Invention Grant
- Patent Title: Method for predicting subsurface features from seismic using deep learning dimensionality reduction for segmentation
-
Application No.: US17275302Application Date: 2019-09-10
-
Publication No.: US11808906B2Publication Date: 2023-11-07
- Inventor: Donald Paul Griffith , Sam Ahmad Zamanian , Russell David Potter
- Applicant: SHELL OIL COMPANY
- Applicant Address: US TX Houston
- Assignee: SHELL USA, INC.
- Current Assignee: SHELL USA, INC.
- Current Assignee Address: US TX Houston
- Agency: SHELL USA, INC.
- International Application: PCT/EP2019/074081 2019.09.10
- International Announcement: WO2020/053197A 2020.03.19
- Date entered country: 2021-03-11
- Main IPC: G01V1/30
- IPC: G01V1/30 ; G06N3/084
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.
Public/Granted literature
Information query
