公开(公告)号：US20190064389A1

公开(公告)日：2019-02-28

申请号：US16057356

申请日：2018-08-07

Applicant: Huseyin DENLI ,  Niranjan A. Subrahmanya

Inventor： Huseyin DENLI ,  Niranjan A. Subrahmanya

IPC: G01V99/00 ,  G06N3/08 ,  G06N3/04

Abstract: A method including: storing, in a computer memory, geophysical data obtained from a survey of a subsurface region; and extracting, with a computer, a subsurface physical property model by processing the geophysical data with one or more convolutional neural networks, which are trained to relate the geophysical data to at least one subsurface physical property consistent with geological prior information.

公开(公告)号：US20150362622A1

公开(公告)日：2015-12-17

申请号：US14693464

申请日：2015-04-22

Applicant: Huseyin Denli ,  Alex Kanevsky

Inventor： Huseyin Denli ,  Alex Kanevsky

IPC: G01V99/00

CPC classification number: G01V99/005 ,  G01V1/282 ,  G01V2210/614 ,  G01V2210/6161 ,  G01V2210/62 ,  G01V2210/675

Abstract: A method, including: obtaining an initial geophysical model; modeling a forward wavefield with viscoacoustic or viscoelastic wave equations; modeling an adjoint wavefield with adjoint viscoacoustic or adjoint viscoelastic wave equations, wherein the adjoint viscoacoustic wave equations are based on an auxiliary variable that is a function of pressure and a memory variable or the adjoint viscoelastic wave equations are based on a combination of stress and a memory variable, respectively; obtaining a gradient of a cost function based on a combination of a model of the forward wavefield and a model of the adjoint wavefield; and using the gradient of the cost function to update the initial geophysical model and obtain an updated geophysical model.

Abstract translation: 一种方法，包括：获得初始地球物理模型; 用粘弹性或粘弹性波动方程建模前向波场; 使用伴随粘声或伴随粘弹波方程建模伴随波场，其中伴随粘弹性波方程基于作为压力和记忆变量的函数的辅助变量或伴随粘弹性波方程基于压力和 记忆变量分别为 基于前向波场的模型和伴随波场的模型的组合获得成本函数的梯度; 并使用成本函数的梯度来更新初始地球物理模型并获得更新的地球物理模型。

公开(公告)号：US20170003409A1

公开(公告)日：2017-01-05

申请号：US15190222

申请日：2016-06-23

Applicant: Volkan Akcelik ,  Huseyin Denli

Inventor： Volkan Akcelik ,  Huseyin Denli

IPC: G01V1/28 ,  E21B41/00 ,  E21B49/00 ,  G01V1/30

CPC classification number: G01V1/30 ,  G01V1/28 ,  G01V1/306

Abstract: A method, including: storing, in a computer memory, seismic data acquired from a seismic survey of a subsurface region; and generating, with a computer, a final subsurface physical property model of the subsurface region by processing the seismic data with an iterative full wavefield inversion method, wherein the iterative full wavefield inversion method generates the final subsurface physical property model by iteratively applying a linear solver with a preconditioner that is generated from information from one or more previous iterations of the linear solver.

Abstract translation: 一种方法，包括：在计算机存储器中存储从地下区域的地震勘测获取的地震数据; 并通过用迭代全波场反演方法处理地震数据，通过计算机生成地下区域的最终地下物理属性模型，其中迭代全波场反演方法通过迭代应用线性求解器生成最终的地下物理属性模型 具有从线性求解器的一个或多个先前迭代的信息产生的预处理器。

公开(公告)号：US10996372B2

公开(公告)日：2021-05-04

申请号：US16057356

申请日：2018-08-07

Applicant: Huseyin Denli ,  Niranjan A. Subrahmanya

Inventor： Huseyin Denli ,  Niranjan A. Subrahmanya

IPC: G01V99/00 ,  G06N3/08 ,  G06N3/04 ,  G01V7/06 ,  G01V1/30 ,  G01V1/28 ,  G01V3/38 ,  G01V11/00

Abstract: A method including: storing, in a computer memory, geophysical data obtained from a survey of a subsurface region; and extracting, with a computer, a subsurface physical property model by processing the geophysical data with one or more convolutional neural networks, which are trained to relate the geophysical data to at least one subsurface physical property consistent with geological prior information.

公开(公告)号：US10054714B2

公开(公告)日：2018-08-21

申请号：US14693464

申请日：2015-04-22

Applicant: Huseyin Denli ,  Alex Kanevsky

Inventor： Huseyin Denli ,  Alex Kanevsky

IPC: G01V99/00 ,  G01V1/28

CPC classification number: G01V99/005 ,  G01V1/282 ,  G01V2210/614 ,  G01V2210/6161 ,  G01V2210/62 ,  G01V2210/675

Abstract: A method, including: obtaining an initial geophysical model; modeling a forward wavefield with viscoacoustic or viscoelastic wave equations; modeling an adjoint wavefield with adjoint viscoacoustic or adjoint viscoelastic wave equations, wherein the adjoint viscoacoustic wave equations are based on an auxiliary variable that is a function of pressure and a memory variable or the adjoint viscoelastic wave equations are based on a combination of stress and a memory variable, respectively; obtaining a gradient of a cost function based on a combination of a model of the forward wavefield and a model of the adjoint wavefield; and using the gradient of the cost function to update the initial geophysical model and obtain an updated geophysical model.