Image analysis well log data generation

Patent metadata

Field	Value
Publication number	US-2022010675-A1
Application number	US-202016923220-A
Country	US
Kind code	A1
Filing date	Jul 8, 2020
Priority date	Jul 8, 2020
Publication date	Jan 13, 2022
Grant date	—

Abstract

A well log is scanned for one or more dimensions that describe one or more features of a well. Each dimension includes a plurality of values in a numerical format that represents each dimension. A missing value is detected in a first plurality of values of a first dimension of the well log. The first dimension of the well log is transformed, in response to the missing value, into a first image that visually depicts the first dimension including the first plurality of values and the missing value. Based on the first image and based on an image analysis algorithm a second image is created that visually depicts the first plurality of values and includes a found depiction visually depicting a found value in place of the missing value. The found depiction is converted, based on the second image, into a first value in the numerical format.

First claim

What is claimed is:

1 . A method comprising:
scanning a well log for one or more dimensions, the one or more dimensions describe one or more features of a well, each dimension of the well log corresponds to each feature, each dimension includes a plurality of values in a numerical format that numerically represents each dimension; detecting, based on the well log, a missing value in a first plurality of values of a first dimension of the well log; transforming, in response to the missing value, the first dimension of the well log into a first image, the first image visually depicts the first dimension including the first plurality of values and the missing value; creating, based on the first image and based on an image analysis algorithm, a second image, the second image visually depicts the first plurality of values and a found depiction that visually depicts a found value in place of the missing value; and converting, based on the second image, the found depiction of the found value into a first value, the first value in the numerical format.

2 . The method of claim 1 , wherein the transforming includes plotting each of the first plurality of values as a first-dimension curve and the missing value as a visual gap in the first-dimension curve.

3 . The method of claim 1 , wherein the image analysis algorithm is an inpainting algorithm.

4 . The method of claim 1 , wherein the image analysis algorithm performs inpainting based on a neural network.

5 . The method of claim 4 , wherein a plurality of historical well logs exists for the well, each historical well log of the plurality of historical well logs describes the one or more features of the well at an earlier time, and wherein the method further comprises:
transforming, each of the plurality of historical well logs, into a plurality of training images; and training, based on the plurality of training images, the neural network.

6 . The method of claim 4 , wherein a plurality of historical well logs does not exist for the well, and wherein the method further comprises:
generating, based on the well log, a training data set; and training, based on the training data set, the neural network.

7 . The method of claim 6 , wherein the generating the training data set comprises:
determining, based on the well log, a number of permutations of the one or more dimensions; generating, for each of the number of permutations, a plurality of arrangements of the one or more dimensions; and transforming, for each arrangement of the plurality of arrangements, the plurality of dimensions of a given arrangement into a training image of the plurality of training images.

8 . The method of claim 7 , wherein the method further comprises:
identifying, for each training image of the plurality of training images, an inpainted section; and averaging, based on the identifying, each of the identified inpainted sections.

9 . The method of claim 1 , wherein the transforming includes transforming the one or more dimensions other than the first dimension into the first image, and wherein the first image visually depicts the one or more dimensions.

10 . The method of claim 9 , wherein the method further comprises:
performing a second image analysis algorithm to identify the first plurality of values and the found depiction.

11 . A system comprising:
a memory, the memory containing one or more instructions; and a processor, the processor communicatively coupled to the memory, the processor, in response to reading the one or more instructions, configured to:
scan a well log for one or more dimensions, the one or more dimensions describe one or more features of a well, each dimension of the well log corresponds to each feature, each dimension includes a plurality of values in a numerical format that numerically represents each dimension;
detect, based on the well log, a missing value in a first plurality of values of a first dimension of the well log;
transform, in response to the missing value, the first dimension of the well log into a first image, the first image visually depicts the first dimension including the first plurality of values and the missing value;
create, based on the first image and based on an image analysis algorithm, a second image, the second image visually depicts the first plurality of values and a found depiction that visually depicts a found value in place of the missing value; and
convert, based on the second image, the found depiction of the found value into a first value, the first value in the numerical format.

12 . The system of claim 11 , wherein the transforming includes plotting each of the first plurality of values as a first-dimension curve and the missing value as a visual gap in the first-dimension curve.

13 . The system of claim 11 , wherein the image analysis algorithm is an inpainting algorithm.

14 . The system of claim 11 , wherein the transforming includes transforming the one or more dimensions other than the first dimension into the first image, and wherein the first image visually depicts the one or more dimensions.

15 . The system of claim 14 , wherein the processor is further configured to:
perform, a second image analysis algorithm, to identify the first plurality of values and the found depiction.

16 . A computer program product, the computer program product comprising:
one or more computer readable storage media; and program instructions collectively stored on the one or more computer readable storage media, the program instructions configured to:
scan a well log for one or more dimensions, the one or more dimensions describe one or more features of a well, each dimension of the well log corresponds to each feature, each dimension includes a plurality of values in a numerical format that numerically represents each dimension;
detect, based on the well log, a missing value in a first plurality of values of a first dimension of the well log;
transform, in response to the missing value, the first dimension of the well log into a first image, the first image visually depicts the first dimension including the first plurality of values and the missing value;
create, based on the first image and based on an image analysis algorithm, a second image, the second image visually depicts the first plurality of values and a found depiction that visually depicts a found value in place of the missing value; and
convert, based on the second image, the found depiction of the found value into a first value, the first value in the numerical format.

17 . The computer program product of claim 16 , wherein the image analysis algorithm performs inpainting based on a neural network.

18 . The computer program product of claim 17 , wherein a plurality of historical well logs exists for the well, each historical well log of the plurality of historical well logs describes the one or more features of the well at an earlier time, and wherein the program instructions are further configured to:
transform, each of the plurality of historical well logs, into a plurality of training images; and train, based on the plurality of training images, the neural network.

19 . The computer program product of claim 17 , wherein a plurality of historical well logs does not exist for the well, and wherein the program instructions are further configured to:
generating, based on the well log, a training data set; and training, based on the training data set, the neural network.

20 . The computer program product o

Assignees

• IBM

Inventors

• Yin kun yan
• Zhan sheng hui
• Miao Wan Wan
• Wu Xun
• Yu Zi Yang
• Chen jian hui

Classifications

• G06V10/20 Primary

  Image preprocessing · CPC title

• G06V10/7715

  Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods · CPC title

• G06V10/771

  Feature selection, e.g. selecting representative features from a multi-dimensional feature space · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title