MULTI-TASK NEURAL NETWORK FOR SALT MODEL BUILDING

    公开(公告)号:US20240210586A1

    公开(公告)日:2024-06-27

    申请号:US18557715

    申请日:2022-03-24

    Inventor: Ruichao YE

    CPC classification number: G01V1/301 G01V1/345 G01V2210/66

    Abstract: A method and a system for a multi-task neural network for salt model building is disclosed. Imaging salt in the subsurface may be challenging because salt may be associated with strong diffraction and poor focused image, thereby making it difficult to interpret sediments underneath salt body or near salt flanks. To better image salt in the subsurface, the method and system trains, in combination, multiple aspects related to the subsurface, one of which is the target salt feature, in order to generate a salt feature model. The multiple aspects may include the target salt feature, such as the predicted salt mask, and at least one other salt feature, and one or more subsurface features, such as reconstruction of the input image and P-wave velocity. Thus, the salt model may better image salt, thereby making the seismic migration image more focused and easier to identify geological structures.

    METHODS FOR ACCELERATED DEVELOPMENT PLANNING OPTIMIZATION USING MACHINE LEARNING FOR UNCONVENTIONAL OIL AND GAS RESOURCES

    公开(公告)号:US20240192646A1

    公开(公告)日:2024-06-13

    申请号:US18555098

    申请日:2022-02-03

    CPC classification number: G05B13/0265

    Abstract: Methods for analyzing subsurface process data in order to perform one or more subsurface operations in a subsurface are provided. Generating subsurface models is typically a long and laborious process in which subsurface process data is analyzed in order to generate the subsurface models. In contrast, work in generating the subsurface models may be front-loaded by first using a physics simulator in order to generate a training set of subsurface forward models, and then performing machine learning using the training set to generate one or more proxy models, such as a forward proxy model and an inverse proxy model. The machine learning may be constrained using physics-based rules to better converge on the proxy models. In this way, the already-trained inverse proxy model may input the subsurface process data in order to generate potential inverse models, which may then be used to perform subsurface operations in the subsurface.

    Method for performing well performance diagnostics

    公开(公告)号:US12001762B2

    公开(公告)日:2024-06-04

    申请号:US16720195

    申请日:2019-12-19

    CPC classification number: G06F30/13 G06N5/04

    Abstract: The methods disclosed herein are directed to an automated method for monitoring performance of a well in a hydrocarbon reservoir for continuous monitoring of well test production data for a plurality of well system performance parameters, trending actual performance parameter deviations from a well system model, and determining most probable root cause(s) of the performance parameter deviations based on the trend of the deviations of a plurality of parameters for an outflow component of a well performance model and a plurality of parameters inflow component of a well performance model. The method automatically notifies an operator of detected root causes of the performance degradation, and further may perform corrective action in the well system based on at least one root cause of the deviation determined by the well performance model.

    Systems and methods for renewable fuels

    公开(公告)号:US11981872B2

    公开(公告)日:2024-05-14

    申请号:US18210878

    申请日:2023-06-16

    CPC classification number: C10G47/20 C10G67/00 C10G2300/1014 C10G2300/30

    Abstract: This application relates to production of renewable fuels, including a method of producing renewable fuels. The method comprises hydrotreating a biofeedstock by contacting reactants comprising a combined feedstock and hydrogen with a hydrotreating catalyst to produce normal paraffins. The combined feedstock comprises a biofeedstock and an additional feedstock. The biofeedstock has about 10% or more of each of metals, phosphorous, and chlorophyll than the additional feedstock. The biofeedstock comprises the metals in an amount of about 300 parts per million (“ppm”) or less, the phosphorous in an amount of about 300 ppm or less, and the chlorophyll in an amount of about 50 ppm or less. The method further comprises isomerizing at least a portion of the normal paraffins to produce branched paraffins in an isomerization effluent.

    Process and system to make olefin epoxides

    公开(公告)号:US11919876B2

    公开(公告)日:2024-03-05

    申请号:US17597888

    申请日:2020-06-30

    CPC classification number: C07D301/19

    Abstract: Processes and systems for producing olefin epoxides with three or more carbon atoms by oxidation of the corresponding branched hydrocarbons using oxygen are disclosed. An example process for producing olefin epoxides may include oxidizing a branched alkane to produce at least an organic hydroperoxide. The example process may further include epoxidizing a branched alkene by a catalytic reaction with least a portion of the organic hydroperoxide to produce at least an olefin epoxide and an alcohol. The example process may further include converting at least a portion of the alcohol to either additional branched alkane and/or additional branched alkene.

Patent Agency Ranking