# US 12,007,518 B2 · Systems and methods for identifying type curve regions as a function of position in a region of interest

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

- Number: US 12,007,518 B2
- Document ID: US12007518B2
- Status: Granted
- Kind: B2
- Application number: 17/562,629
- Filed: 2021-12-27
- Published: 2023-06-29
- Granted: 2024-06-11
- Earliest claimed: 2021-12-27
- Assignees: Chevron U.S.A. Inc.
- Applicants: Chevron U.S.A. Inc.
- Inventors: Shane James Prochnow; Benjamin Rodolphe Cormier; Vahid Tohidi; Michelle Wan
- Web page: https://patentgrep.com/patent/US12007518B2

## CPC

- E21B 43/00: Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells (applicable only to water E03B)
- G01V 20/00: Geomodelling in general
- G01V 11/002: {Details, e.g. power supply systems for logging instruments, transmitting or recording data, specially adapted for well logging, also if the prospecting method is irrelevant (means for transmitting well survey signals E21B47/12; signal transmission systems in general G08C; transmission in general H04B)}
- G06N 20/20: Ensemble learning
- E21B 2200/22: Fuzzy logic, artificial intelligence, neural networks or the like
- G01V 2210/66: Subsurface modeling
- G01V 2210/663: Modeling production-induced effects
- E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- 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

Methods, systems, and non-transitory computer readable media for identifying type curve regions as a function of position in a region of interest are disclosed. Exemplary implementations may include: obtaining a spatial clustering model from the non-transitory storage medium; obtaining well data from the non-transitory storage medium; obtaining production parameter data from the non-transitory storage medium; and delineating each of the type curve regions in the region of interest by applying the spatial clustering model to the well data and the production parameter data.

## Claims

### Claim 1

A computer-implemented method for identifying type curve regions as a function of position in a region of interest, the computer-implemented method being implemented in a computer system that includes a physical computer processor, a non-transitory storage medium, and a display, the computer-implemented method comprising:
obtaining a spatial clustering model from the non-transitory storage medium;
obtaining well data from the non-transitory storage medium, wherein the well data includes well locations in the region of interest and corresponding productivity for the well locations;
obtaining production parameter data from the non-transitory storage medium, wherein the production parameter data includes production parameter values characterizing subsurface production features that affect reservoir productivity in the region of interest;
delineating, with the physical computer processor, each of the type curve regions in the region of interest by applying the spatial clustering model to the well data and the production parameter data, evaluating differences in types of productivity values, and identifying a target type curve region with greater distinction in mean productivity values relative to a neighboring type curve region and minimal variation in productivity values within the target type curve region;
generating, with the physical computer processor, a representation of the type curve regions as the function of the position in the region of interest using visual effects to depict geographic boundaries outlining at least some of the type curve regions delineated using the spatial clustering model; and
displaying the representation via the display.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the spatial clustering model is based on at least a ratio between a mean productivity variation between areas in the region of interest and a productivity variation within one of the areas in the region of interest.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, wherein the spatial clustering model comprises an unsupervised machine learning model, wherein the unsupervised machine learning model comprises adjustable hyperparameters.

### Claim 4 (depends on 3)

The computer-implemented method of claim 3, wherein the adjustable hyperparameters comprise a spatial weighting of one of reservoir original oil in place, porosity, geomechanics, pressure, temperature, permeability, mineralogy, stratigraphic beds, depositional facies, diagenic facies, natural fracture intensity, pore saturation, reservoir property, position, reservoir thickness, or a number of the type curve regions” in order to provide appropriate antecedence basis.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein the production parameter data comprise one of average porosity, pore saturation, mineralogy, lithofacies, geomechanical properties, organic richness, pore pressure, quartz normalized, volume water, argillic bed count, bed thickness, gross thickness, gross perforation length, fracture fluid intensity, proppant intensity, permeability, mineralogy, stratigraphic beds, depositional facies, diagenic facies, natural fracture intensity, pore saturation, reservoir property, or productivity.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the types of productivity values comprise mean productivity values and percentile P10-P90 values” in order to provide appropriate antecedence basis.

