Patent · US Active

Training data for machine learning seismic inversion

US12130398B2 · kind B2 · utility

0Cited by

1References

18Claims

0Family size

Assignee

CHEVRON U.S.A. INC. · US

Inventors

Prasenjit Roy · Houston, US
Yang Zhang · San Diego, US
Xinfa Zhu · Dallas, US
Reynaldo Cardona · Houston, US
Yong Hua · Lone Pine, CA
Kun Fu · Los Angeles, US
Bassel Mouloud Almoughraby · Spring, US

Key dates

Filing date	Feb 15, 2022
Grant date	Oct 29, 2024
Priority date	—
Expiry date	Apr 7, 2043

Classification

Technology area (CPC G)Physics
CPC primaryG06F2218/08
WIPO fieldMeasurement
WIPO sectorInstruments

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.