# US 2009/0276157 A1 · System and method for interpretation of well data

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

- Number: US 2009/0276157 A1
- Document ID: US20090276157A1
- Status: Published application
- Kind: A1
- Application number: 12/113,821
- Filed: 2008-05-01
- Published: 2009-11-05
- Earliest claimed: 2008-05-01
- Assignees: Chevron U.S.A. Inc.
- Inventors: David A. Wilkinson; Tina Yu
- Web page: https://patentgrep.com/patent/US20090276157A1

## CPC

- G01V 11/00: Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)

## Abstract

Well log data is assigned depositional labels by a soft computing method. A model is trained on an expert-interpreted well log by segmenting, assigning fuzzy symbols to the segments, and calculating attribute values for units labeled by the expert. From these values, classifiers are trained for each of a number of depositional types. Finally, a model is developed for translating fuzzy symbols into depositional labels. Once trained, the model is applied to well log data.

## Claims

### Claim 1

A method of interpreting well log data indicative of physical attributes of a portion of a subterranean formation comprising:
partitioning the well log data into segments, each segment representing a respective contiguous portion of the extent of the logged well;
defining a membership function for each segment, the membership function defining a degree to which each segment belongs to a defined set; and
determining, based on attribute values derived from previously interpreted depositional units, and the membership functions, a depositional type for each segment.

### Claim 2 (depends on 1)

A method as in claim 1, wherein the partitioning further comprises applying at least one variation criterion to the well log data such that each segment represents data varying from neighboring data by an amount less than the variation criterion.

### Claim 3 (depends on 1)

A method as in claim 1, wherein, subsequent to the partitioning, the segments are compared to a set of segments produced by a human log data interpreter interpreting the same well log data, and differences in boundaries in the set of segments produced by the human log data interpreter are adjusted on the basis of the comparison.

### Claim 4 (depends on 1)

A method as in claim 1, wherein the previously interpreted depositional units are previously interpreted by a human log data interpreter.

### Claim 5 (depends on 1)

A method as in claim 1, wherein the previously interpreted depositional units are previously interpreted by an expert system.

### Claim 6 (depends on 1)

A method as in claim 1, wherein, for each segment, a value of the data is set equal to an average value of the data for the segment.

### Claim 7 (depends on 1)

A method as in claim 1, wherein the previously interpreted depositional units are from a region having a same depositional environment as the subterranean formation.

### Claim 8 (depends on 1)

A method as in claim 1, wherein the well log data are gamma ray data.

### Claim 9 (depends on 8)

A method as in claim 8, further comprising, converting the gamma ray data to shale volume data.

### Claim 10 (depends on 9)

A method as in claim 9, wherein the shale volume data are represented as a series of numerical values Vsh=s1, s2, . . . , si, where si is an average of the data within the ith segment.

### Claim 11

A system for automated interpretation of well log data indicative of physical attributes of a portion of a subterranean formation comprising:
a data storage device, configured and arranged to store the well log data;
a processor, configured and arranged to execute machine executable instructions to partition the well log data into segments, each segment representing a respective contiguous portion of the extent of the logged well, to define a membership function for each segment, the membership function defining a degree to which each segment belongs to a defined set, and to determine, based on attribute values derived from previously interpreted depositional units, and the membership functions, a depositional type for each segment.

### Claim 12 (depends on 11)

A system as in claim 11, further including an input device, configured and arranged for a user to input adjustments to boundaries of the segments.

### Claim 13 (depends on 11)

A system as in claim 11, further including machine readable data including the previously interpreted depositional units, and wherein the previously interpreted depositional units comprises human-interpreted depositional units.

### Claim 14 (depends on 11)

A system as in claim 11, wherein the processor is further configured and arranged to partition the well log data into segments by applying at least one variation criterion to the well log data such that each segment represents data varying from neighboring data by an amount less than the variation criterion.

### Claim 15 (depends on 11)

A system as in claim 11, further comprising a probe, constructed and arranged to measure the physical attributes of the portion of the subterranean formation and to transmit the measured attributes to the data storage device.
