OPTIMIZING HYDROCARBON RECOVERY THROUGH INTEGRATED UTILIZATION OF GEOMECHANICS AND INJECTION/PRODUCTION USING MACHINE LEARNING

    公开(公告)号:US20230272711A1

    公开(公告)日:2023-08-31

    申请号:US17577463

    申请日:2022-01-18

    发明人: Cenk Temizel

    IPC分类号: E21B49/00 E21B43/26 E21B47/06

    摘要: Systems and methods include a computer-implemented method for optimized injection/production and placement of wells. Stress change correlations are received over space and time for injection/production of fluids to/from a reservoir. A stress distribution of the reservoir is determined using reservoir geomechanical modeling tools and stress change correlations. Fracture growth/propagation behavior for the reservoir is determined using fracture modeling software and geomechanical properties for optimizing treatment. Fracture design and orientation needed for optimum recovery of hydrocarbons are determined by analyzing relationships between fluid injection/withdrawal and geomechanical changes and stress distribution, reservoir geomechanical, and flow characteristics. Changes in the stress distribution in the reservoir are determined through injection/production of fluids. An optimized injection/production and placement of wells are determined using the changes in the stress distribution and the fracture design and orientation. An optimum stress distribution for placement of new wells is determined using the optimized injection/production and placement of wells.

    ESTIMATING PRODUCTIVITY AND ESTIMATED ULTIMATE RECOVERY (EUR) OF UNCONVENTIONAL WELLS THROUGH SPATIAL-PERFORMANCE RELATIONSHIP USING MACHINE LEARNING

    公开(公告)号:US20240102371A1

    公开(公告)日:2024-03-28

    申请号:US17951541

    申请日:2022-09-23

    IPC分类号: E21B43/16

    摘要: Systems and methods include an importance that each of the attributes and features of the well data has on machine learning models. Well data is collected for each well in an unconventional field, including attributes and features of basin data, completion data, and production data. Spatial features are generated for each well in different regions. A combined well features dataset is generated. The dataset maps the well data to the spatial features for each well in the different regions. A training dataset and a testing dataset are generated by splitting the combined dataset. A machine learning model is trained using cross-validation and tuning on the training dataset to predict estimated ultimate recovery (EUR). The performance of a machine learning (EUR) model is evaluated with respect to different regression metrics. An importance that each of the attributes and features of the well data has on machine learning models is determined.

    ESTIMATED ULTIMATE RECOVERY FORECASTING IN UNCONVENTIONAL RESERVOIRS BASED ON FLOW CAPACITY

    公开(公告)号:US20220372873A1

    公开(公告)日:2022-11-24

    申请号:US17328735

    申请日:2021-05-24

    IPC分类号: E21B49/08 E21B47/10

    摘要: Embodiments herein relate to a technique that may include identifying historical data related to at least one remote well. The technique may further include identifying, based on the historical data, a correlation between gas flow capacity and estimated ultimate recovery (EUR) of the at least one other well. The technique may further include identifying gas flow capacity of a well. The technique may further include predicting, based on the gas flow capacity of the well and the identified correlation between gas flow capacity and EUR of the at least one other well, EUR of the well. The technique may further include operating the well based on the predicted EUR. Other embodiments may be described or claimed.