公开(公告)号：US20210223422A1

公开(公告)日：2021-07-22

申请号：US15733912

申请日：2019-04-16

Applicant: SHELL OIL COMPANY

Inventor： Donald Paul GRIFFITH ,  Sam Ahmad ZAMANIAN ,  Russell David POTTER ,  Antoine Victor Applolinaire VIAL-AUSSAVY

IPC: G01V1/28 ,  G01V1/30 ,  G06F30/27 ,  G06N3/08

Abstract: A method for producing a synthetic model for training a backpropagation-enabled process for identifying subsurface features, includes generating synthetic subsurface models with realizations of subsurface features. The synthetic subsurface models are generated by introducing at least three distinct model variations selected from geologically realistic features simulating the outcome of a geologic process, simulations of geologic processes, simulations of noise sources, and combinations thereof. Labels are applied to one or more of the subsurface features in one or more of the synthetic subsurface models. The labels and the corresponding synthetic subsurface models are imported into the backpropagation-enabled process for training.

公开(公告)号：US20210223423A1

公开(公告)日：2021-07-22

申请号：US15733920

申请日：2019-04-16

Applicant: SHELL OIL COMPANY

Inventor： Donald Paul GRIFFITH ,  Sam Ahmad ZAMANIAN ,  Russell David POTTER ,  Antoine Victor Applolinaire VIAL-AUSSAVY

IPC: G01V1/28 ,  G01V1/30 ,  G06N3/08 ,  G06F30/27

Abstract: A method for producing a synthetic model for training a backpropagation-enabled process for identifying subsurface features, includes generating noise-free synthetic subsurface models with realizations of subsurface features. The noise-free synthetic subsurface models are generated by introducing a model variation selected from geologically realistic features simulating the outcome of a geologic process, simulations of geologic processes, and combinations thereof. Labels are applied to one or more of the subsurface features in one or more of the synthetic subsurface models. A simulation of a noise source is applied to a copy of one or more of the noise-free synthetic subsurface models to produce a noise-augmented copy. The labels and the corresponding synthetic subsurface models are imported into the backpropagation-enabled process for training.

公开(公告)号：US20220113440A1

公开(公告)日：2022-04-14

申请号：US17275302

申请日：2019-09-10

Applicant: SHELL OIL COMPANY

Inventor： Donald Paul GRIFFITH ,  Sam Ahmad ZAMANIAN ,  Russell David POTTER

IPC: G01V1/30 ,  G06N3/08

Abstract: A method for training a backpropagation-enabled segmentation process is used for identifying an occurrence of a sub-surface feature. A multi-dimensional seismic data set with an input dimension of at least two is inputted into a backpropagation-enabled process. A prediction of the occurrence of the subsurface feature has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.

公开(公告)号：US20170358130A1

公开(公告)日：2017-12-14

申请号：US15524198

申请日：2015-11-03

Applicant: SHELL OIL COMPANY

Inventor： Donald Paul GRIFFITH

IPC: G06T17/05 ,  G06T11/00

CPC classification number: G06T17/05 ,  G06T11/001

Abstract: Example of systems and methods are provided for visualization of multi-dimensional geophysical data visualization. Combining several attributes from multi-dimensional geophysical data or seismic data using color modeling techniques provide for the interpretation of data more efficiently by a user. A color space is defined and multi-dimensional geophysical data attributes are created along with blending filters, such as asymmetric blending filters. Blended multi-dimensional geophysical data attribute cubes are created from the blending filters and the geophysical data attributes. The blended multi-dimensional geophysical data attributes or cubes are displayed using the defined multi-dimensional color space.

公开(公告)号：US20220113441A1

公开(公告)日：2022-04-14

申请号：US17275309

申请日：2019-09-10

Applicant: SHELL OIL COMPANY

Inventor： Donald Paul GRIFFITH ,  Sam Ahmad ZAMANIAN ,  Russell David POTTER

IPC: G01V1/30 ,  G06N3/08

Abstract: A method for training a backpropagation-enabled regression process is used for predicting values of an attribute of subsurface data. A multi-dimensional seismic data set with an input dimension of at least two is inputted into a backpropagation-enabled process. A predicted value of the attribute has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.

公开(公告)号：US20190080507A1

公开(公告)日：2019-03-14

申请号：US16191173

申请日：2018-11-14

Applicant: Shell Oil Company

Inventor： Donald Paul GRIFFITH

IPC: G06T15/50 ,  G06N3/08

Abstract: A method for visualization of multi-dimensional geophysical data involves combining several attributes from multi-dimensional geophysical data or seismic data using color modeling techniques and provides for the interpretation of data more efficiently by a user. A color space is defined and multi-dimensional geophysical data attributes are created along with blending filters, such as asymmetric blending filters. Blended multi-dimensional geophysical data attribute cubes are created from the blending filters and the geophysical data attributes by making a prediction using a deep convolutional neural network trained via a backpropagation-enabled regression process.