Method for using a closed layer model as training data for machine learning

Abstract

A method for generating a closed layer model of a subsurface includes receiving input data including a 3D seismic volume having a plurality of horizons. The method also includes identifying labeled areas of the plurality of horizons based to produce identified labeled areas for the plurality of horizons. The method further includes determining lateral extents of the identified labeled areas based on the input data, and sorting the plurality of horizons based on the lateral extents to produce a plurality of sorted horizons. The method also includes identifying boundary points of the plurality of horizons based on the lateral extents, and creating truncation maps for the plurality of horizons based on the boundary points of the plurality of sorted horizons. The method also includes generating the closed layer model based on the plurality of horizons and the truncation maps thereof.

Description

PATENT Atorney Docket No.: IS24.1847-WO-PCTMETHOD FOR USING A CLOSED LAYER MODEL AS TRAINING DATA FORMACHINE LEARNINGCross-Reference to Related Applications

[0001] This application claims priority to and the benefit of U.S. Provisional Patent Application No. 63 / 725115 filed on November 26, 2024, the entirety of which is incorporated herein by reference to the extent consistent with the present disclosure.Background

[0002] Seismic interpretation relies on the delineation and mapping of subsurface features within seismic volumes. Horizons, which represent reflection surfaces, are identified in seismic data by their consistent wavelet signatures across a survey. Accurate horizon mapping allows interpreters to evaluate amplitude variations for the detection of potential fluid anomalies. Conventional automated approaches, including machine learning and pattern-recognition techniques, have been developed to assist in mapping such features. However, these methods often involve extensive labeled training data, large-scale iterative optimization, and computational resources. In practice, these approaches are often slow to converge, sensitive to noise, and limited in their ability to generalize across surveys with varying acquisition parameters or geologic settings.

[0003] What is needed, then, are systems and methods that can more efficiently and reliably predict stratigraphic layers and other structural features in three-dimensional seismic volumes.Summary

[0004] A method for generating a closed layer model of a subsurface is disclosed. The method includes receiving input data including a 3D seismic volume. The 3D seismic volume includes a plurality of horizons. The method also includes identifying labeled areas of the plurality of horizons based on the input data to produce identified labeled areas for the plurality of horizons. The method further includes determining lateral extents of the identified labeled areas based on the input data. The method also includes sorting the plurality of horizons based on the lateral extents to produce a plurality of sorted horizons. The method also includes identifying boundary points of the plurality of horizons based on the lateral extents. The method also includes creating truncation maps for the plurality of horizons based on the boundary points of the plurality of sortedPATENT Atorney Docket No.: IS24.1847-WO-PCT horizons. The method also includes generating the closed layer model based on the plurality of horizons and the truncation maps thereof.

[0005] A computing system is also disclosed. The computing system includes one or more processors and a method system. The method system includes one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations for generating a closed layer model of a subsurface. The operations include receiving input data including a 3D seismic volume associated with the subsurface. The 3D seismic volume includes a plurality of horizons. Each horizon of the plurality of horizons includes a respective labeled area. The respective labeled area of each horizon of the plurality of horizons includes one or more horizon points. The operations also include identifying the respective labeled area of each horizon of the plurality of horizons based on the one or more horizon points thereof to produce an identified labeled area for each horizon of the plurality of horizons. The respective identified labeled area is a sparce labeled area or a continuous labeled area. The operations further include determining a respective lateral extent of the sparce labeled area, the continuous labeled area, or a combination thereof of each horizon of the plurality of horizons based on the one or more horizon points thereof. The operations also include sorting the plurality of horizons vertically based on the respective lateral extent of the identified labeled area of each horizon of the plurality of horizons to produce a plurality of sorted horizons. The operations also include identifying boundary points of each horizon of the plurality of horizons based on the respective lateral extent thereof. The operations also include creating a truncation map for each horizon of the plurality of horizons based on the respective boundary points of each horizon of the plurality of sorted horizons. The operations also include generating the closed layer model of the subsurface based on the plurality of horizons and the truncation map of each horizon of the plurality of horizons.

[0006] A non-transitory computer-readable medium is also disclosed. The medium stores instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations for generating a closed layer model of a subsurface. The operations include receiving input data including a 3D seismic volume associated with the subsurface. The 3D seismic volume includes a plurality of horizons. Each horizon of the plurality of horizons includes a respective labeled area. The respective labeled area of each horizon of the plurality of horizons includes one or more horizon points. The operations also include identifyingPATENT Atorney Docket No.: IS24.1847-WO-PCT the respective labeled area of each horizon of the plurality of horizons based on the one or more horizon points thereof to produce an identified labeled area for each horizon of the plurality of horizons. The respective identified labeled area is a sparce labeled area or a continuous labeled area. The operations further include determining a respective lateral extent of the sparce labeled area, the continuous labeled area, or a combination thereof for each horizon of the plurality of horizons. The operations also include sorting the plurality of horizons vertically based on the respective lateral extent of each horizon of the plurality of horizons to produce a plurality of sorted horizons. Sorting the plurality of horizons vertically includes determining a relative vertical position of each horizon of the plurality of horizon based on a respective overlap between two or more horizons of the plurality of horizons. The operations also include identifying boundary points of each horizon of the plurality of horizons based on the respective lateral extent thereof. The operations also include creating a truncation map for each horizon of the plurality of horizons based on the respective boundary points of each horizon of the plurality of sorted horizons. The operations also include generating the closed layer model of the subsurface based on the plurality of horizons and the truncation map of each horizon of the plurality of horizons.

[0007] It will be appreciated that this summary is intended merely to introduce some aspects of the present methods, systems, and media, which are more fully described and / or claimed below. Accordingly, this summary is not intended to be limiting.Brief Description of the Drawings

[0008] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the present teachings and together with the description, serve to explain the principles of the present teachings. In the figures:

[0009] Figure 1 illustrates an example of a system that includes various management components to manage various aspects of a geologic environment, according to an embodiment.

[0010] Figure 2 an exemplary machine learning workflow where the method disclosed herein may be applied, according to an embodiment

[0011] Figure 3A illustrates an exemplary horizon including sparse (I, J)-locations of labelled horizon points, according to an embodiment.PATENT Atorney Docket No.: IS24.1847-WO-PCT

[0012] Figures 3B and 3C illustrate the exemplary horizon including labelled (I, J)-locations split up in points along the I-direction (Figure 3B) and J-direction (Figure 3C), according to an embodiment.

[0013] Figure 3D illustrates the exemplary horizon including an edge or minimum line capturing a minimum of labelled points along the I-direction, according to an embodiment.

[0014] Figure 3E illustrates the exemplary horizon including an edge or maximum line capturing a maximum of labelled points along the I-direction, according to an embodiment.

[0015] Figure 3F illustrates the exemplary horizon including an edge or minimum line capturing a minimum of labelled points along the J-direction, according to an embodiment.

[0016] Figure 3G illustrates the exemplary horizon including an edge or maximum line capturing a minimum of labelled points along the J-direction, according to an embodiment.

[0017] Figure 3H illustrates the exemplary horizon including the boundary represented as a final polygon around the labelled points, according to an embodiment.

[0018] Figure 31 illustrates the exemplary horizon including the detected lateral extent of the labelled area and non-labelled background, according to an embodiment.

[0019] Figure 4A illustrates an exemplary horizon including continuous (I, J)-locations of labelled horizon points, according to an embodiment.

[0020] Figure 4B illustrates the exemplary horizon including non-labelled points split into an external area and voids or void areas and, according to an embodiment.

[0021] Figure 4C illustrates the exemplary horizon including identified boundary points around the labelled points, obtained at the intersection of labelled points and external non-labelled points, according to an embodiment.

[0022] Figure 5 A illustrates a plurality of stacked or sorted horizons, according to an embodiment.

[0023] Figure 5B illustrates the plurality of stacked or sorted horizons including layer labels, according to an embodiment.

[0024] Figure 6 illustrates a flowchart of a method for predicting layers in a 3D seismic volume, according to an embodiment.

