WO2025199452A1 - Identification d'anomalies liées à des hydrocarbures assistée par ia à l'aide d'un flux de travail spécifique à une tâche d'apprentissage profond optimisé - Google Patents

Identification d'anomalies liées à des hydrocarbures assistée par ia à l'aide d'un flux de travail spécifique à une tâche d'apprentissage profond optimisé

Info

Publication number
WO2025199452A1
WO2025199452A1 PCT/US2025/020932 US2025020932W WO2025199452A1 WO 2025199452 A1 WO2025199452 A1 WO 2025199452A1 US 2025020932 W US2025020932 W US 2025020932W WO 2025199452 A1 WO2025199452 A1 WO 2025199452A1
Authority
WO
WIPO (PCT)
Prior art keywords
trained
model
seismic
hydrocarbon
workstream
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/US2025/020932
Other languages
English (en)
Inventor
Arvind Sharma
Adam Niven SHUMAKER
Shashi Menon
Hiren MANIAR
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Schlumberger Canada Ltd
Services Petroliers Schlumberger SA
Geoquest Systems BV
Schlumberger Technology Corp
Original Assignee
Schlumberger Canada Ltd
Services Petroliers Schlumberger SA
Geoquest Systems BV
Schlumberger Technology Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Schlumberger Canada Ltd, Services Petroliers Schlumberger SA, Geoquest Systems BV, Schlumberger Technology Corp filed Critical Schlumberger Canada Ltd
Publication of WO2025199452A1 publication Critical patent/WO2025199452A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V20/00—Geomodelling in general
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning

