Building scalable geological property models using machine learning algorithms

    公开(公告)号:US12189075B2

    公开(公告)日:2025-01-07

    申请号:US17585441

    申请日:2019-12-03

    Abstract: A method of predicting rock properties at a selectable scale is provided, including receiving coordinates of locations of respective sample points, receiving measurement data associated with measurements or measurement interpretations for each sample point, receiving for each sample point a scale that indicates the scale used to obtain the measurements and/or measurement interpretations, wherein different scales are received for different sample points. A deep neural network (DNN) is trained by applying the received coordinates, measurement data, and scale associated with each sample point and associating the sample point with a rock property as a function of the coordinates, measurement data, and scale applied for the sample point. The DNN is configured to generate rock property data for a received request point having coordinates and a selectable scale, wherein the rock property data is determined for the request point as a function of the coordinates and the selectable scale.

    GLOBAL GRID BUILDING IN REVERSE FAULTED AREAS BY AN OPTIMIZED UNFAULTING METHOD
    16.
    发明申请
    GLOBAL GRID BUILDING IN REVERSE FAULTED AREAS BY AN OPTIMIZED UNFAULTING METHOD 有权
    通过优化的不均匀方法在反向故障区域中的全球网格建筑

    公开(公告)号:US20160116636A1

    公开(公告)日:2016-04-28

    申请号:US14892470

    申请日:2013-09-03

    CPC classification number: G01V99/005 G06F17/30336 G06F17/5009 G06T17/05

    Abstract: A method to generate a global grid may include storing at least one data structure representing a plurality of fault blocks associated with one or more faults in a geographic formation; selecting two fault blocks associated with a fault of the one or more faults; changing the position of a first of the two fault blocks in the at least one data structure representative of a shift of the first fault block towards the other fault block of the two fault blocks to position the center of gravity of a fault boundary of the first fault block with the center of gravity of a fault boundary of the other fault block; aligning the first fault block with the other fault block according to a permitted level of conflict between fault blocks; and updating the at least one data structure to indicate a merging of the two selected fault blocks.

    Abstract translation: 生成全局网格的方法可以包括存储表示与地理地层中的一个或多个故障相关联的多个故障块的至少一个数据结构; 选择与一个或多个故障故障相关联的两个故障块; 将所述至少一个数据结构中的所述两个故障块中的第一个故障块的位置改变为代表所述第一故障块向所述两个故障块的另一个故障块的移位,以将所述第一故障块的故障边界的重心定位在所述第一故障块 故障块与其他故障块的故障边界的重心; 根据允许的故障块之间的冲突等级,将第一个故障块与另一个故障块对齐; 以及更新所述至少一个数据结构以指示所述两个所选故障块的合并。

    RESERVOIR TURNING BANDS SIMULATION WITH DISTRIBUTED COMPUTING

    公开(公告)号:US20230213685A1

    公开(公告)日:2023-07-06

    申请号:US17646705

    申请日:2021-12-31

    CPC classification number: G01V99/005 G06F30/20 G06F2111/08

    Abstract: Some implementations relate to a method for parallelizing, by a geological data system, operations of a geostatistical simulation for a well data set via a plurality of processing elements (PEs). The method may include determining a reservoir area for the well data set. The method may include determining a set of turning band lines for the reservoir area. The method may include dividing the reservoir area into a plurality of tiles, each tile including a respective subset of the set of turning band lines. The method may include assigning at least one of the tiles to each of the PEs. The method may include determining, in parallel for each tile, intermediate results with respect to each respective subset of turning band lines. The method may include aggregating the intermediate results to form a final result of the geostatistical simulation.

Patent Agency Ranking