[0025] Figure 7 illustrates a flowchart of a method for generating a closed layer model of a subsurface, according to an embodiment.

[0026] Figure 8 illustrates a schematic view of a computing system for performing at least a portion of the method(s) described herein, according to an embodiment.PATENT Atorney Docket No.: IS24.1847-WO-PCTDetailed Description

[0027] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings and figures. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be apparent to one of ordinary skill in the art that the present disclosure may be practiced without these specific details. In other instances, well-known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0028] It will also be understood that, although the terms first, second, etc. may be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, a first object or step could be termed a second object or step, and, similarly, a second object or step could be termed a first object or step, without departing from the scope of the present disclosure. The first object or step, and the second object or step, are both, objects or steps, respectively, but they are not to be considered the same object or step.

[0029] The terminology used in the description herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used in this description and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any possible combinations of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Further, as used herein, the term “if’ may be construed to mean “when” or “upon” or “in response to determining” or “in response to detecting,” depending on the context.

[0030] Attention is now directed to processing procedures, methods, techniques, and workflows that are in accordance with some embodiments. Some operations in the processing procedures, methods, techniques, and workflows disclosed herein may be combined and / or the order of some operations may be changed.PATENT Atorney Docket No.: IS24.1847-WO-PCTSystem Overview

[0031] Figure 1 illustrates an example of a system 100 that includes various management components 110 to manage various aspects of a geologic environment 150 (e.g., an environment that includes a sedimentary basin, a reservoir 151, one or more faults 153-1, one or more geobodies 153-2, etc.). For example, the management components 110 may allow for direct or indirect management of sensing, drilling, injecting, extracting, etc., with respect to the geologic environment 150. In turn, further information about the geologic environment 150 may become available as feedback 160 (e.g., optionally as input to one or more of the management components 110).

[0032] In the example of Figure 1, the management components 110 include a seismic data component 112, an additional information component 114 (e g., well / logging data), a processing component 116, a simulation component 120, an attribute component 130, an analysis / visualization component 142 and a workflow component 144. In operation, seismic data and other information provided per the components 112 and 114 may be input to the simulation component 120.

[0033] In an example embodiment, the simulation component 120 may rely on entities 122. Entities 122 may include earth entities or geological objects such as wells, surfaces, bodies, reservoirs, etc. In the system 100, the entities 122 may include virtual representations of actual physical entities that are reconstructed for purposes of simulation. The entities 122 may include entities based on data acquired via sensing, observation, etc. (e.g., the seismic data 112 and other information 114). An entity may be characterized by one or more properties (e.g., a geometrical pillar grid entity of an earth model may be characterized by a porosity property). Such properties may represent one or more measurements (e.g., acquired data), calculations, etc.

[0034] In an example embodiment, the simulation component 120 may operate in conjunction with a software framework such as an object-based framework. In such a framework, entities may include entities based on pre-defined classes to facilitate modeling and simulation. A commercially available example of an object-based framework is the MICROSOFT® .NET® framework (Redmond, Washington), which provides a set of extensible object classes. In the .NET® framework, an object class encapsulates a module of reusable code and associated data structures. Object classes may be used to instantiate object instances for use in by a program,PATENT Atorney Docket No.: IS24.1847-WO-PCT script, etc. For example, borehole classes may define objects for representing boreholes based on well data.

[0035] In the example of Figure 1, the simulation component 120 may process information to conform to one or more attributes specified by the attribute component 130, which may include a library of attributes. Such processing may occur prior to input to the simulation component 120 (e.g., consider the processing component 116). As an example, the simulation component 120 may perform operations on input information based on one or more attributes specified by the attribute component 130. In an example embodiment, the simulation component 120 may construct one or more models of the geologic environment 150, which may be relied on to simulate behavior of the geologic environment 150 (e.g., responsive to one or more acts, whether natural or artificial). In the example of Figure 1, the analysis / visualization component 142 may allow for interaction with a model or model-based results (e.g., simulation results, etc.). As an example, output from the simulation component 120 may be input to one or more other workflows, as indicated by a workflow component 144.

[0036] As an example, the simulation component 120 may include one or more features of a simulator such as the ECLIPSE™ reservoir simulator (SLB, Houston Texas), the INTERSECT™ reservoir simulator (SLB, Houston Texas), etc. As an example, a simulation component, a simulator, etc. may include features to implement one or more meshless techniques (e.g., to solve one or more equations, etc ). As an example, a reservoir or reservoirs may be simulated with respect to one or more enhanced recovery techniques (e.g., consider a thermal process such as SAGD, etc ).

[0037] As an example, the simulation component 120 may include one or more features of a simulator such as SYMMETRY™ software (SLB, Houston, Texas). More particularly, SYMMETRY™ may process workflows in a single integrated environment with accurate thermodynamic fluid representation and consistent modeling across multiple disciplines including process, production, and HSE. The simulator integrates steady-state and transient (e.g., dynamic) analyses that may be tailored for each domain. This approach enables users to optimize processes in upstream, midstream, and downstream sectors while maximizing profits and minimizing capital expenditures. It may also help reduce emissions, energy consumption, and waste.

[0038] As an example, the simulation component 120 may include one or more features of a simulator such as PIPESIM™ (SLB, Houston, Texas). More particularly, PIPESIM™ is steady-PATENT Atorney Docket No.: IS24.1847-WO-PCT state multiphase flow simulator that incorporates the three areas of flow modeling: multiphase flow, heat transfer and fluid behavior.

[0039] As an example, the simulation component 120 may include one or more features of a simulator such as OLGA™ (SLB, Houston, Texas). More particularly, OLGA™ is a dynamic multiphase flow simulator that models transient flow (e.g., time-dependent behaviors) to maximize production potential. Transient modeling is a component for feasibility studies and field development design. Dynamic simulation is useful in deep water and is used in both offshore and onshore developments to investigate transient behavior in pipelines and wellbores. Transient simulation with the OLGA™ simulator provides an added dimension to steady-state analysis by predicting system dynamics, such as time-varying changes in flow rates, fluid compositions, temperature, solids deposition, and operational changes.

[0040] In an example embodiment, the management components 110 may include features of a commercially available framework such as the PETREL® seismic to simulation software framework (SLB, Houston, Texas). The PETREL® framework provides components that allow for optimization of exploration and development operations. The PETREL® framework includes seismic to simulation software components that may output information for use in increasing reservoir performance, for example, by improving asset team productivity. Through use of such a framework, various professionals (e.g., geophysicists, geologists, and reservoir engineers) may develop collaborative workflows and integrate operations to streamline processes. Such a framework may be considered an application and may be considered a data-driven application (e.g., where data is input for purposes of modeling, simulating, etc.).

[0041] In an example embodiment, various aspects of the management components 110 may include add-ons or plug-ins that operate according to specifications of a framework environment. For example, a commercially available framework environment marketed as the OCEAN® framework environment (SLB, Houston, Texas) allows for integration of add-ons (or plug-ins) into a PETREL® framework workflow. The OCEAN® framework environment leverages .NET® tools (Microsoft Corporation, Redmond, Washington) and offers stable, user-friendly interfaces for efficient development. In an example embodiment, various components may be implemented as add-ons (or plug-ins) that conform to and operate according to specifications of a framework environment (e.g., according to application programming interface (API) specifications, etc.).PATENT Atorney Docket No.: IS24.1847-WO-PCT

[0042] Figure 1 also shows an example of a framework 170 that includes a model simulation layer 180 along with a framework services layer 190, a framework core layer 195 and a modules layer 175. The framework 170 may include the commercially available OCEAN® framework where the model simulation layer 180 is the commercially available PETREL® model-centric software package that hosts OCEAN® framework applications. In an example embodiment, the PETREL® software may be considered a data-driven application. The PETREL® software may include a framework for model building and visualization.