Definitions

  • Identifying seismic anomalies for exploration purposes in the oil and gas industry may be challenging due to a diversity of geological settings for hydrocarbon accumulation and limitations and ambiguity of the imaging capabilities of seismic data. For this reason, geoscientists go through an extensive process of tests and validations to mature the identified seismic anomaly to a drillable prospect.
  • This may include an interpreter manually inspecting slices of 3-dimensional (3D) seismic data to identify and interpret anomalous seismic amplitudes. 3D seismic volumes viewed by the interpreter may be derived based upon seismic attributes that emphasize seismic anomalies and direct hydrocarbon fluid indicators.
  • a method for detecting hydrocarbon-related seismic anomalies includes receiving input data related to a reservoir.
  • the method also includes training an artificial intelligence (Al) model based upon the input data to produce a trained Al model.
  • the method also includes classifying seismic anomalies in the input data using the trained Al model to produce classified seismic anomalies.
  • the method also includes generating exploration tasks using the trained Al model based at least partially upon the classified seismic anomalies.
  • the exploration tasks include pay maps, confidence attributes, and/or risk resource determinations.
  • a computing system includes one or more processors and a memory system.
  • the memory 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.
  • the operations include receiving input data related to a reservoir.
  • the input data includes an interpretation workstream.
  • the interpretation workstream includes a well log interpretation, a geophysical interpretation, a stratigraphic interpretation, and/or hydrocarbon anomaly interpretations and labels.
  • the hydrocarbon anomaly interpretations and labels include a ID trace level classification mask, a 2D section level classification mask, and/or a 3D volume level classification mask that represent geological features related to seismic anomalies.
  • the operations also include training an artificial intelligence (Al) model based upon the input data to produce a trained Al model.
  • the Al model is trained based upon a subset of the hydrocarbon anomaly interpretations and labels.
  • the operations also include classifying the seismic anomalies in the input data using the trained Al model to produce classified seismic anomalies.
  • the operations also include receiving direct hydrocarbon indicator (DHI) diagnostics related to the classified seismic anomalies.
  • the operations also include attempting to validate the trained Al model based upon the classified seismic anomalies and the DHI diagnostics. Attempting to validate the trained Al model includes comparing the DHI diagnostics to the classified seismic anomalies to determine differences therebetween.
  • the operations also include re-training the trained Al model in response to the differences being greater than the predetermined thresholds to produce a re-trained Al model.
  • the operations also include generating exploration tasks using the re-trained Al model.
  • the exploration tasks include pay maps, confidence attributes, and/or risk resource determinations.
  • a non-transitory computer-readable medium stores instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations.
  • the operations include receiving input data related to a reservoir.
  • the input data includes an interpretation workstream.
  • the interpretation workstream includes a well log interpretation, a geophysical interpretation, a stratigraphic interpretation, and hydrocarbon anomaly interpretations and labels.
  • the hydrocarbon anomaly interpretations and labels include a ID trace level classification mask, a 2D section level classification mask, and a 3D volume level classification mask that represent geological features related to seismic anomalies.
  • the input data also includes a geophysical workstream.
  • the geophysical workstream includes application or generation of seismic data, amplitude versus offset (AVO)-related seismic attributes, frequency-related seismic attributes, and a rock property-related seismic inversion.
  • the input data also includes a data science workstream.
  • the data science workstream includes supervised and unsupervised learning.
  • the operations also include training an artificial intelligence (Al) model based upon the input data to produce a trained Al model.
  • the Al model is trained based upon a subset of the hydrocarbon anomaly interpretations and labels and a subset of the geophysical workstream.
  • the subset of the hydrocarbon anomaly interpretations and labels comprises the ID trace level classification mask, the 2D section level classification mask, and the 3D volume level classification mask.
  • the subset of the geophysical workstream includes the AVO-related seismic attributes.
  • the operations also include classifying the seismic anomalies in the input data using the trained Al model to produce classified seismic anomalies.
  • the operations also include receiving direct hydrocarbon indicator (DHI) diagnostics related to the classified seismic anomalies.
  • DHI direct hydrocarbon indicator
  • the operations also include attempting to validate the trained Al model based upon the classified seismic anomalies and the DHI diagnostics. Attempting to validate the trained Al model includes comparing the DHI diagnostics to the classified seismic anomalies to determine differences therebetween.
  • the trained Al model is determined to be valid in response to the differences being less than predetermined thresholds.
  • the operations also include re-training the trained Al model in response to the differences being greater than the predetermined thresholds.
  • the trained Al model is re-trained based upon a different subset of the hydrocarbon anomaly interpretations and labels and a different subset of the geophysical workstream.
  • the different subset of the hydrocarbon anomaly interpretations and labels includes rock typing features, fluid types, stacked oil pay, thin gas pay, and/or wet sand.
  • the rock typing features include a channel axis, a channel margin, and/or mudstone facies.
  • the different subset of the geophysical workstream comprises near-far to emphasize oil pay compared to sweetness to emphasize gas pay.
  • the operations also include generating exploration tasks using the re-trained Al model.
  • the exploration tasks include pay maps, confidence attributes, and/or risk resource determinations.
  • the pay maps include a two-dimensional (2D) net thickness of hydrocarbon pay in the reservoir.
  • the confidence attributes include a likelihood of the hydrocarbon pay in the reservoir.
  • the risk resource determinations include an aggregate risk-weighted estimation of the net thickness and gross resources of the reservoir.
  • 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.
  • Figure 2 illustrates a schematic view of a model application framework, according to an embodiment.
  • Figure 3 illustrates a flowchart of a method for detecting hydrocarbon related seismic anomalies, according to an embodiment.
  • Figure 4 illustrates a schematic view of an interdisciplinary Al model -building framework that may perform at least a portion of the method, according to an embodiment.
  • Figure 5 illustrates a cross-sectional side view of a reservoir where direct hydrocarbon indicator (DHI) diagnostics provide a model validation control point in a three-dimensional geologic context, according to an embodiment.
  • DHI direct hydrocarbon indicator
  • Figures 6A-6D illustrate images of seismic sections, according to an embodiment.
