# US 2024/0254868 A1 · System and method for using ai-based model to predict borehole size in horizontal carbonate wells

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

- Number: US 2024/0254868 A1
- Document ID: US20240254868A1
- Status: Published application
- Kind: A1
- Application number: 18/102,293
- Filed: 2023-01-27
- Published: 2024-08-01
- Earliest claimed: 2023-01-27
- Assignees: Saudi Arabian Oil Company
- Applicants: Saudi Arabian Oil Company
- Inventors: Lailaa Helmi Alshammasi; Yacine Meridji; Majed Fareed Kanfar; Lautaro Rayo
- Web page: https://patentgrep.com/patent/US20240254868A1

## CPC

- E21B 43/16: Enhanced recovery methods for obtaining hydrocarbons
- E21B 2200/22: Fuzzy logic, artificial intelligence, neural networks or the like
- E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS

## Abstract

Some implementations provide a method that includes: accessing a stream of input data from logging tools in a first well-bore, wherein the stream of input data comprises measurements of bore sizes inside the first well-bore; splitting the stream of input data into a training set of input data and a testing set of input data; training a machine learning model using the training set of input data, wherein the machine learning model is configured to predict a bore size parameter based on input features of the training set of input data; evaluating the machine learning model using the testing set of input data; and in response to evaluating the machine learning model as satisfactory, applying the machine learning model to a newly received stream of input data from a second well-bore such that the bore size parameter of the second well-bore is determined independent of measurements of bore sizes inside the second well-bore.

## Claims

### Claim 1

A computer-implemented method, comprising:
accessing a stream of input data from logging tools in a first well-bore, wherein the stream of input data comprises measurements of bore sizes inside the first well-bore;
splitting the stream of input data into a training set of input data and a testing set of input data;
training a machine learning model using the training set of input data, wherein the machine learning model is configured to predict a bore size parameter based on input features of the training set of input data;
evaluating the machine learning model using the testing set of input data; and
in response to evaluating the machine learning model as satisfactory, applying the machine learning model to a newly received stream of input data from a second well-bore such that the bore size parameter of the second well-bore is determined independent of measurements of bore sizes inside the second well-bore.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein the machine learning model comprises at least one of: a Random Forest (RF) model, or a XGBoost (eXtreme Gradient Boosting) model.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, further comprising:
selecting the input features for the machine learning model.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein evaluating the machine learning model comprises:
computing a Root Mean Square Error (RMSE) between the predicted bore size parameter and an actual measurement; and
comparing the RMSE with a pre-determined threshold.

### Claim 5 (depends on 4)

The computer-implemented method of claim 4, further comprising:
in response to evaluating the machine learning model as unsatisfactory, refining the machine learning model.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein refining the machine learning model comprises at least one of: providing at least one additional input feature to the machine learning model, or replacing at least one input feature with a different input feature.

### Claim 7 (depends on 5)

The computer-implemented method of claim 5, wherein refining the machine learning model comprises:
adjusting at least one parameter of the machine learning model.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the stream of input data comprises logging data encoding a resistivity, a density, a neutron recording, and a gamma ray recording.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the bore size parameter comprises at least one of: a maximum size, or a minimum size.

### Claim 10

A computer system comprising one or more hardware processors configured to perform operations of:
accessing a stream of input data from logging tools in a first well-bore, wherein the stream of input data comprises measurements of bore sizes inside the first well-bore;
splitting the stream of input data into a training set of input data and a testing set of input data;
training a machine learning model using the training set of input data, wherein the machine learning model is configured to predict a bore size parameter based on input features of the training set of input data;
evaluating the machine learning model using the testing set of input data; and
in response to evaluating the machine learning model as satisfactory, applying the machine learning model to a newly received stream of input data from a second well-bore such that the bore size parameter of the second well-bore is determined independent of measurements of bore sizes inside the second well-bore.

### Claim 11 (depends on 10)

The computer system of claim 10, wherein the machine learning model comprises at least one of: a Random Forest (RF) model, or a XGBoost (eXtreme Gradient Boosting) model.

### Claim 12 (depends on 11)

The computer system of claim 11, wherein the operations further comprise:
selecting the input features for the machine learning model.

### Claim 13 (depends on 11)

The computer system of claim 11, wherein evaluating the machine learning model comprises:
computing a Root Mean Square Error (RMSE) between the predicted bore size parameter and an actual measurement; and
comparing the RMSE with a pre-determined threshold.

### Claim 14 (depends on 13)

The computer system of claim 13, wherein the operations further comprise:
in response to evaluating the machine learning model as unsatisfactory, refining the machine learning model.

### Claim 15 (depends on 13)

The computer system of claim 13, wherein refining the machine learning model comprises at least one of: providing at least one additional input feature to the machine learning model, or replacing at least one input feature with a different input feature.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein refining the machine learning model comprises:
adjusting at least one parameter of the machine learning model.

### Claim 17 (depends on 10)

The computer system of claim 10, wherein the stream of input data comprises logging data encoding a resistivity, a density, a neutron recording, and a gamma ray recording.

### Claim 18 (depends on 10)

The computer system of claim 10, wherein the bore size parameter comprises at least one of: a maximum size, or a minimum size.

### Claim 19

A non-transitory computer-readable medium comprising software instructions which, when executed by one or more computer processors, cause the one or more computer processors to perform operations of:
accessing a stream of input data from logging tools in a first well-bore, wherein the stream of input data comprises measurements of bore sizes inside the first well-bore;
splitting the stream of input data into a training set of input data and a testing set of input data;
training a machine learning model using the training set of input data, wherein the machine learning model is configured to predict a bore size parameter based on input features of the training set of input data;
evaluating the machine learning model using the testing set of input data; and
in response to evaluating the machine learning model as satisfactory, applying the machine learning model to a newly received stream of input data from a second well-bore such that the bore size parameter of the second well-bore is determined independent of measurements of bore sizes inside the second well-bore.

### Claim 20 (depends on 19)

The non-transitory computer-readable medium of claim 19, wherein evaluating the machine learning model comprises:
computing a Root Mean Square Error (RMSE) between the predicted bore size parameter and an actual measurement; and
comparing the RMSE with a pre-determined threshold.