[0043] As an example, a framework may include features for implementing one or more mesh generation techniques. For example, a framework may include an input component for receipt of information from interpretation of seismic data, one or more attributes based at least in part on seismic data, log data, image data, etc. Such a framework may include a mesh generation component that processes input information, optionally in conjunction with other information, to generate a mesh.

[0044] In the example of Figure 1, the model simulation layer 180 may provide domain objects 182, act as a data source 184, provide for rendering 186 and provide for various user interfaces 188. Rendering 186 may provide a graphical environment in which applications may display their data while the user interfaces 188 may provide a common look and feel for application user interface components.

[0045] As an example, the domain objects 182 may include entity objects, property objects and optionally other objects. Entity objects may be used to geometrically represent wells, surfaces, bodies, reservoirs, etc., while property objects may be used to provide property values as well as data versions and display parameters. For example, an entity object may represent a well where a property object provides log information as well as version information and display information (e.g., to display the well as part of a model).

[0046] In the example of Figure 1, data may be stored in one or more data sources (or data stores, generally physical data storage devices), which may be at the same or different physical sites and accessible via one or more networks. The model simulation layer 180 may be configured to model projects. As such, a particular project may be stored where stored project information may include inputs, models, results and cases. Thus, upon completion of a modeling session, a user may store a project. At a later time, the project may be accessed and restored using the model simulation layer 180, which may recreate instances of the relevant domain objects.PATENT Atorney Docket No.: IS24.1847-WO-PCT

[0047] In the example of Figure 1 , the geologic environment 150 may include layers (e.g., stratification) that include a reservoir 151 and one or more other features such as the fault 153-1, the geobody 153-2, etc. As an example, the geologic environment 150 may be outfitted with any of a variety of sensors, detectors, actuators, etc. For example, equipment 152 may include communication circuitry to receive and to transmit information with respect to one or more networks 155. Such information may include information associated with downhole equipment 154, which may be equipment to acquire information, to assist with resource recovery, etc. Other equipment 156 may be located remote from a well site and include sensing, detecting, emitting or other circuitry. Such equipment may include storage and communication circuitry to store and to communicate data, instructions, etc. As an example, one or more satellites may be provided for purposes of communications, data acquisition, etc. For example, Figure 1 shows a satellite in communication with the network 155 that may be configured for communications, noting that the satellite may additionally or instead include circuitry for imagery (e.g., spatial, spectral, temporal, radiometric, etc.).

[0048] Figure 1 also shows the geologic environment 150 as optionally including equipment 157 and 158 associated with a well that includes a substantially horizontal portion that may intersect with one or more fractures 159. For example, consider a well in a shale formation that may include natural fractures, artificial fractures (e.g., hydraulic fractures) or a combination of natural and artificial fractures. As an example, a well may be drilled for a reservoir that is laterally extensive. In such an example, lateral variations in properties, stresses, etc. may exist where an assessment of such variations may assist with planning, operations, etc. to develop a laterally extensive reservoir (e.g., via fracturing, injecting, extracting, etc.). As an example, the equipment 157 and / or 158 may include components, a system, systems, etc. for fracturing, seismic sensing, analysis of seismic data, assessment of one or more fractures, etc.

[0049] As mentioned, the system 100 may be used to perform one or more workflows. A workflow may be a process that includes a number of worksteps. A workstep may operate on data, for example, to create new data, to update existing data, etc. As an example, a may operate on one or more inputs and create one or more results, for example, based on one or more algorithms. As an example, a system may include a workflow editor for creation, editing, executing, etc. of a workflow. In such an example, the workflow editor may provide for selection of one or more predefined worksteps, one or more customized worksteps, etc. As an example, a workflow may be aPATENT Atorney Docket No.: IS24.1847-WO-PCT workflow implementable in the PETREL® software, for example, that operates on seismic data, seismic attribute(s), etc. As an example, a workflow may be a process implementable in the OCEAN® framework. As an example, a workflow may include one or more worksteps that access a module such as a plug-in (e.g., external executable code, etc.).Method for Using a Closed Layer Model as Training Data for Machine Learning (ML)

[0050] In the context of a machine learning approach for training a machine to detect multiple geological layers from seismic data, a workflow is described herein where training data may be picked along selected seismic horizons defining the boundaries between the layers. While the training data may be provided as labeled points positioned along the seismic horizons, the training of the machine may involve the full vertical extent of the data to be labeled with one unique label value per geological layer. Furthermore, when the trained machine is applied to predict layer labels on unseen seismic data, knowledge of the relationships between horizon labels and layer labels may be helpful when extracting horizons of layer boundaries from the predicted layer label volume.

[0051] The methods described herein may convert horizon point labels into layer interval labels, ensuring layer label consistency in 3D between different locations of labeled horizon points. In particular, the approach ensures accurate labelling of layers also in geological settings where some of the horizons exist in some regions of the study area.

[0052] The method includes receiving, as input, a collection of labelled horizon points from a 3D seismic volume, where each horizon may be assigned a unique label, and each point may correspond to a location along the horizon and may be assigned the label of the horizon. The method then creates a layer label volume the same size as the seismic volume, where each trace containing labelled horizon points may be assigned vertical layer interval labels continuously between the labelled horizon points.

[0053] Creating the layer label volume may generally include one or more of the following:1. Identifying the lateral extent of the labelled area of each labelled horizon.2. Sorting the labelled horizons vertically based on lateral overlaps.3. Creating a truncation map for each horizon, indicating where a horizon may be truncated or not, and to which horizon it may be truncated.PATENT Atorney Docket No.: IS24.1847-WO-PCT a. For positions along the boundary of the lateral extent of each labelled horizon, determine if the labelled horizon is truncated towards a shallower horizon, truncated towards a deeper horizon, or if the horizon is still present in the seismic data but not labelled beyond the boundary.4. Defining the lateral extent of where each labelled horizon may be present in the seismic data as the combination of the extent of the labelled area, and the area extending beyond any boundary positions where no truncation is detected.5. Populating layer labels within the 3D volume.6. To get the layers vertically at any lateral position within the study area, let the labelled horizons present at the position define vertically succeeding pairs of layer boundaries, and use the identified truncations of the other labelled horizons to determine the appropriate layer label between any pair of labelled horizons.

[0054] Vertical layer transitions may be captured by identifying, from the input horizon labels and the assigned layer labels, which horizon label may be present as a boundary between any unique pair of vertically succeeding layer labels.

[0055] The method complements a machine learning workflow for prediction of multiple seismic horizons, defined as boundaries between layers, by automating the conversion of training data along individual horizons to training data of a closed layer model. Furthermore, it enables an automatic association of layer interfaces extracted from a layer prediction volume back to the original input horizons.

[0056] The method also provides an automatic procedure for converting points picked along a set of seismic horizons into a closed volume of layers, suitable for training a machine learning model for layer prediction. The procedure detects and accounts for seismic horizons terminating against other horizons. The method also automates training data preparation in a machine learning workflow for mapping and extracting multiple seismic horizons, and automating the association of horizon points extracted from the machine learning prediction to the corresponding training input horizons.

[0057] The method converts training points along individual horizons into a consistent closed volume layer model. The method also captures unique layer transitions.Layer label volume creationPATENT Atorney Docket No.: IS24.1847-WO-PCT

[0058] Figure 2 illustrates an exemplary machine learning workflow where the method disclosed herein may be applied, according to an embodiment. The method may be located within the dotted rectangle. The elements outside the dotted rectangle may be considered an example.

[0059] The following gives an example of how the method may be executed, where data may be represented on a regular grid in 3D. The input may be or include labelled horizon points represented as (X, Y, Z) earth coordinates and associated horizon labels, where (X, Y) represents the lateral positions of a seismic trace and Z the vertical positions in seismic time or depth domain. The input may also be or instead include 3D seismic data file providing (1) the total grid size of the 3D volume and / or (2) conversion from (X, Y, Z) earth coordinates to integer (I, J, K) volume indices, where (I, J) represents indexing into the lateral position of a seismic trace (e.g., a column through the 3D data volume), and K is indexing into the vertical dimension in seismic time or depth domain (e.g., the vertical position in the column through the 3D data volume).Data preparation

[0060] For each labelled horizon, the method may convert the (X, Y, Z) earth coordinates of the labelled horizon points into (I, J, K) indices relative to the seismic volume. In a conventional machine learning workflow of labelling seismic training points, labelled points may often be selected along a few vertical sections through the seismic 3D volume. For horizon labelling, this may provide continuous or semi-continuous labelled points along a few I- or J-indices, but in 3D the labelled points overall appear sparse. A different strategy for labelling seismic horizons may be to label a continuous, but limited region of each horizon. This may provide continuous or semi- continuous labelled points in a limited, but continuous range of I- and J-indices. The methods disclosed herein accept both strategies by analyzing the labelled horizon points to automatically determine if the labelled points are considered sparse or continuous.

[0061] For each labelled horizon, the method identifies the I- and J- indices respectively of vertical seismic sections containing enough labelled points to be considered a labelled section. From the identified I- and J- indices of labelled sections, the method determines whether the labelled points are mainly located along a few separated labelled sections in one or both directions, referred to as sparse labelled horizon points, or in connected regions spanning many succeeding labelled sections, referred to as continuous labelled horizon points.PATENT Atorney Docket No.: IS24.1847-WO-PCTIdentify the lateral extent of the labelled area of each labelled horizon

[0062] The lateral extent of the labelled area may be determined individually for each of the labelled horizons, using different strategies for sparse and continuous labelled horizon points respectively.Sparse labelled horizon points

[0063] Figure 3A illustrates an exemplary horizon 300 including sparse (I, J)-locations of labelled horizon points 302, according to an embodiment. For sparse labelled horizon points 302, a boundary 304 of a lateral extent 306 of a labelled area may be represented as an enclosing polygon defined by a set of (I, J) indices, ensuring the labelled points are located within the polygon.

[0064] Figures 3B and 3C illustrate the exemplary horizon 300 including labelled (I, J)-locations split up in points along the I-direction (Figure 3B) and J-direction (Figure 3C), according to an embodiment. Figure 3D illustrates the exemplary horizon 300 including an edge or minimum line 308 capturing a minimum of labelled points along the I-direction, according to an embodiment. Figure 3E illustrates the exemplary horizon 300 including an edge or maximum line 310 capturing a maximum of labelled points along the I-direction, according to an embodiment. Figure 3F illustrates the exemplary horizon 300 including an edge or minimum line 312 capturing a minimum of labelled points along the J-direction, according to an embodiment. Figure 3G illustrates the exemplary horizon 300 including an edge or maximum line 314 capturing a minimum of labelled points along the J-direction, according to an embodiment. Figure 3H illustrates the exemplary horizon 300 including the boundary 304 represented as a final polygon (in black) around the labelled points, obtained by combining the edges 308, 310, 312, 314 of the minimum and maximum range of labelled points along the I- and J-direction, according to an embodiment. Figure 31 illustrates the exemplary horizon 300 including the detected lateral extent 306 of the labelled area in gray and non-labelled background (in white), according to an embodiment.

[0065] In at least one embodiment, an algorithm may be designed, constructing the polygon by separating the labelled points into labels across labelled sections in the I- and J-direction (Figures 3B and 3C) identifying minimum and / or maximum lines 308, 310, 312, 314 representing the minimum and maximum range of labels in the I- and J-direction (Figures 3D and 3E, and Figures 3F and 3F, respectively), and combining the lines into a closed polygon (Figures 3H and 31) to represent, define, or otherwise identify the lateral extent 306.PATENT Atorney Docket No.: IS24.1847-WO-PCTContinuous labelled horizon points

[0066] Figure 4A illustrates an exemplary horizon 400 including continuous (I, J)-locations of labelled horizon points 402, according to an embodiment. Figure 4B illustrates the exemplary horizon 400 including non-labelled points split into an external area 404 and voids or void areas 406, according to an embodiment. Figure 4C illustrates the exemplary horizon 400 including identified boundary points 408 (in black) around the labelled points, obtained at the intersection of labelled points and external non-labelled points, according to an embodiment.

[0067] More particularly, for continuous labelled horizon points (Figure 4A), the (I, J) indices not containing a label may be categorized as belonging to the external area 404 or the void area 406, where a void area 406 may be a set of non-labelled points encircled by the labelled points, and the external area 404 may contain the non-labelled points between the labelled points and an edge 410 of the horizon 400 or the study area. The boundary 408 of the lateral extent of the labelled area may be represented by the indices (I, J) of labelled points where at least one of the neighbors (I- 1, J), (1+1, J), (I, J-l) or (I, J+l) belongs to the external area 404 (Figure 4C).Sort the labelled horizons vertically based on lateral overlaps

[0068] The labelled horizons may be sorted in a vertical order based on the vertical position of each horizon within the extent of the labelled region. For pairwise laterally overlapping labelled horizons, it may be determined from the overlapping area which horizon is vertically deeper than the other.Create a truncation map for each horizon

[0069] Horizon terminations may be identified to create a closed stratigraphic model in 3D. For each horizon, the vertical closeness of its boundary points to other horizons may be considered, and points along the boundary may be categorized as truncated upwards against a shallower horizon, truncated downwards against a deeper horizon, or not truncated. In at least one embodiment, creating the truncation map(s) may include one or more of the following:1. Number the horizons in the vertical order from the shallowest to the deepest.2. Interpolate the depths of each labelled horizon within the boundary of the labelled area.3. For each horizon populate truncation maps with truncation values:PATENT Atorney Docket No.: IS24.1847-WO-PCT a. For the indices (I, J) within the lateral extent of the labelled area, set the truncation value to 0. b. For each boundary point of the horizon find a truncation value. i. Let (I, J, K) be the index of the boundary point. ii. Determine which other horizon is vertically closest to K at the lateral position (I, J). iii. If the closest horizon is within a maximum vertical distance AK from the boundary point, categorize the boundary point as truncated and set the truncation value at (I, J) as the difference between the horizon number of the closest horizon and the current horizon number. If the closest horizon is shallower, the horizon is truncated upwards, and the truncation value is negative. If the closest horizon is deeper, the horizon is truncated downwards, and the truncation value is positive. iv. If the closest horizon is beyond the maximum vertical distance AK, categorize the boundary point as not truncated and set the truncation value at (I, J) to 0. The seismic horizon is assumed to exist, but not be labelled, laterally beyond the boundary point. c. Extrapolate the truncation values into areas beyond the extent of the labelled area.

[0070] The resulting set of truncation maps identify, for each labelled horizon region, where the horizon is present (e g., labelled or non-labelled), and regions where it is not present, beyond truncations to other horizons. The lateral extent of where each labelled horizon is present in the seismic data may be defined by truncation value 0 and includes the combination of the extent of the labelled area, and the area extending beyond any boundary positions where no truncation is detected.Populate layer labels within the 3D volume

[0071] The layer labels may be populated individually for each trace index (I, J) within the 3D volume of the study area using the truncation maps to determine the different ranges of K-indices of each layer present in the trace. The depth of each labelled horizon present in the trace defines the layer boundaries in the trace, and the layer labels may be found by a recursive algorithm based on the truncation maps.PATENT Atorney Docket No.: IS24.1847-WO-PCT

