

Abstract：Channel identification is crucial for predicting fluvial facies reservoirs.However，when the P-wave impedancecontrast between channel sandstones and surounding rocks is minimal，it is dificult to useonly poststack P-wave seismicdata for channel identification.S-wave data can efectively enhance the reliability of predicting the spatial distribution of channels.However，the combined identification process of P-wave and S- wave involves chalenges such as dificult parameter selection，high subjectivity，and extended working cycles， leading to ineficiencies and reduced reliability. This paper proposes an automatic channel identification methodbased on the joint P-wave and S-wave seismic data. First，to address the issue of insuficient sample data，it puts forward a method for automaticaly generating synthetic forward modeling samples of 3D channel geological models based on actual data interpretation and channel interpretation results，efectively expanding the sample data set. Subsequently，a new 3D automatic channel identification network structure is then designed， which efectively integrates P-wave and S-wave seismic data，enhancing the reliability of the identification re sults.Finall，the proposed method is applied to identify tight gas channel sandstones in a work area in southwestern China. Compared with traditional seismic attribute analysis and inteligent identification results relying ona singledata type，the proposed method demonstrates higher eficiencyand reliability，validatingits applicability. Keywords： S-wave，P-wave，deep learning，3D channel sample data，channel identification

陈康，戴隽成，再崎，等。（剩余16748字）