US-12624633-B2 - Detection of anomaly in a subsurface region

Abstract

A region of interest may include a group of wells. The group of wells may be connected to form a graph of wells, with nodes representing wells and edges representing connections between wells. Connection scores from dynamic time warping paths for individual pairs of connected wells may be used to detect anomalies in the region of interest. Number of boundaries within individual wells may be used to detect anomalies in the region of interest. Connection score and/or number of boundaries may be represented on a visual map of the region of interest.

Inventors

• Robert Chadwick Holmes
• Frank TAMAKLOE
• Fabien J. Laugier

Assignees

• CHEVRON U.S.A. INC.

Dates

Publication Date

20260512

Application Date

20211110

Claims (20)

1. 1 . A system for detecting subsurface anomalies, the system comprising: one or more physical processors configured by machine-readable instructions to: obtain well information, the well information defining a group of wells within a region of interest, the group of wells including multiple wells; connect individual wells in the group of wells based on a distance threshold to form a graph of wells, the graph of wells including nodes representing the multiple wells and edges representing connections between pairs of the multiple wells, wherein two wells that are within the distance threshold of each other are connected, two wells that are not within the distance threshold of each other are not connected, further wherein connected wells are analyzed for detection of anomalies and unconnected wells are not analyzed for detection of anomalies; determine dynamic time warping paths for individual pairs of the connected wells, wherein the dynamic time warping paths are characterized by connection scores for the individual pairs of the connected wells, wherein a given connection score for a given pair of the connected wells indicates similarity between the given pair of the connected wells; and detect an anomaly in the region of interest based on deviation of the connection scores for the individual pairs of the connected wells, wherein detection of the anomaly in the region of interest based on the deviation of the connection scores for the individual pairs of the connected wells includes: identification of a given well as being characterized by an unreliable well log based on the connection scores for connections between the given well and nearby wells deviating from the connection scores for connections between the nearby wells; or identification of a geological boundary located between a first subgroup of wells and a second subgroup of wells based on the connection scores for connections between wells within the first subgroup of wells and wells within the second subgroup of wells deviating from the connection scores for connections between the wells within the first subgroup and the connection scores for connections between the wells within the second subgroup.
2. 2 . The system of claim 1 , wherein the one or more physical processors are further configured by the machine-readable instructions to provide a visual representation of the graph of wells, wherein a visual characteristic of the edges representing the connections between the pairs of the multiple wells is determined based on the connection scores.
3. 3 . The system of claim 2 , wherein the connection scores determine color of the edges representing the connections between the pairs of the multiple wells.
4. 4 . The system of claim 1 , wherein: the well information includes one or more well logs for the individual wells in the group of wells; the one or more well logs for the individual wells are normalized based on a log scaling; and the dynamic time warping paths for the individual pairs of the connected wells are determined based on the one or more normalized well logs for the individual wells.
5. 5 . The system of claim 1 , wherein the distance threshold is adjusted such that none of the multiple wells are isolated.
6. 6 . The system of claim 1 , wherein: the one or more physical processors are further configured by the machine-readable instructions to determine number of boundaries within the individual wells; and the anomaly in the region of interest is detected further based on the number of boundaries within the individual wells.
7. 7 . The system of claim 6 , wherein the anomaly in the region of interest includes a transition between a third subgroup of wells and a fourth subgroup of wells within the region of interest identified based on a change in the number of boundaries within the third subgroup of wells and the fourth subgroup of wells.
8. 8 . The system of claim 6 , wherein the one or more physical processors are further configured by the machine-readable instructions to provide a visual representation of the graph of wells, wherein a visual characteristic of the nodes representing the multiple wells is determined based on the number of boundaries within the individual wells.
9. 9 . The system of claim 8 , wherein the visual characteristic of the nodes representing the multiple wells is gridded onto a surface representing the region of interest within the visual representation of the graph of wells.
10. 10 . The system of claim 9 , wherein the number of boundaries within the individual wells are extrapolated to the region of interest to provide visualization of changes in the number of boundaries throughout the region of interest.
11. 11 . A method for detecting subsurface anomalies, the method comprising: obtaining well information, the well information defining a group of wells within a region of interest, the group of wells including multiple wells; connecting individual wells in the group of wells based on a distance threshold to form a graph of wells, the graph of wells including nodes representing the multiple wells and edges representing connections between pairs of the multiple wells, wherein two wells that are within the distance threshold of each other are connected, two wells that are not within the distance threshold of each other are not connected, further wherein connected wells are analyzed for detection of anomalies and unconnected wells are not analyzed for detection of anomalies; determining dynamic time warping paths for individual pairs of the connected wells, wherein the dynamic time warping paths are characterized by connection scores for the individual pairs of the connected wells, wherein a given connection score for a given pair of the connected wells indicates similarity between the given pair of the connected wells; and detecting an anomaly in the region of interest based on deviation of the connection scores for the individual pairs of the connected wells, wherein detecting the anomaly in the region of interest based on the deviation of the connection scores for the individual pairs of the connected wells includes: identifying a given well as being characterized by an unreliable well log based on the connection scores for connections between the given well and nearby wells deviating from the connection scores for connections between the nearby wells; or identifying a geological boundary located between a first subgroup of wells and a second subgroup of wells based on the connection scores for connections between wells within the first subgroup of wells and wells within the second subgroup of wells deviating from the connection scores for connections between the wells within the first subgroup and the connection scores for connections between the wells within the second subgroup.
12. 12 . The method of claim 11 , further comprising providing a visual representation of the graph of wells, wherein a visual characteristic of the edges representing the connections between the pairs of the multiple wells is determined based on the connection scores.
13. 13 . The method of claim 12 , wherein the connection scores determine color of the edges representing the connections between the pairs of the multiple wells.
14. 14 . The method of claim 11 , wherein: the well information includes one or more well logs for the individual wells in the group of wells; the one or more well logs for the individual wells are normalized based on a log scaling; and the dynamic time warping paths for the individual pairs of the connected wells are determined based on the one or more normalized well logs for the individual wells.
15. 15 . The method of claim 11 , wherein the distance threshold is adjusted such that none of the multiple wells are isolated.
16. 16 . The method of claim 11 , further comprising determining number of boundaries within the individual wells, wherein the anomaly in the region of interest is detected further based on the number of boundaries within the individual wells.
17. 17 . The method of claim 16 , wherein the anomaly in the region of interest includes a transition between a third subgroup of wells and a fourth subgroup of wells within the region of interest identified based on a change in the number of boundaries within the third subgroup of wells and the fourth subgroup of wells.
18. 18 . The method of claim 16 , further comprising providing a visual representation of the graph of wells, wherein a visual characteristic of the nodes representing the multiple wells is determined based on the number of boundaries within the individual wells.
19. 19 . The method of claim 18 , wherein the visual characteristic of the nodes representing the multiple wells is gridded onto a surface representing the region of interest within the visual representation of the graph of wells.
20. 20 . The method of claim 19 , wherein the number of boundaries within the individual wells are extrapolated to the region of interest to provide visualization of changes in the number of boundaries throughout the region of interest.