[0072] For the trace indices (I, J) within the 3D volume:1. Define layer boundaries in the trace.1.1 Set the first layer boundary to the top of the trace.1.2 Identify which labelled horizons may be present in the trace and define layer boundaries by the K-indices of the depth of these horizons at (I, J).1.3 Set the last layer boundary to the base of the trace.2. Determine the layer label for each succeeding pair of layer boundaries.2.1 Initialize the layer label as the horizon number of the shallowest boundary in the pair of layer boundaries, or the number before the shallowest of all horizons if the layer top is the top of the trace.2.2 Initialize a horizon range of the horizons between, but not including, the pair of layer boundaries.2.3 Recursively increment the layer label.2.3.1 If the horizon range is empty, increment the layer label by 1 and exit the recursions.2.3.2 If the horizons in the horizon range are truncated downwards, increment the layer label by 1 and exit the recursions.2.3.3 If the first horizon in the horizon range is truncated to first horizon after the horizon range, increment the layer label by 1 and exit the recursions.2.3.4 If the horizons in the horizon range are truncated upwards, increment the layer label by 1 plus the number of horizons in the horizon range and exit the recursions.2.3.5 If the last truncated horizon in the horizon range is truncated to the last horizon before the horizon range, increment the layer label by 1 plus the number of horizons in the horizon range and exit the recursions.2.3.6 For each horizon except the first in the horizon range:(1) If the horizon is truncated to the first horizon after the horizon range:(a) Remove the current and all succeeding horizons from the horizon range and go to step 2.3.1.2.3.7 For a reverse order of each horizon except the last in the horizon range:(1) If the horizon is truncated to the last horizon before the horizon range:(a) Increment the layer label by the relative number of the horizon within the horizon range.PATENT Atorney Docket No.: IS24.1847-WO-PCT(b) Remove the current and the preceding horizons from the horizon range and go to step 2.3.1.3. For each pair of layer boundaries, populate the layer label between the K-indices of the top and base layer boundaries.

[0073] Properties of the described algorithm may include one or more of the following: (1) the volume above the shallowest labelled horizon may be defined as the first layer, and the layer label may be set to the number of the shallowest labelled horizon; (2) the volume below the deepest labelled horizon may be defined as the last layer, and the layer label may be set to the number of the deepest labelled horizon plus 1; (3) if two succeeding labelled horizons are both present in a trace, the layer label between the two horizons may be set to the same value as the number of the deeper of the two horizons.

[0074] Figure 5A illustrates a plurality of stacked or sorted horizons 500, according to an embodiment. Figure 5B illustrates the plurality of stacked or sorted horizons 500 including layer labels 504, according to an embodiment. Figures 5A and 5B illustrate terminations detected from the vertically sorted horizons 500 with dotted lines 502 indicating regions where a horizon is truncated, and hence not present, according to an embodiment. As illustrated in Figure 5B, the layer labels 504 may be populated between the horizons. As illustrated in Figure 5B, some layer labels 504 may be absent in vertical sections of the data where some horizons are truncated.

[0075] The result of methods disclosed herein and / or the described algorithm may be a 3D layer label volume, where a plurality or otherwise every (I, J, K) index in the volume may be assigned a layer label 504. The 3D volume honors the input horizon labels through layer boundaries defined at the positions of the labelled horizon points and has a lateral consistency in layer labels with truncations accounted for. Hence, 1-dimensional (1-D), 2-dimensional (2D), or 3D sub-volumes of layer labels may be collected from the layer label volume along traces where labelled horizon points were provided and applied in training a machine learning (ML) model to detect multiple geological layers from seismic data.Identify unique combinations of layer labels and horizon labels

[0076] Steps 1 and 2 of the layer label volume generation may produce a set of succeeding layers with associated layer labels for the traces in the 3D volume. The succession of layers across the traces may also be used to obtain a unique set of triplets (e.g., top layer label, base layer label,PATENT Atorney Docket No.: IS24.1847-WO-PCT boundary horizon label) present in the data, defining vertical layer transitions. These unique triplets may later be used as a look-up to assign proper horizon numbers to new horizons extracted from layer predictions obtained by applying the trained model. Each extracted horizon point may separate two layers, and the transition lookup may be applied to determine which horizon number the point belongs to.

[0077] For the trace indices (I, J) within the 3D volume the method may include one or more of the following:1. Define layer boundaries in the traces as described in step 1 for 3D layer label volume generation.2. Determine the layer label for each succeeding pair of layer boundaries as described in step 2 for 3D layer label volume generation.3. For each succeeding pair of layers, defined by their pair of layer boundaries and the layer label obtained in step 2:3.1 Set the top layer label to the layer label of the shallowest layer in the pair.3.2 Set the base layer label to the layer label of the deepest layer in the pair.3.3 Set the horizon boundary to the horizon label of the boundary between the two layers, constituting the base boundary of the shallowest layer in the pair and the top layer of the deepest layer in the pair.3.4 Capture the triplet (e.g., top layer label, base layer label, boundary horizon label).

[0078] Table 1 illustrates an example of a vertical layer transition lookup, corresponding to the horizon labels and layer labels in Figures 5A and 5B. In particular, the transition definitions ensure that horizon points extracted in regions of one or more truncated horizons are associated with the correct horizon label (e.g., any horizon point separation layer label 2 and 4 should be assigned to horizon 2).PATENT Atorney Docket No.: IS24.1847-WO-PCTExemplary Method

[0079] Figure 6 illustrates a flowchart of a method 600 for predicting layers in a 3D seismic volume, according to an embodiment. An illustrative order of the method 600 is provided below; however, one or more portions of the method 600 may be performed in a different order, simultaneously, repeated, or omitted. At least a portion of the method 600 may be performed with a computing system (described below).

[0080] The method 600 may include receiving input data, as at 610. The input data may include a 3D seismic volume having a plurality of horizons. Each of the horizons may include one or more labelled horizon points.

[0081] The method 600 may also include creating a layer label volume based upon the input data, as at 620. The layer label volume may have a same size as the 3D seismic volume. Creating the layer label volume may include identifying a lateral extent of a labelled area of each of the horizons that differs from a lateral extent of the other horizons, as at 621. The area may include the labelled horizon points.

[0082] Creating the layer label volume may also include sorting the horizons based upon overlaps of the horizons, as at 622. The horizons may be sorted vertically. The overlaps may be or include lateral overlaps.

[0083] Creating the layer label volume may also include creating truncations for each of the horizons, as at 623. The truncations may vary laterally along borders of the horizons and be represented as a truncation map. The truncations may indicate where each of the horizons is truncated and to which of the horizons they are truncated. Creating the truncations may include (1) for positions along a boundary of the lateral extent of each of the horizons, determining whether each of the horizons is truncated toward a shallower one of the horizons, toward a deeper one of the horizons, or is still present in the input data but not labelled beyond the boundary. Creating the truncations may also or instead include (2) defining the lateral extent of where each horizon isPATENT Atorney Docket No.: IS24.1847-WO-PCT present in the input data as a combination of the labelled area and an area extending beyond the boundary where no truncations are detected.

[0084] Creating the layer label volume may also include populating layer labels within the input data based upon the horizons and the truncations, as at 624. The layer labels may be populated within the 3D seismic volume. Populating the layer labels may include (1) orienting the layer labels vertically at any lateral position by allowing the horizons to define vertically succeeding pairs of layer boundaries. Populating the layer labels may also or instead include (2) determining the layer labels between any pair of labelled horizons based upon the truncations of a remaining portion of the horizons.

[0085] The method 600 may also include identifying which horizon label is present as the boundary between any of the vertically succeeding pairs based upon the input data and the populated layer labels, as at 630.

[0086] The method 600 may also include displaying the layer label volume, the horizons, the truncations, the layer labels, horizon label(s), or a combination thereof, as at 640.

[0087] The method 600 may also include performing a wellsite action, as at 650. The wellsite action may be based upon or in response to the layer label volume, the horizons, the truncations, the layer labels, horizon label(s), or a combination thereof. The wellsite action may be or include generating and / or transmitting a signal (e.g., using a computing system) that instructs or causes a physical action to occur at a wellsite. The wellsite action may also or instead include performing the physical action at the wellsite. The physical action may include selecting where to drill a wellbore, drilling the wellbore, varying a weight and / or torque on a drill bit that is drilling the wellbore, varying a drilling trajectory of the wellbore, varying a concentration and / or flow rate of a fluid pumped into the wellbore, or the like.

[0088] Figure 7 illustrates a flowchart of a method 700 for generating a closed layer model of a subsurface, according to an embodiment. The closed layer model may be a closed layer model of a subsurface of a geological region. An illustrative order of the method 700 is provided below; however, one or more portions of the method 700 may be performed in a different order, simultaneously, repeated, or omitted. At least a portion of the method 700 may be performed with a computing system (described below).

