NOISE FILTERING METHOD FOR SEISMIC DATA

Patent №

US 5,971,095

Granted

1999-10-26

Filed 1998

Owner

SCHLUMBERGER TECHNOLOGY CORPORATION

Lab

AI components

1

ml

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

09091895

A method for filtering noise from discrete noisy seismic signals in a time interval ([1, . . . , T]) is provided. The method comprising the steps of using the noisy seismic signals for determining at least one reference channel (x(t)) for the time interval as an estimate of the noise; determining coefficients for M temporally local filters (w(i, t)), the filters forming a filter bank, and M being a number equal to or larger than two, by minimizing a cost function (J(t)) representing a measure of the error of the output of the filter bank, and applying the filter bank to at least one estimate (x(t)) to determine M filtered estimates of the noise. The filtered estimates are multipled with temporal windows (h(i, t)).

Machine learningG01V 1/364G01V 2210/324G01V 2210/3246

AI classification

Machine learning0.98
Vision0.39
AI hardware0.03
Planning0.00
Speech0.00
Evolutionary computation0.00
Natural language0.00
Knowledge representation0.00

Ownership

SCHLUMBERGER TECHNOLOGY CORPORATION

assignment · 96230136

Assignors

OZBEK, ALI

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC