公开(公告)号：US10997705B2

公开(公告)日：2021-05-04

申请号：US16601818

申请日：2019-10-15

Applicant: Chevron U.S.A. Inc.

Inventor： Bo Gong ,  Dustin J. Keele ,  Emmanuel Toumelin ,  Simon Clinch

IPC: G06T7/00 ,  G06N20/00 ,  G06N3/08

Abstract: A method is described for ways to generate a Fraction of Sand (Fsand) estimate and net-to-gross (NTG) estimate of sand in a formation using a machine-learning algorithm such as a neural network based on borehole image logs. The method may use the Fsand and other information to estimate hydrocarbons in place in a subsurface formation. The method may be executed by a computer system.

公开(公告)号：US10996364B2

公开(公告)日：2021-05-04

申请号：US15948702

申请日：2018-04-09

Applicant: Chevron U.S.A. Inc.

Inventor： Haijing Wang ,  Hanming Wang ,  Emmanuel Toumelin

IPC: G01V3/20 ,  G01V3/32 ,  G01V3/38 ,  G01N27/02 ,  G01N15/08 ,  G01N33/24

Abstract: A method for determining water-filled porosity and water salinity in a well includes obtaining complex dielectric permittivity of earth formations, either from dielectric measurements representative of well cores, or from dielectric well logs; selecting a dielectric mixing law for the index number m; plotting a m-th root of complex dielectric permittivity at a specified frequency in the complex domain, wherein m is an index number; determining a matrix permittivity, a water salinity, and a water-filled porosity based on the complex dielectric permittivity and the dielectric mixing law; and displaying the water salinity and the water-filled porosity.