[0089] The method 700 may include receiving input data including a 3D seismic volume including a plurality of horizons, as at 702. For example, the method 700 may include receiving input dataPATENT Atorney Docket No.: IS24.1847-WO-PCT including the 3D seismic volume associated with the subsurface of the geological region. The 3D seismic volume may include a plurality of horizons. Each horizon of the plurality of horizons may include a respective labeled area. Each horizon of the plurality of horizons may include one or more horizon points. The respective labeled area of each horizon of the plurality of horizons may include the one or more horizon points. Each horizon point of the one or more horizon points may include an ordered triple. The ordered triple may include a vertical coordinate and two lateral coordinates. The two lateral coordinates may correspond to or may be associated with lateral positions of a seismic trace of the 3D seismic volume. A first lateral coordinate may correspond to an x-coordinate of the respective horizon. A second lateral coordinate may correspond to a y- coordinate of the respective horizon. The vertical coordinate may correspond to or be associated with a seismic time or depth domain of the 3D seismic volume.

[0090] The method 700 may also include identifying labeled areas of the plurality of horizons based on the input data to produce identified labeled areas for the plurality of horizons, as at 704. For example, the method 700 may include identifying a respective labeled area of each horizon of a plurality of horizons based on the input data to produce an identified labeled area for each horizon of the plurality of horizons. The respective labeled area may be identified based on the one or more horizon points. The respective labeled area may be identified based on the two lateral coordinates of the one or more horizon points. The respective identified labeled area may be identified as a sparce labeled area or a continuous labeled area.

[0091] The method 700 may also include determining lateral extents of the identified labeled areas based on the input data, as at 706. For example, the method 700 may include determining a respective lateral extent of the identified labeled area of each horizon of the plurality of horizons based on the input data. The respective lateral extent of each identified labeled area of each horizon may be identified based on the one or more horizon points. Determining 706 the respective lateral extent of the identified labeled area of each horizon may include determining the respective lateral extent of the sparce labeled area, the continuous labeled area, or a combination thereof.

[0092] Determining 706 the respective lateral extent of the sparce labeled area may include identifying a minimum line and a maximum line in a first lateral direction of each horizon based on the one or more horizon points. Determining 706 the respective lateral extent of the sparce labeled area may also include identifying a minimum line and a maximum line in a second lateral direction of each horizon based on the one or more horizon points. Determining 706 the respectivePATENT Atorney Docket No.: IS24.1847-WO-PCT lateral extent of the sparce labeled area may further include generating a respective closed polygon for each horizon of the plurality of horizons based on the respective minimum line in the first lateral direction, the respective maximum line in the first direction, the respective minimum line in the second lateral direction, and the respective maximum line in the second direction.

[0093] Determining 706 the respective lateral extent of the continuous labeled area may include identifying a respective void area for each horizon of the plurality of horizons based on the input data. The void area may be identified based on the one or more horizon points of each horizon of the plurality of horizons. The void area may be identified based on the absence of the one or more horizon points of each horizon of the plurality of horizons. It should be appreciated that the boundary of the voids may be evaluated or checked to determine if the horizon is truncated or not within the void, similar to the external area. For example, it may be determined if the void is internal to the labelled area or if the void may be considered as a part of the external area with its own set of internal boundary points.

[0094] Determining 706 the respective lateral extent of the identified labeled area of each horizon may also include identifying a respective external area for each horizon of the plurality of horizons based on the input data. The external area may be identified based on the one or more horizon points and a respective edge of each horizon of the plurality of horizons. Determining 706 the respective lateral extent of the identified labeled area of each horizon may further include identifying a respective border of the lateral extent of the continuous labeled area based on the respective external area, the respective void area, the respective one or more horizon points, or a combination thereof. Determining 706 the respective lateral extent of the identified labeled area of each horizon may also include determining the respective lateral extent of the identified labeled area of each horizon based on the border or the closed polygon.

[0095] The method 700 may include sorting the plurality of horizons vertically based on the respective lateral extent of the identified labeled area of each horizon of the plurality of horizons, as at 708. For example, the method 700 may include sorting the plurality of horizons vertically based on the respective lateral extent of the identified labeled area of each horizon of the plurality of horizons. Sorting 708 the plurality of horizons vertically may produce a plurality of sorted horizons. Sorting 708 the plurality of horizons vertically may include determining a relative vertical position of each horizon of the plurality of horizon based on a respective overlap between two or more horizons of the plurality of horizons.PATENT Atorney Docket No.: IS24.1847-WO-PCT

[0096] The method 700 may also include identifying boundary points of the plurality of horizons based on the lateral extents, as at 710. For example, the method 700 may also include identifying boundary points of each horizon of the plurality of horizons based on the respective lateral extent. The boundary points of each horizon of the plurality of horizons may be based on the respective closed polygon or the border of the respective lateral extent thereof.

[0097] The method 700 may further include creating truncation maps for the plurality of horizons based on the boundary points of the plurality of horizons, as at 712. For example, the method 700 may further include creating a truncation map for each horizon of the plurality of horizons based on the respective boundary points of each horizon of the plurality of horizons. The truncation map for each horizon may identify the lateral extent where the respective horizon is present and not present. The truncation map for each horizon may define the respective lateral extent of each horizon present in the input data as a combination of the respective labeled area and an extended area beyond the boundary points where no truncations are identified.

[0098] Creating 712 the truncation map for each horizon of the plurality of horizons may include consecutively identifying each horizon of the plurality of sorted horizons based on a respective depth thereof. The plurality of sorted horizons may be consecutively identified in a direction from shallowest to deepest. The plurality of sorted horizons may be consecutively identified by numbering from shallowest to deepest.

[0099] Creating 712 the truncation map for each horizon of the plurality of horizons may also include interpolating a respective depth of each horizon of the plurality of sorted horizons based on the respective one or more horizon points thereof. The respective depth of each horizon of the plurality of sorted horizons may be based on the vertical coordinate of at least one horizon point of the one or more horizon points.

[0100] Creating 712 the truncation map for each horizon of the plurality of horizons may further include assigning a truncation value for each boundary point of the respective boundary points of each horizon of the plurality of horizons based on the respective one or more horizon points, the respective boundary points, the respective vertical coordinate, or any combination thereof, of an adjacent horizon of the plurality of sorted horizons. The truncation value for each boundary point of the respective boundary points may indicate that the horizon is truncated shallower, truncated deeper, or not truncated. The truncation value for each boundary point of the respective boundary points may identify a proximal horizon to which the horizon is truncated.PATENT Atorney Docket No.: IS24.1847-WO-PCT

[0101] Creating 712 the truncation map for each horizon of the plurality of horizons may also include extrapolating the truncation value for at least one boundary point of the respective boundary points beyond the respective lateral extent of the identified labeled area based on the respective truncation value for each boundary point of all the boundary points.

[0102] Creating 712 the truncation map for each horizon may also include creating the truncation map for each horizon of the plurality of horizons based on the truncation value for each boundary point of the respective boundary points of each horizon.

[0103] The method 700 may also include generating the closed layer model based on the plurality of horizons and the truncation maps thereof, as at 714. For example, the method 700 may also include generating the closed layer model of the subsurface of the geological region based on the plurality of horizons and the truncation map of each horizon of the plurality of horizons. The closed layer model may include a plurality of layers, a plurality of layer boundaries defining the plurality of layers, and a plurality of layer labels identifying the plurality of layers. Each pair of adjacent layer boundaries of the plurality of layer boundaries may define a respective layer of the plurality of layers. Generating 714 the closed layer model may include populating the plurality of layer labels of the closed layer model based on the plurality of horizons and the truncation map of each horizon of the plurality of horizons to generate the closed layer model. Populating the plurality of layer labels may include defining the plurality of layer boundaries of the closed layer model based on the plurality of horizons. Populating the plurality of layer labels may include determining a respective layer label for each layer of the plurality of layers based on at least one horizon of the plurality of horizons disposed in the respective layer and the truncation map of the respective truncation map of the at least one horizon.

