# US 2022/0018983 A1 · Method and device for determining sonic slowness

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0018983 A1
- Document ID: US20220018983A1
- Status: Published application
- Kind: A1
- Application number: 17/250,941
- Filed: 2019-10-01
- Published: 2022-01-20
- Earliest claimed: 2018-10-01
- Assignees: Schlumberger Technology Corporation
- Applicants: Schlumberger Technology Corporation
- Inventors: Bassem Khadhraoui; Lu Duc Duong Lam; Ridvan Akkurt; Hiroaki Yamamoto; Erik Wielemaker; Saad Kisra
- Web page: https://patentgrep.com/patent/US20220018983A1

## CPC

- G01V 1/303: {for determining velocity profiles or travel times}
- G01V 1/42: using generators in one well and receivers elsewhere or vice versa (G01V1/52 takes precedence)
- G01V 1/345: {Visualisation of seismic data or attributes, e.g. in 3D cubes}
- G01V 1/50: Analysing data
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G01V 2210/6222: Velocity; travel time
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Sonic logging data including a sonic waveform associated with a plurality of shot gathers is accessed. A transformation operator is applied to the sonic logging data to provide a transformed sonic image, the transformation operator including at least one of a short time average long time average (STA/LTA) operator, a phase shift operator, and a deconvolution operator. A machine learning process is performed using the transformed sonic image to determine a sonic slowness associated with the sonic logging data. The sonic slowness is provided as an output.

## Claims

### Claim 1

A method for determining sonic slowness, comprising:
accessing sonic logging data including a sonic waveform associated with a plurality of shot gathers;
applying a transformation operator to the sonic logging data to provide a transformed sonic image, the transformation operator including at least one of a short time average long time average (STA/LTA) operator, a phase shift operator, and a deconvolution operator;
performing a machine learning process using the transformed sonic image to determine a sonic slowness associated with the sonic logging data; and
providing the sonic slowness as an output.

### Claim 2 (depends on 1)

The method of claim 1, wherein the sonic logging data includes a shot gather of a monopole waveform, and the transformation operator includes the STA/LTA operator.

### Claim 3 (depends on 1)

The method of claim 1, wherein the sonic logging data includes a shot gather of a dipole waveform, and the transformation operator includes the phase shift operator.

### Claim 4 (depends on 1)

The method of claim 1, wherein the sonic logging data includes a two-dimensional image, and the transformation includes the deconvolution operator.

### Claim 5 (depends on 1)

The method of claim 1, wherein the sonic logging data includes a three-dimensional image, and the transformation includes the deconvolution operator.

### Claim 6 (depends on 1)

The method of claim 1, wherein the machine learning process includes a convolutional neural network.

### Claim 7 (depends on 1)

The method of claim 1, wherein the determined sonic slowness includes at least one of a slowness of a compressional wave, a slowness of a shear wave, a slowness of a Stoneley wave, a slowness of a leaky-P wave, a slowness of a Raleigh wave, and a slowness of a pseudo-Raleigh wave.

### Claim 8 (depends on 1)

The method of claim 1, wherein the providing includes displaying the sonic slowness.

### Claim 9 (depends on 8)

The method of claim 8, wherein the providing includes displaying the sonic slowness as a function of depth.

### Claim 10

An apparatus, comprising:
an interface configured to obtain sonic logging data including a sonic waveform associated with a plurality of shot gathers;
a memory configured to store computer executable instructions; and
a processor operatively coupled to the interface and the memory, the processor being configured to execute the instructions and cause the apparatus to:
apply a transformation operator to the sonic logging data to provide a transformed sonic image, the transformation operator including at least one of a short time average long time average (STA/LTA) operator, a phase shift operator, and a deconvolution operator;
perform a machine learning process using the transformed sonic image to determine a sonic slowness associated with the sonic logging data; and
provide the sonic slowness as an output.

### Claim 11 (depends on 10)

The apparatus of claim 10, wherein the sonic logging data includes a shot gather of a monopole waveform, and the transformation operator includes the STA/LTA operator.

### Claim 12 (depends on 10)

The apparatus of claim 10, wherein the sonic logging data includes a shot gather of a dipole waveform, and the transformation operator includes the phase shift operator.

### Claim 13 (depends on 10)

The apparatus of claim 10, wherein the sonic logging data includes a two-dimensional image, and the transformation includes the deconvolution operator.

### Claim 14 (depends on 10)

The apparatus of claim 10, wherein the sonic logging data includes a three-dimensional image, and the transformation includes the deconvolution operator.

### Claim 15 (depends on 10)

The apparatus of claim 10, wherein the machine learning process includes a convolutional neural network.

### Claim 16 (depends on 10)

The apparatus of claim 10, wherein the determined sonic slowness includes at least one of a slowness of a compressional wave, a slowness of a shear wave, and a slowness of a Stoneley wave.

### Claim 17 (depends on 10)

The apparatus of claim 10, wherein the apparatus includes a display configured to display the sonic slowness.

### Claim 18 (depends on 17)

The apparatus of claim 17, wherein the display is configured to display the sonic slowness as a function of depth.

### Claim 19

A method for training a machine learning process, comprising:
accessing a plurality of sonic logging data including sonic waveforms associated with a plurality of shot gathers and a sonic slowness; and
training a database of the machine learning process using the sonic logging data as a training input and the sonic slowness as a training output.

### Claim 20 (depends on 19)

The method of claim 19, further comprising applying a transformation operator to the sonic logging data before the training step, the transformation operator including at least one of a short time average long time average (STA/LTA) operator, a phase shift operator, and a deconvolution operator.
