公开(公告)号：US20150032426A1

公开(公告)日：2015-01-29

申请号：US13953240

申请日：2013-07-29

Applicant: Chevron U.S.A., Inc.

Inventor： Jinsong Chen ,  Gary Michael Hoversten

IPC: G01V99/00 ,  G06N7/00

CPC classification number: G01V99/005 ,  G01V1/306 ,  G01V3/38 ,  G01V11/00 ,  G01V2210/614 ,  G01V2210/6163 ,  G01V2210/6169 ,  G01V2210/622 ,  G01V2210/624 ,  G01V2210/6242 ,  G01V2210/6244 ,  G06N7/005

Abstract: A system and a method for estimating a reservoir parameter are provided. The method includes calculating a plurality of priors using a Markov random field, the plurality of priors comprising probability distributions of a plurality of litho-types; calculating posterior distributions based on the priors, the posterior distribution depending upon measured geophysical data, geophysical attributes and reservoir parameters; and determining at least a portion of litho-types in the plurality of litho-types that correlate most with the measured geophysical data.

Abstract translation: 提供了一种用于估计储层参数的系统和方法。 该方法包括使用马尔科夫随机场计算多个先验，所述多个先验包括多个光刻类型的概率分布; 基于先验计算后验分布，后验分布取决于测量的地球物理数据，地球物理属性和储层参数; 以及确定与测量的地球物理数据最相关的多个光刻类型中的至少一部分光刻类型。

公开(公告)号：US11822030B2

公开(公告)日：2023-11-21

申请号：US17654630

申请日：2022-03-14

Applicant: Chevron U.S.A. Inc.

Inventor： Jinsong Chen ,  Huafeng Liu ,  Andrey Hanan Shabelansky ,  Cory James Hoelting ,  Min Yang ,  Ying Tan ,  Maisha Lara Amaru

IPC: G01V1/34 ,  G01V1/28 ,  G06N7/01

CPC classification number: G01V1/345 ,  G01V1/282 ,  G06N7/01 ,  G01V2210/60 ,  G01V2210/74

Abstract: A method is described for seismic depth uncertainty analysis including receiving wavelet basis functions and cutoff thresholds and randomly perturbing wavelet coefficients in reduced wavelet space based on the wavelet basis functions and the cutoff thresholds to generate a plurality of random wavelet fields; receiving a reference model in a depth domain; transforming the plurality of random wavelet fields to the depth domain and combining them with the reference model to form candidate models; performing a hierarchical Bayesian modeling with Markov Chain Monte Carlo (MCMC) sampling methods using the candidate models as input to generate a plurality of realizations; and computing statistics of the plurality of realizations to estimate depth uncertainty. The method may be executed by a computer system.

公开(公告)号：US20230288605A1

公开(公告)日：2023-09-14

申请号：US17654633

申请日：2022-03-14

Applicant: Chevron U.S.A. Inc.

Inventor： Huafeng Liu ,  Andrey Hanan Shabelansky ,  Jinsong Chen

IPC: G01V99/00 ,  G01V1/30 ,  G01V1/40

CPC classification number: G01V99/005 ,  G01V1/301 ,  G01V1/40

Abstract: A method is described for estimating depth uncertainty including receiving seismic data, a reference model, and trial model realizations; generating realization gathers from the trial model realizations; generating reference gathers from the reference model; determining a reference data fit based on the reference gathers and a data fit for trial models based on the realization gathers; selecting refined models from the trial model realizations based on the reference data fit, the data fit for trial models, and a data fit tolerance criterion; and calculating depth uncertainty based on statistics of the refined models. The method may be executed by a computer system.

公开(公告)号：US20200217978A1

公开(公告)日：2020-07-09

申请号：US16724738

申请日：2019-12-23

Applicant: Chevron U.S.A. Inc. ,  The Regents of The University of California

Inventor： Jinsong Chen ,  Gary Michael Hoversten

IPC: G01V1/28 ,  G06N3/08 ,  G06N20/20 ,  G01V1/30 ,  G06F30/20 ,  G06N7/00 ,  G01V1/50 ,  G06F113/08

Abstract: A method is described for deriving high-resolution reservoir properties for a subsurface reservoir. The method may include receiving a seismic dataset; inverting the seismic dataset to generate an ensemble of coarse-scale seismic parameters, wherein the inverting may use one of Bayesian models with Markov Chain Monte Carlo (MCMC) sampling, simulated annealing, partial swarm, or analytic Bayes formulations; receiving fine-scale lithotype models; developing deep learning neural networks based on transfer learning using the fine-scale lithotype models to generate a conditional probability distribution of high-resolution reservoir parameters; generating an ensemble of high-resolution reservoir parameters using the deep learning neural network to condition the ensemble of coarse-scale seismic parameters; and displaying, on a user interface, the ensemble of high-resolution reservoir parameters. The method is executed by a computer system.

公开(公告)号：US20230288588A1

公开(公告)日：2023-09-14

申请号：US17654632

申请日：2022-03-14

Applicant: Chevron U.S.A. Inc.

Inventor： Andrey Hanan Shabelansky ,  Huafeng Liu ,  Cory James Hoelting ,  Min Yang ,  Jinsong Chen

IPC: G01V1/28 ,  G06F30/20

CPC classification number: G01V1/282 ,  G06F30/20 ,  G06F2111/08

Abstract: A method is described for stochastic modeling of seismic velocity and anisotropic parameters, including receiving 3D bounds of normal moveout velocity (Vnmo) and anisotropic parameter η; modeling 3D bounds for vertical velocity V and anisotropic parameter δ based on the 3D bounds of Vnmo and η; generating 3D model realizations of V, η, and δ within the 3D bounds; and testing detectability of each of the 3D model realizations to create a detectable subset of model realizations wherein the detectability identifies which 3D model realizations will produce images with flat migrated gathers. The method may be executed by a computer system.

公开(公告)号：US09207356B2

公开(公告)日：2015-12-08

申请号：US13953240

申请日：2013-07-29

Applicant: Chevron U.S.A., Inc.

Inventor： Jinsong Chen ,  Gary Michael Hoversten

IPC: G06G7/48 ,  G01V99/00 ,  G06N7/00 ,  G01V1/30 ,  G01V3/38 ,  G01V11/00

CPC classification number: G01V99/005 ,  G01V1/306 ,  G01V3/38 ,  G01V11/00 ,  G01V2210/614 ,  G01V2210/6163 ,  G01V2210/6169 ,  G01V2210/622 ,  G01V2210/624 ,  G01V2210/6242 ,  G01V2210/6244 ,  G06N7/005

Abstract: A system and a method for estimating a reservoir parameter are provided. The method includes calculating a plurality of priors using a Markov random field, the plurality of priors comprising probability distributions of a plurality of litho-types; calculating posterior distributions based on the priors, the posterior distribution depending upon measured geophysical data, geophysical attributes and reservoir parameters; and determining at least a portion of litho-types in the plurality of litho-types that correlate most with the measured geophysical data.

Abstract translation: 提供了一种用于估计储层参数的系统和方法。 该方法包括使用马尔科夫随机场计算多个先验，所述多个先验包括多个光刻类型的概率分布; 基于先验计算后验分布，后验分布取决于测量的地球物理数据，地球物理属性和储层参数; 以及确定与测量的地球物理数据最相关的多个光刻类型中的至少一部分光刻类型。

公开(公告)号：US20240210584A1

公开(公告)日：2024-06-27

申请号：US18069865

申请日：2022-12-21

Applicant: Chevron U.S.A. Inc.

Inventor： Ke Wang ,  Jinsong Chen ,  Yijie Zhou

IPC: G01V1/30 ,  G01V1/28 ,  G01V1/34 ,  G06N3/091

CPC classification number: G01V1/30 ,  G01V1/282 ,  G01V1/345 ,  G06N3/091

Abstract: A method is described for seismic inversion with uncertainty quantification including performing low frequency Markov Chain Monte Carlo (MCMC) processes on rock physics models to generate low frequency models (LFMs) of rock properties and training a deep neural network using the low frequency models and synthetic seismograms to generate a trained neural network. Given a seismic dataset, the trained neural network can generate a high frequency rock property model and then broad-band MCMC processes can be performed on the high frequency rock property model for uncertainty quantification. The method is executed by a computer system.

公开(公告)号：US20230288593A1

公开(公告)日：2023-09-14

申请号：US17654630

申请日：2022-03-14

Applicant: Chevron U.S.A. Inc.

Inventor： Jinsong Chen ,  Huafeng Liu ,  Andrey Hanan Shabelansky ,  Cory James Hoelting ,  Min Yang ,  Ying Tan ,  Maisha Lara Amaru

IPC: G01V1/34 ,  G01V1/28 ,  G06N7/00

CPC classification number: G01V1/345 ,  G01V1/282 ,  G06N7/005 ,  G01V2210/74 ,  G01V2210/60

Abstract: A method is described for seismic depth uncertainty analysis including receiving wavelet basis functions and cutoff thresholds and randomly perturbing wavelet coefficients in reduced wavelet space based on the wavelet basis functions and the cutoff thresholds to generate a plurality of random wavelet fields; receiving a reference model in a depth domain; transforming the plurality of random wavelet fields to the depth domain and combining them with the reference model to form candidate models; performing a hierarchical Bayesian modeling with Markov Chain Monte Carlo (MCMC) sampling methods using the candidate models as input to generate a plurality of realizations; and computing statistics of the plurality of realizations to estimate depth uncertainty. The method may be executed by a computer system.

公开(公告)号：US20230099919A1

公开(公告)日：2023-03-30

申请号：US17279375

申请日：2021-03-15

Applicant: Chevron U.S.A. Inc.

Inventor： Jinsong Chen ,  Uwe K. Albertin ,  Kurt T. Nihei ,  Sam T. Kaplan ,  Gary Michael Hoversten ,  Lin Zhang ,  Dimitri Bevc

IPC: G01V1/28 ,  G01V1/34 ,  G01V1/30

Abstract: A method is described for generating a subsurface model using stochastic full waveform inversion by receiving a seismic dataset representative of a subsurface volume of interest; performing stochastic full waveform inversion of the seismic dataset to generate a long wavelength subsurface model; and performing full waveform inversion of the seismic dataset using the long wavelength subsurface model as a starting model to generate an improved subsurface model. The method may further include performing seismic imaging of the seismic dataset using the improved subsurface model to generate a seismic image and identifying geologic features based on the seismic image. The method may be executed by a computer system.