中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

4 records (took 0.011 seconds)

    RESERVOIR CHARACTERIZATION USING MACHINE-LEARNING TECHNIQUES
    1.
    发明申请
    RESERVOIR CHARACTERIZATION USING MACHINE-LEARNING TECHNIQUES 有权

    公开(公告)号：US20220206177A1

    公开(公告)日：2022-06-30

    申请号：US17136838

    申请日：2020-12-29

    Applicant: Landmark Graphics Corporation

    Inventor： Kalyan Saikia ,  Samiran Roy

    IPC: G01V1/30 ,  G06N20/00 ,  G06N5/04

    Abstract: A system can determine a location for future wells using machine-learning techniques. The system can receive seismic data about a subterranean formation and may determine a set of seismic attributes from the seismic data. The system can block the set of seismic attributes into a set of blocked seismic attributes by distributing the set of seismic attributes onto a geo-cellular grid representative of the subterranean formation. The system can apply a trained machine-learning model to the set of blocked seismic attributes to generate a composite seismic parameter. The system can distribute the composite seismic parameter in the subterranean formation to characterize formation locations based on a predicted presence of hydrocarbons.

    Reservoir characterization using machine-learning techniques
    2.
    发明授权
    Reservoir characterization using machine-learning techniques 有权

    公开(公告)号：US11703608B2

    公开(公告)日：2023-07-18

    申请号：US17136838

    申请日：2020-12-29

    Applicant: Landmark Graphics Corporation

    Inventor： Kalyan Saikia ,  Samiran Roy

    IPC: G01V1/30 ,  G06N5/04 ,  G06N20/00

    CPC classification number: G01V1/307 ,  G06N5/04 ,  G06N20/00 ,  G01V2210/63

    Abstract: A system can determine a location for future wells using machine-learning techniques. The system can receive seismic data about a subterranean formation and may determine a set of seismic attributes from the seismic data. The system can block the set of seismic attributes into a set of blocked seismic attributes by distributing the set of seismic attributes onto a geo-cellular grid representative of the subterranean formation. The system can apply a trained machine-learning model to the set of blocked seismic attributes to generate a composite seismic parameter. The system can distribute the composite seismic parameter in the subterranean formation to characterize formation locations based on a predicted presence of hydrocarbons.

    Probabilistic Methodology for Real Time Drilling
    4.
    发明申请
    Probabilistic Methodology for Real Time Drilling 审中-公开
    实时钻井概率法

    公开(公告)号：US20160145991A1

    公开(公告)日：2016-05-26

    申请号：US14891315

    申请日：2013-08-13

    Applicant: LANDMARK GRAPHICS CORPORATION

    Inventor： Jeffrey Marc Yarus ,  Rae Mohan Srivastava ,  Kalyan Saikia ,  Jordan Michael Yarus

    IPC: E21B44/00 ,  G06N7/00 ,  E21B49/00 ,  G05B13/04 ,  E21B7/04 ,  E21B47/022

    CPC classification number: E21B44/00 ,  E21B7/04 ,  E21B47/02 ,  E21B47/022 ,  E21B49/003 ,  G05B13/04 ,  G06N7/005

    Abstract: The disclosed embodiments include a method, apparatus, and computer program product configured to provide a probabilistic approach for real time drilling. In particular, the disclosed embodiments are configured to obtain real-time data gathered during the drilling operation to update a probability model of a formation that is used in determining whether to alter a direction of a drill path. The disclosed embodiments may be configured to provide a notification to a user indicating or suggesting that certain adjustments be made to the drill path based on the updated probability model. Additionally, the disclosed embodiments may be configured to automatically make the adjustments to the drill path based on the updated probability model.

    Abstract translation: 所公开的实施例包括被配置为提供用于实时钻孔的概率方法的方法，装置和计算机程序产品。 特别地，所公开的实施例被配置为获得在钻井操作期间收集的实时数据，以更新用于确定是否改变钻孔路径的方向的地层的概率模型。 所公开的实施例可以被配置为向用户提供指示或建议基于更新的概率模型对钻孔路径进行某些调整的通知。 另外，所公开的实施例可以被配置为基于更新的概率模型自动地对钻孔路径进行调整。

Patent Agency Ranking