System and method for accelerated computation of subsurface representations

    公开(公告)号:US11604909B2

    公开(公告)日:2023-03-14

    申请号:US16706596

    申请日:2019-12-06

    Abstract: A computational stratigraphy model may be run for M mini-steps to simulate changes in a subsurface representation across M mini-steps (from 0-th subsurface representation to M-th subsurface representation), with a mini-step corresponding to a mini-time duration. The subsurface representation after individual steps may be characterized by a set of computational stratigraphy model variables. Some or all of the computational stratigraphy model variables from running of the computational stratigraphy model may be provided as input to a machine learning model. The machine learning model may predict changes to the subsurface representation over a step corresponding to a time duration longer than the mini-time duration and output a predicted subsurface representation. The subsurface representation may be updated based on the predicted subsurface representation outputted by the machine learning model. Running of the computational stratigraphy model and usage of the machine learning model may be iterated until the end of the simulation.

    NESTED MODEL SIMULATIONS TO GENERATE SUBSURFACE REPRESENTATIONS

    公开(公告)号:US20210341642A1

    公开(公告)日:2021-11-04

    申请号:US15929390

    申请日:2020-04-30

    Abstract: Process-based numerical forward stratigraphic models of different spatiotemporal scales may be nested to address subsurface characterization at different scales. Subsurface representations may be generated using an iterative loop in which subsurface representations are generated using different-scale subsurface models, compared to scale-appropriate data, and used to define boundary conditions/inputs for subsequently run subsurface models. Results from the subsurface models may be compared to one or more standards for quality control and/or for subsurface representation selection. A series of comprehensive subsurface representations may be generated, with the subsurface representations being constrained by different scales of information and physical plausible scenarios.

    COMPARISON OF WELLS USING A DISSIMILARITY MATRIX

    公开(公告)号:US20210302620A1

    公开(公告)日:2021-09-30

    申请号:US16832641

    申请日:2020-03-27

    Abstract: Well information may define subsurface configuration of different wells. Marker information defining marker positions within the wells may be obtained. A dissimilarity matrix for the wells may generated, with the element values of the dissimilarity matrix determined based on comparison of corresponding subsurface configuration of the wells. A gated dissimilarity matrix may be generated from the dissimilarity matrix based on the marker positions within the wells. The elements values of the gated dissimilarity matrix corresponding to one set of marker positions and not corresponding to the other set of marker positions may be changed. Correlation between the wells may be determined based on the gated dissimilarity matrix such that correlation exists between a marker position in one well and a marker position in another well.

    SYSTEM AND METHOD FOR ACCELERATED COMPUTATION OF SUBSURFACE REPRESENTATIONS

    公开(公告)号:US20200380390A1

    公开(公告)日:2020-12-03

    申请号:US16706596

    申请日:2019-12-06

    Abstract: A computational stratigraphy model may be run for M mini-steps to simulate changes in a subsurface representation across M mini-steps (from 0-th subsurface representation to M-th subsurface representation), with a mini-step corresponding to a mini-time duration. The subsurface representation after individual steps may be characterized by a set of computational stratigraphy model variables. Some or all of the computational stratigraphy model variables from running of the computational stratigraphy model may be provided as input to a machine learning model. The machine learning model may predict changes to the subsurface representation over a step corresponding to a time duration longer than the mini-time duration and output a predicted subsurface representation. The subsurface representation may be updated based on the predicted subsurface representation outputted by the machine learning model. Running of the computational stratigraphy model and usage of the machine learning model may be iterated until the end of the simulation.

Patent Agency Ranking