基于UNet+GRU深度学习方法提高叠后地震资料分辨率  

Improving the resolution of poststack seismic data based on UNet+GRU deep learning method

作　　者：郭爱华 路鹏飞 王丹丹[2] 吴吉忠 陈晓 彭怀宇 蒋书豪 Guo Ai-Hua;Lu Peng-Fei;Wang Dan-Dan;Wu Ji-zhong;Chen Xiao;Peng Huai-Yu;Jiang Shu-Hao(School of Information Engineering,East China University of Technology,Nanchang 330013,China;Geology Research Institute of the first Oil Production Plant of Huabei Oilfield,062250;Northeast Petroleum University,066000;School of Geophysics and measurement and control technology,East China University of Technology,Nanchang 330013,China)

机构地区：[1]东华理工大学信息工程学院,江西南昌330013 [2]华北油田第一采油厂地质研究所,河北任丘062550 [3]东北石油大学,河北秦皇岛066000 [4]东华理工大学地球物理与测控技术学院,江西南昌330013

出　　处：《Applied Geophysics》2023年第2期176-185,241,共11页应用地球物理（英文版）

基　　金：supported by the Open Fund project of Jiangxi Research Center of Nuclear Geoscience Data Science and Systems Engineering Technology“Research on intelligent recognition method of low-order fault based on V-net deep learning architecture”(JETRCNGDSS202205);“Study on the method of identifying the superior reservoir of tight sandstone based on depth learning”(JETRCNGDSS202103);School-level project of the East China University of Technology“Study on the method of identifying low-order faults with geological big data”(DHBK2019222);the Ministry of Education 2021 the first batch of industry-university collaboration projects(202101185011).

摘　　要：现有的地震资料提频方法大部分都有各自的局限性,根据已有方法的优缺点,本文尝试将深度学习技术应用到提高地震资料分辨率中。首先,在UNet深度学习方法的基础上,井震结合,以测井声波时差和密度曲线建立合成地震记录,以井上合成地震记录为标签,以井旁地震道数据为输入数据,建立井旁地震道数据与井上合成地震记录的训练模型,用来提高地震资料的中高频信息;其次,利用GRU实现原始地震记录中低频趋势的保留,将UNet和GRU结果组合在一起,实现既提高了中高频信息又保护了地震数据中的低频信息;然后开展模型训练,将模型应用到三维地震数据体上开展计算,提高地震资料分辨率。相对以往方法,提取出的信息更加丰富。通过理论模型和实际数据应用,表明本文方法在提高叠后地震资料分辨率方面有效。Most existing seismic data frequency enhancement methods have limitations.Given the advantages and disadvantages of these methods,this study attempts to apply deep learning technology to improve seismic data resolution.First,on the basis of the UNet deep learning method,which combines well-logging and seismic data,a synthetic seismic record is established with logging acoustic data and density,the borehole synthetic seismic record is labeled,and the borehole seismic trace data are taken as the input data.The training model of the borehole seismic trace data and the borehole synthetic seismic record is established to improve the medium-and high-frequency information in the seismic data.Second,the gate recurrent unit(GRU)is used to retain the low-frequency trend in the original seismic record,and the UNet and GRU results are combined to improve the medium-and high-frequency information while preserving the low-frequency information in the seismic data.Then,model training is performed,the model is applied to the three-dimensional seismic data volume for calculation,and the seismic data resolution is improved.The information extracted using our method is more abundant than that extracted using previous methods.The application of a theoretical model and actual field data shows that our method is effective in improving the resolution of poststack seismic data.

关 键 词：叠后地震数据 测井数据 提高分辨率 深度学习 UNet GRU 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] P631.443[自动化与计算机技术—控制科学与工程]