公开(公告)号：US20230258838A1

公开(公告)日：2023-08-17

申请号：US17672486

申请日：2022-02-15

Applicant: Chevron U.S.A. Inc.

Inventor： Prasenjit Roy ,  Yang Zhang ,  Xinfa Zhu ,  Reynaldo Cardona ,  Yong Hua ,  Kun Fu ,  Bassel Mouloud Almoughraby

IPC: G01V1/50 ,  G01V1/46 ,  G01V1/00 ,  G06K9/62

CPC classification number: G01V1/50 ,  G01V1/46 ,  G01V1/003 ,  G06K9/6256 ,  G01V2210/1299 ,  G01V2210/62

Abstract: Well data (e.g., well log) may be divided into multiple segments, and different samplings of data in the individual segments may be performed to increase the amount of data that is used to train a seismic inversion model. Synthetic well data may be generated from real well data to increase the amount of well data from which sampling is performed.

公开(公告)号：US20210311223A1

公开(公告)日：2021-10-07

申请号：US17223364

申请日：2021-04-06

Applicant: Chevron U.S.A. Inc.

Inventor： Prasenjit Roy ,  Xinfa Zhu

IPC: G01V1/50 ,  G01V1/30 ,  G01V1/28 ,  G06N20/00

Abstract: A method is described for inverting seismic data including obtaining well logs representative of subsurface volumes of interest; generating an amplitude variation with angle (AVA) database from the well logs by seismic modeling, wherein the seismic modeling is performed a plurality of times for all combinations of fluid substitutions of brine, oil, and gas and low porosity, mid-porosity, and high porosity; generating a trained AVA model using the AVA database; obtaining a seismic dataset; calibrating the seismic dataset; computing seismic attributes for the calibrated seismic dataset using statistics for AVA classification; and generating direct hydrocarbon indicators as a function of position in the subsurface volume of interest by applying the trained AVA model to the seismic attributes. The method is executed by a computer system.

公开(公告)号：US11796705B2

公开(公告)日：2023-10-24

申请号：US17223364

申请日：2021-04-06

Applicant: Chevron U.S.A. Inc.

Inventor： Prasenjit Roy ,  Xinfa Zhu

IPC: G01V1/50 ,  G06N20/00 ,  G01V1/28 ,  G01V1/30

CPC classification number: G01V1/50 ,  G01V1/282 ,  G01V1/307 ,  G06N20/00 ,  G01V2210/632

Abstract: A method is described for inverting seismic data including obtaining well logs representative of subsurface volumes of interest; generating an amplitude variation with angle (AVA) database from the well logs by seismic modeling, wherein the seismic modeling is performed a plurality of times for all combinations of fluid substitutions of brine, oil, and gas and low porosity, mid-porosity, and high porosity; generating a trained AVA model using the AVA database; obtaining a seismic dataset; calibrating the seismic dataset; computing seismic attributes for the calibrated seismic dataset using statistics for AVA classification; and generating direct hydrocarbon indicators as a function of position in the subsurface volume of interest by applying the trained AVA model to the seismic attributes. The method is executed by a computer system.

公开(公告)号：US12130398B2

公开(公告)日：2024-10-29

申请号：US17672486

申请日：2022-02-15

Applicant: Chevron U.S.A. Inc.

Inventor： Prasenjit Roy ,  Yang Zhang ,  Xinfa Zhu ,  Reynaldo Cardona ,  Yong Hua ,  Kun Fu ,  Bassel Mouloud Almoughraby

IPC: G01V1/48 ,  G01V1/00 ,  G01V1/46 ,  G01V1/50 ,  G06F18/214

CPC classification number: G01V1/50 ,  G01V1/003 ,  G01V1/46 ,  G06F18/214 ,  G01V2210/1299 ,  G01V2210/62

Abstract: Well data (e.g., well log) may be divided into multiple segments, and different samplings of data in the individual segments may be performed to increase the amount of data that is used to train a seismic inversion model. Synthetic well data may be generated from real well data to increase the amount of well data from which sampling is performed.