### Claim 7

A system comprising:
non-transitory storage medium;
a display; and
a physical computer processor configured by machine-readable instructions to:
obtain a spatial clustering model from the non-transitory storage medium;
obtain well data from the non-transitory storage medium, wherein the well data includes well locations in a region of interest and corresponding productivity for the well locations;
obtain production parameter data from the non-transitory storage medium, wherein the production parameter data includes production parameter values characterizing subsurface production features that affect reservoir productivity in the region of interest;
delineate, with the physical computer processor, each of the type curve regions in the region of interest by applying the spatial clustering model to the well data and the production parameter data, evaluate differences in types of productivity values, and identify a target type curve region with greater distinction in mean productivity values relative to a neighboring type curve region and minimal variation in productivity values within the target type curve region;
generate, with the physical computer processor, a representation of the type curve regions as the function of the position in the region of interest using visual effects to depict geographic boundaries outlining at least some of the type curve regions delineated using the spatial clustering model; and
display the representation via the display.

### Claim 8 (depends on 7)

The system of claim 7, wherein the spatial clustering model is based on at least a ratio between a mean productivity variation between areas in the region of interest and a productivity variation within one of the areas in the region of interest.

### Claim 9 (depends on 7)

The system of claim 7, wherein the spatial clustering model comprises an unsupervised machine learning model, wherein the unsupervised machine learning model comprises adjustable hyperparameters.

### Claim 10 (depends on 9)

The system of claim 9, wherein the adjustable hyperparameters comprise a spatial weighting of one of reservoir original oil in place, porosity, geomechanics, pressure, temperature, permeability, mineralogy, stratigraphic beds, depositional facies, diagenic facies, natural fracture intensity, pore saturation, reservoir property, position, reservoir thickness, or a number of the type curve regions” in order to provide appropriate antecedence basis.

### Claim 11 (depends on 7)

The system of claim 7, wherein the production parameter data comprise one of average porosity, pore saturation, mineralogy, lithofacies, geomechanical properties, organic richness, pore pressure, quartz normalized, volume water, argillic bed count, bed thickness, gross thickness, gross perforation length, fracture fluid intensity, proppant intensity, permeability, mineralogy, stratigraphic beds, depositional facies, diagenic facies, natural fracture intensity, pore saturation, reservoir property, or productivity.

### Claim 12 (depends on 7)

The system of claim 7, wherein the types of productivity values comprise mean productivity values and percentile P10-P90 values” in order to provide appropriate antecedence basis.

### Claim 13

A non-transitory computer-readable medium storing instructions for identifying type curve regions as a function of position in a region of interest, the instructions configured to, when executed:
obtain a spatial clustering model from a non-transitory storage medium;
obtain well data from the non-transitory storage medium, wherein the well data includes well locations in the region of interest and corresponding productivity for the well locations;
obtain production parameter data from the non-transitory storage medium, wherein the production parameter data includes production parameter values characterizing subsurface production features that affect reservoir productivity in the region of interest;
delineate, with a physical computer processor, each of the type curve regions in the region of interest by applying the spatial clustering model to the well data and the production parameter data, evaluate differences in types of productivity values, and identify a target type curve region with greater distinction in mean productivity values relative to a neighboring type curve region and minimal variation in productivity values within the target type curve region;
generate, with the physical computer processor, a representation of the type curve regions as the function of the position in the region of interest using visual effects to depict geographic boundaries outlining at least some of the type curve regions delineated using the spatial clustering model; and
display the representation via a display.

### Claim 14 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the spatial clustering model is based on at least a ratio between a mean productivity variation between areas in the region of interest and a productivity variation within one of the areas in the region of interest.

### Claim 15 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the spatial clustering model comprises an unsupervised machine learning model, wherein the unsupervised machine learning model comprises adjustable hyperparameters.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the adjustable hyperparameters comprise one of reservoir original oil in place, porosity, geomechanics, pressure, temperature, position, reservoir thickness, or a number of the type curve regions.

### Claim 17 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the production parameter data comprises one of average porosity, pore saturation, mineralogy, lithofacies, geomechanical properties, organic richness, pore pressure, quartz normalized, volume water, argillic bed count, bed thickness, gross thickness, gross perforation length, fracture fluid intensity, proppant intensity, or productivity.

### Claim 18 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the different types of productivity values comprise mean productivity values and percentile P10-P90 values” in order to provide appropriate antecedence basis.