Description

CROSS-REFERENCE TO RELATED APPLICATION The present application is a national stage application of International Application No. PCT/US21/58835, filed Nov. 10, 2021, which claims the benefit of U.S. Provisional Application No. 63/113,704, entitled “DETECTION OF ANOMALY IN A SUBSURFACE REGION,” which was filed on Nov. 13, 2020, the entirety of which is hereby incorporated herein by reference. FIELD The present disclosure relates generally to the field of detecting subsurface anomalies. BACKGROUND Reservoir characterization from well data is a key challenge in subsurface analysis. Well data may include anomalies, such as problematic data, error in correlation interval, and/or localized data (e.g., local conditions impacts a well that adjacent wells do not intersect). Identifying such anomalies may be difficult, subjective, biased, and non-repeatable. SUMMARY This disclosure relates to detecting subsurface anomalies. Well information and/or other information may be obtained. The well information may define a group of wells within a region of interest. The group of wells may include multiple wells. Individual wells in the group of wells may be connected based on a distance threshold and/or other information to form a graph of wells. The graph of wells may include nodes representing the multiple wells and edges representing connections between pairs of the multiple wells. Dynamic time warping paths for individual pairs of the connected wells may be determined. The dynamic time warping paths may be characterized by connection scores for the individual pairs of the connected wells. One or more anomalies in the region of interest may be detected based on the connection scores for the individual pairs of the connected wells and/or other information. A system that detects subsurface anomalies may include one or more electronic storage, one or more processors and/or other components. The electronic storage may store well information, information relating to wells, information relating to group of wells, information relating to region of interest, information relating to distance threshold, information relating to graph of wells, information relating to nodes, information relating to edges, information relating to dynamic time warping paths, information relating to connection scores, information relating to anomaly, and/or other information. The processor(s) may be configured by machine-readable instructions. Executing the machine-readable instructions may cause the processor(s) to facilitate detecting subsurface anomalies. The machine-readable instructions may include one or more computer program components. The computer program components may include one or more of a well information component, a connection component, a path component, an anomaly component, and/or other computer program components. The well information component may be configured to obtain well information and/or other information. The well information may define a group of wells within a region of interest. The group of wells may include multiple wells. In some implementations, the well information may include one or more well logs for the individual wells in the group of wells. The well log(s) for the individual wells may be normalized based on a log scaling and/or other information. The connection component may be configured to connect individual wells in the group of wells. The individual wells in the group of wells may be connected based on a distance threshold and/or other information. The individual wells in the group of wells may be connected to form a graph of wells. The graph of wells may include nodes and edges. The nodes may represent the multiple wells and the edges may represent connections between pairs of the multiple wells. In some implementations, the distance threshold may be adjusted such that none of the multiple wells are isolated. The path component may be configured to determine dynamic time warping paths for individual pairs of the connected wells. The dynamic time warping paths may be characterized by connection scores for the individual pairs of the connected wells. In some implementations, the dynamic time warping paths for the individual pairs of the connected wells may be determined based on the normalized well log(s) for the individual wells and/or other information. The anomaly component may be configured to detect one or more anomalies in the region of interest. The anomal(ies) may be detected based on the connection scores for the individual pairs of the connected wells and/or other information. In some implementations, the anomal(ies) in the region of interest may include a transition and/or a partition between subgroups of wells within the region of interest. In some implementations, the anomal(ies) in the region of interest may include an unreliable well characterized by an unreliable well log. In some implementations, the anomaly component may be configured to determine number of boundaries within the individual w