国外测井专利  

出　　处：《国外测井技术》2025年第3期27-27,73,77,共3页World Well Logging Technology

摘　　要：公开(公告)号:WO2023102054A1 Deep learning architecture for seismic post-stack inversion用于地震叠后反演的深度学习架构摘要:A system for estimating a rock property away from a well may include one or more hardware processors configured to access acquired three-dimensional(3D)seismic data that includes seismic traces(520)from a 3D seismic survey of an area of interest.The system may also include a multi-head Convolutional Neural Network(CNN)model(522).The multi-head CNN model(522)may include a plurality of kernels of various sizes for determining spatial and temporal relationships of the captured 3D seismic data at different resolutions.The multi-head CNN model(522)may be trained to generate an estimated rock property value of a formation zone included in the area of interest,away from the well.The one or more hardware processors(322)are further configured to update a drilling program for a production system based on the estimated rock property value.The drilling program may be executed on a computing device(1000)of the production system.一种用于估计远离井的岩石特性的系统可以包括一个或多个硬件处理器,该硬件处理器被配置为访问获取的三维(3D)地震数据,该地震数据包括来自感兴趣区域的3D地震勘测的地震轨迹(520)。该系统还可以包括多头卷积神经网络(CNN)模型(522)。多头CNN模型(522)可以包括多个不同大小的内核,用于确定不同分辨率下捕获的3D地震数据的空间和时间关系。可以训练多头CNN模型(522)以生成远离井的感兴趣区域中包括的地层带的估计岩石特性值。一个或多个硬件处理器(322)进一步配置成基于估计的岩石特性值更新生产系统的钻井程序。钻井程序可以在生产系统的计算设备(1000)上执行。

关 键 词：深度学习 地震叠后反演 卷积神经网络 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]