[0104] The method 700 may also include identifying a respective horizon label present between two or more vertically succeeding pairs of layers of the plurality of layers based on the input data and the plurality of layer labels.

[0105] The method 700 may also include displaying an output. For example, the method 700 may also include displaying the closed layer model or a portion thereof, as at 716. For example, the method 700 may include displaying one or more of the plurality of horizons and / or one or more horizons thereof, the respective labelled area of one or more horizons of the plurality of horizons, the respective identified area of one or more horizons of the plurality of horizons, the respective lateral extent of one or more horizons of the plurality of horizons, the plurality of sorted horizons,PATENT Atorney Docket No.: IS24.1847-WO-PCT the respective boundary points of one or more horizons of the plurality of horizons, the respective truncation map of one or more horizons of the plurality of horizons, one or more layer labels of the plurality of layer labels, the horizon labels, or any combination thereof.

[0106] The method 700 may also include performing an action in response to displaying the closed layer model or the portion thereof, as at 718. The action may be or include generating and / or transmitting a signal that recommends, instructs, or causes a physical action to occur. The physical action may be or include one or more of optimizing a trajectory of a wellbore drilling operation, conducting drilling operations, conducting an exploratory operation, utilizing a singleupscaled permeability model in a simulation model, designing a production strategy, designing a hydraulic fracturing strategy, conducting risk assessments, or any combination thereof. The physical action may also be or include one or more of selecting where to drill a wellbore, drilling the wellbore, varying a weight and / or torque on a drill bit that is drilling the wellbore, determining a location and / or amount of hydrocarbons in a subsurface formation and then varying a drilling trajectory of the wellbore toward the hydrocarbons, varying a concentration and / or flow rate of a fluid pumped into the wellbore, or a combination thereof.Exemplary Computing System

[0107] In some embodiments, the methods of the present disclosure may be executed by a computing system. Figure 8 illustrates an example of such a computing system 800, in accordance with some embodiments. The computing system 800 may include a computer or computer system 801A, which may be an individual computer system 801A or an arrangement of distributed computer systems. The computer system 801A includes one or more analysis modules 802 that are configured to perform various tasks according to some embodiments, such as one or more methods disclosed herein. To perform these various tasks, the analysis module 802 executes independently, or in coordination with, one or more processors 804, which is (or are) connected to one or more storage media 806. The processor(s) 804 is (or are) also connected to a network interface 807 to allow the computer system 801 A to communicate over a data network 809 with one or more additional computer systems and / or computing systems, such as 80 IB, 801C, and / or 80 ID (note that computer systems 80 IB, 801C and / or 80 ID may or may not share the same architecture as computer system 801 A, and may be located in different physical locations, e.g., computer systems 801 A and 80 IB may be located in a processing facility, while in communicationPATENT Atorney Docket No.: IS24.1847-WO-PCT with one or more computer systems such as 801 C and / or 80 ID that are located in one or more data centers, and / or located in varying countries on different continents).

[0108] A processor may include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.

[0109] The storage media 806 may be implemented as one or more computer-readable or machine- readable storage media. Note that while in the example embodiment of Figure 8 storage media 806 is depicted as within computer system 801A, in some embodiments, storage media 806 may be distributed within and / or across multiple internal and / or external enclosures of computing system 801A and / or additional computing systems. Storage media 806 may include one or more different forms of memory including semiconductor memory devices such as dynamic or static random access memories (DRAMs or SRAMs), erasable and programmable read-only memories (EPROMs), electrically erasable and programmable read-only memories (EEPROMs) and flash memories, magnetic disks such as fixed, floppy and removable disks, other magnetic media including tape, optical media such as compact disks (CDs) or digital video disks (DVDs), B LURAY® disks, or other types of optical storage, or other types of storage devices. Note that the instructions discussed above may be provided on one computer-readable or machine-readable storage medium, or may be provided on multiple computer-readable or machine-readable storage media distributed in a large system having possibly plural nodes. Such computer-readable or machine-readable storage medium or media is (are) considered to be part of an article (or article of manufacture). An article or article of manufacture may refer to any manufactured single component or multiple components. The storage medium or media may be located either in the machine running the machine-readable instructions, or located at a remote site from which machine-readable instructions may be downloaded over a network for execution.

[0110] In some embodiments, computing system 800 contains one or more method execution module(s) 808. In the example of computing system 800, computer system 801A includes the method execution module 808. In some embodiments, a single method execution module may be used to perform some aspects of one or more embodiments of the methods disclosed herein. In other embodiments, a plurality of method execution modules may be used to perform some aspects of methods herein.PATENT Atorney Docket No.: IS24.1847-WO-PCT

[0111] It should be appreciated that computing system 800 is merely one example of a computing system, and that computing system 800 may have more or fewer components than shown, may combine additional components not depicted in the example embodiment of Figure 8, and / or computing system 800 may have a different configuration or arrangement of the components depicted in Figure 8. The various components shown in Figure 8 may be implemented in hardware, software, or a combination of both hardware and software, including one or more signal processing and / or application specific integrated circuits.

[0112] Further, the steps in the processing methods described herein may be implemented by running one or more functional modules in information processing apparatus such as general purpose processors or application specific chips, such as ASICs, FPGAs, PLDs, or other appropriate devices. These modules, combinations of these modules, and / or their combination with general hardware are included within the scope of the present disclosure.

[0113] Computational interpretations, models, and / or other interpretation aids may be refined in an iterative fashion; this concept is applicable to the methods discussed herein. This may include use of feedback loops executed on an algorithmic basis, such as at a computing device (e.g., computing system 800, Figure 8), and / or through manual control by a user who may make determinations regarding whether a given step, action, template, model, or set of curves has become sufficiently accurate for the evaluation of the subsurface three-dimensional geologic formation under consideration.

[0114] The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or limiting to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. Moreover, the order in which the elements of the methods described herein are illustrated and described may be re-arranged, and / or two or more elements may occur simultaneously. The embodiments were chosen and described in order to best explain the principles of the disclosure and its practical applications, to thereby enable others skilled in the art to best utilize the disclosed embodiments and various embodiments with various modifications as are suited to the particular use contemplated.

Claims

PATENT Atorney Docket No.: IS24.1847-WO-PCTCLAIMSWhat is claimed is:CLAIMSWhat is claimed is:

1. A method for generating a closed layer model of a subsurface, the method comprising: receiving input data comprising a 3D seismic volume including a plurality of horizons; identifying labeled areas of the plurality of horizons based on the input data; determining lateral extents of the identified labeled areas based on the input data; sorting the plurality of horizons based on the lateral extents; identifying boundary points of the plurality of sorted horizons based on the lateral extents; creating truncation maps for the plurality of sorted horizons based on the boundary points thereof; and generating the closed layer model based on the plurality of horizons and the truncation maps thereof.

2. The method of claim 1, wherein each horizon of the plurality of horizons comprises a respective labeled area of the labeled areas, wherein the respective labeled area of each horizon comprises one or more horizon points, wherein identifying the labeled areas of the plurality of horizons comprises identifying the respective labeled area of each horizon to produce a respective identified labeled area, and wherein the respective identified labeled area is identified as a sparce labeled area or a continuous labeled area.

3. The method of claim 2, wherein determining the lateral extents of the identified labeled areas comprises determining a respective lateral extent of the sparce labeled area, the continuous labeled area, or a combination thereof.

4. The method of claim 3, wherein determining the respective lateral extent of the sparce labeled area comprises:PATENT Atorney Docket No.: IS24.1847-WO-PCT generating a closed polygon for the sparce labeled area of at least one horizon of the plurality of horizons based on the one or more horizon points thereof; and determining the lateral extent of the sparce labeled area of the at least one horizon based on the closed polygon.

