公开(公告)号：US11921256B2

公开(公告)日：2024-03-05

申请号：US17219663

申请日：2021-03-31

Applicant: CHEVRON U.S.A. INC.

Inventor： Larry A. Bowden, Jr. ,  Lokendra Jain ,  Irina V. Prestwood

IPC: G01V99/00 ,  G06F17/13 ,  G06F30/27 ,  G06F30/28 ,  G06N3/02 ,  G06F111/04 ,  G06F113/08

CPC classification number: G01V99/005 ,  G06F17/13 ,  G06F30/27 ,  G06F30/28 ,  G06N3/02 ,  G06F2111/04 ,  G06F2113/08

Abstract: Differential equations defining physics of a reservoir are modeled as a neural network. Measured data for the reservoir is used as boundary condition to calculate the different equation parameters. The result is a neural ordinary differential equation network that models reservoir characteristics (e.g., inter-well connectivities, response times for injection wells and production wells) using physics that are encoded into the network. The neural ordinary differential equation network provides a solution for the reservoir that is constrained by the physics of the reservoir.

公开(公告)号：US20220317332A1

公开(公告)日：2022-10-06

申请号：US17219663

申请日：2021-03-31

Applicant: CHEVRON U.S.A. INC.

Inventor： Larry A. Bowden, Jr. ,  Lokendra Jain ,  Irina V. Prestwood

IPC: G01V99/00 ,  G06F30/28 ,  G06F30/27 ,  G06F17/13 ,  G06N3/02

Abstract: Differential equations defining physics of a reservoir are modeled as a neural network. Measured data for the reservoir is used as boundary condition to calculate the different equation parameters. The result is a neural ordinary differential equation network that models reservoir characteristics (e.g., inter-well connectivities, response times for injection wells and production wells) using physics that are encoded into the network. The neural ordinary differential equation network provides a solution for the reservoir that is constrained by the physics of the reservoir.