5. The method of claim 3, wherein determining the respective lateral extent of the continuous labeled area comprises: identifying a border of the continuous labeled area of at least one horizon of the plurality of horizons based on the one or more horizon points thereof; and determining the lateral extent of the continuous labeled area of the at least one horizon based on the border thereof.

6. The method of claim 1, wherein creating the truncation maps for the plurality of horizons comprises: consecutively identifying each horizon of the plurality of sorted horizons based on a respective depth thereof; interpolating the respective depth of each horizon of the plurality of sorted horizons based on the one or more horizon points thereof; assigning a truncation value for each boundary point of the respective boundary points of each horizon of the plurality of sorted horizons based on the respective one or more horizon points, the respective boundary points, or any combination thereof, of an adjacent horizon of the plurality of sorted horizons; and creating the truncation maps for the plurality of horizons based on the truncation value for each boundary point of the respective boundary points of each horizon of the plurality of sorted horizons.

7. The method of claim 1, wherein the closed layer model comprises a plurality of layers, a plurality of layer boundaries defining the plurality of layers, and a plurality of layer labels identifying the plurality of layers, and wherein generating the closed layer model comprises populating the plurality of layer labels of the closed layer model based on the plurality of horizons and the truncation maps thereof.PATENT Atorney Docket No.: IS24.1847-WO-PCT8. The method of claim 7, wherein populating the plurality of layer labels comprises: defining the plurality of layer boundaries of the closed layer model based on the plurality of horizons; and determining a respective layer label for each layer of the plurality of layers based on at least one horizon of the plurality of horizons disposed in the respective layer and the respective truncation map of the at least one horizon.

9. The method of claim 1, further comprising displaying the closed layer model or a portion thereof.

10. The method of claim 1, further comprising performing an action in response to generating the closed layer model, wherein the action comprises generating or transmitting a signal that recommends, instructs, or causes a physical action to occur, wherein the physical action comprises one or more of selecting where to drill a wellbore, drilling the wellbore, varying a weight and / or torque on a drill bit that is drilling the wellbore, determining a location and / or amount of hydrocarbons in a subsurface formation and then varying a drilling trajectory of the wellbore toward the hydrocarbons, varying a concentration and / or flow rate of a fluid pumped into the wellbore, or a combination thereof.

11. A computing system, comprising: one or more processors; and a memory system comprising one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations for generating a closed layer model of a subsurface, the operations comprising: receiving input data comprising a 3D seismic volume associated with the subsurface, wherein the 3D seismic volume comprises a plurality of horizons, wherein each horizon of the plurality of horizons comprises a sparce labeled area or a continuous labeled area;PATENT Atorney Docket No.: IS24.1847-WO-PCT determining a respective lateral extent of the sparce labeled area, the continuous labeled area, or a combination thereof of each horizon based on the 3D seismic volume; sorting the plurality of horizons vertically based on the respective lateral extent of each horizon ; identifying boundary points of each horizon based on the respective lateral extent thereof; creating a truncation map for each horizon based on the respective boundary points thereof; and generating the closed layer model of the subsurface based on the plurality of horizons and the truncation map.

12. The computing system of claim 11, wherein determining the respective lateral extent of the sparce labeled area comprises: identifying a minimum line and a maximum line in a first lateral direction of at least one horizon of the plurality of horizons based on the 3D seismic volume; identifying a minimum line and a maximum line in a second lateral direction of the at least one horizon based on the 3D seismic volume; generating a respective closed polygon for the sparce labeled area based on the respective minimum lines and the respective maximum lines in the first and second directions; and determining the respective lateral extent of the sparce labeled area based on the closed polygon.

13. The computing system of claim 11, wherein determining the respective lateral extent of the continuous labeled area comprises: identifying a void area for at least one horizon of the plurality of horizons based on the 3D seismic volume; identifying a respective external area for the at least one horizon based on the 3D seismic volume; identifying a respective border of the lateral extent of the continuous labeled area based on the external area and the void area; andPATENT Atorney Docket No.: IS24.1847-WO-PCT determining the respective lateral extent of the continuous labeled area based on the border thereof.

14. The computing system of claim 11, wherein creating the truncation map for each horizon comprises: consecutively identifying each horizon by numbering from shallowest to deepest based on a respective depth thereof; assigning a respective truncation value for each boundary point of the respective boundary points of each horizon based on the 3D seismic volume; extrapolating the truncation value for at least one boundary point of the respective boundary points of at least one horizon beyond the respective lateral extent of the identified labeled area based on the respective truncation value for each boundary point of all the boundary points; and creating the truncation map for each horizon based on the truncation value for each boundary point.

15. The computing system of claim 11, wherein: the closed layer model comprises a plurality of layers, a plurality of layer boundaries defining the plurality of layers, a plurality of layer labels identifying the plurality of layers, wherein each pair of adjacent layer boundaries of the plurality of layer boundaries defines a respective layer of the plurality of layers; generating the closed layer model comprises populating the plurality of layer labels of the closed layer model based on the plurality of horizons and the truncation map of each horizon; and the operations further comprise identifying a respective horizon label present between two or more vertically succeeding pairs of layers of the plurality of layers based on the input data and the plurality of layer labels.

16. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations for generating a closed layer model of a subsurface, the operations comprising:PATENT Atorney Docket No.: IS24.1847-WO-PCT receiving input data comprising a 3D seismic volume associated with the subsurface, wherein the 3D seismic volume comprises a plurality of horizons, wherein each horizon of the plurality of horizons comprises a sparce labeled area or a continuous labeled area; determining a respective lateral extent of the sparce labeled area, the continuous labeled area, or a combination thereof for each horizon; sorting the plurality of horizons vertically based on the respective lateral extent of each horizon, wherein sorting the plurality of horizons comprises determining a relative vertical position of each horizon based on a respective overlap between two or more horizons of the plurality of horizons; identifying boundary points of each horizon based on the respective lateral extent thereof; creating a truncation map for each horizon based on the respective boundary points of each horizon of the plurality of sorted horizons; and generating the closed layer model of the subsurface based on the plurality of horizons and the truncation map of each horizon.

17. The non-transitory computer-readable medium of claim 16, wherein determining the respective lateral extent of the sparce labeled area comprises: identifying a minimum line and a maximum line in a first lateral direction of at least one horizon of the plurality of horizons based on the 3D seismic volume; identifying a minimum line and a maximum line in a second lateral direction of the at least one horizon based the 3D seismic volume; generating a respective closed polygon for the sparce labeled area of the at least one horizon based on the respective minimum lines and the respective maximum lines in the first and second lateral directions; and determining the respective lateral extent of the sparce labeled area based on the closed polygon.

18. The non-transitory computer-readable medium of claim 17, wherein determining the respective lateral extent of the continuous labeled area comprises: identifying a respective void area for at least another horizon of the plurality of horizons based on the presence or absence of one or more horizon points in the at least another horizon;PATENT Atorney Docket No.: IS24.1847-WO-PCT identifying a respective external area for the at least another horizon based on the one or more horizon points and a respective edge of the at least another horizon; identifying a respective border of the lateral extent of the continuous labeled area based on the external area, the void area, and the one or more horizon points; and determining the respective lateral extent of the continuous labeled area based on the border thereof.

19. The non-transitory computer-readable medium of claim 18, wherein creating the truncation map for each horizon of the plurality of horizons comprises: consecutively identifying each horizon from shallowest to deepest based on a respective depth thereof; and interpolating the respective depth of each horizon based on a vertical coordinate of at least one horizon point of each horizon.

20. The non-transitory computer-readable medium of claim 19, wherein creating the truncation map for each horizon further comprises: assigning a respective truncation value for each boundary point of each horizon based on the respective one or more horizon points, the respective boundary points, and the respective vertical coordinate of an adjacent horizon of the plurality of sorted horizons; extrapolating the truncation value for at least one boundary point of the plurality of horizons beyond the respective lateral extent of the identified labeled area based on the respective truncation value; and creating the truncation map for each horizon based on the truncation value the respective boundary points of each horizon.

Images