  • Figures 7A-7D illustrate indicative labels relevant to DHI anomaly facies in comparison to seismic waveforms, according to an embodiment.
  • Figure 8 illustrates an annotated seismic section demonstrating how DHI-calibrated seismic anomalies at a first wellbore and a second (e.g., sidetrack) wellbore in a reservoir can be used to assess the likelihood of pay in a separate reservoir, according to an embodiment.
  • Figure 9 illustrates a schematic view of a computing system for performing at least a portion of the method, according to an embodiment.
  • 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.
  • 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.
  • FIG 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.).
  • the management components 110 may allow for direct or indirect management of sensing, drilling, injecting, extracting, etc., with respect to the geologic environment 150.
  • 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).
  • 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.
  • seismic data and other information provided per the components 112 and 114 may be input to the simulation component 120.
  • 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.
  • the entities 122 can 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.
  • the simulation component 120 may operate in conjunction with a software framework such as an object-based framework.
  • entities may include entities based on pre-defined classes to facilitate modeling and simulation.
  • a software framework such as an object-based framework.
  • objects may include entities based on pre-defined classes to facilitate modeling and simulation.
  • An object-based framework is the MICROSOFT® .NET® framework (Redmond, Washington), which provides a set of extensible object classes.
  • .NET® framework an object class encapsulates a module of reusable code and associated data structures.
  • Object classes can be used to instantiate object instances for use in by a program, script, etc.
  • borehole classes may define objects for representing boreholes based on well data.
  • 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.
  • the simulation component 120 may include one or more features of a simulator such as the ECLIPSETM reservoir simulator (SLB, Houston Texas), the INTERSECTTM reservoir simulator (SLB, Houston Texas), etc.
  • 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 ).
  • 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 ).
  • 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 can 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.
  • the simulation component 120 may include one or more features of a simulator such as PIPESIM (SLB, Houston, Texas). More particularly, PIPESIM is steady-state multiphase flow simulator that incorporates the three areas of flow modeling: multiphase flow, heat transfer and fluid behavior.
  • PIPESIM is steady-state multiphase flow simulator that incorporates the three areas of flow modeling: multiphase flow, heat transfer and fluid behavior.
  • 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 can output information for use in increasing reservoir performance, for example, by improving asset team productivity.
  • various professionals e.g., geophysicists, geologists, and reservoir engineers
  • 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.).
  • various aspects of the management components 110 may include add-ons or plug-ins that operate according to specifications of a framework environment.
  • a framework environment e.g., 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.
  • 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.).
  • API application programming interface
  • 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.
  • the PETREL® software may be considered a data-driven application.
  • the PETREL® software can include a framework for model building and visualization.
  • a framework may include features for implementing one or more mesh generation techniques.
  • 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.
  • 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 can display their data while the user interfaces 188 may provide a common look and feel for application user interface components.
  • the domain objects 182 can include entity objects, property objects and optionally other objects.
  • Entity objects may be used to geometrically represent wells, surfaces, bodies, reservoirs, etc.
  • property objects may be used to provide property values as well as data versions and display parameters.
  • 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).
  • 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 can be accessed and restored using the model simulation layer 180, which can recreate instances of the relevant domain objects.
  • 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.
  • the geologic environment 150 may be outfitted with any of a variety of sensors, detectors, actuators, etc.
  • 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.
  • one or more satellites may be provided for purposes of communications, data acquisition, etc.
  • 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.).
  • imagery e.g., spatial, spectral, temporal, radiometric, etc.
  • 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.
  • equipment 157 and 158 associated with a well that includes a substantially horizontal portion that may intersect with one or more fractures 159.
  • a well in a shale formation may include natural fractures, artificial fractures (e.g., hydraulic fractures) or a combination of natural and artificial fractures.
  • a well may be drilled for a reservoir that is laterally extensive.
  • 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.).
  • 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.
  • 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.
  • a may operate on one or more inputs and create one or more results, for example, based on one or more algorithms.
  • a system may include a workflow editor for creation, editing, executing, etc. of a workflow.
  • the workflow editor may provide for selection of one or more predefined worksteps, one or more customized worksteps, etc.
  • a workflow may be a workflow implementable in the PETREL " software, for example, that operates on seismic data, seismic attribute(s), etc.
  • a workflow may be a process implementable in the OCEAN® framework.
  • a workflow may include one or more worksteps that access a module such as a plug-in (e.g., external executable code, etc.).
  • a plug-in e.g., external executable code, etc.
  • the present disclosure describes a generalized artificial intelligence (Al)-based method for hydrocarbon-related seismic anomaly detection.
  • the method may be applied to a defined global play type including, but not limited to, Class II deep water channel sands or Class III gas saturated carbonates.
  • the embodiments provide an optimized deep learning pipeline that automatically identifies and rates seismic anomalies in service of accelerating and improving exploration processes and workstreams.
  • the method may be used to perform geophysical prospecting such as hydrocarbon anomaly detection risk assessment.
  • the method may use machine learning (ML)-generated geophysical features as input into a deep learning model that infers a location and a likelihood of a subsurface hydrocarbon deposit.
  • ML machine learning
  • Another aspect of the method is the optimization scheme used to select optimal geophysical features for each desired geophysical play type.
  • the method may be or include a deep learning method that encodes multi-dimensional geophysical input to automatically identify seismic anomalies related to pay.
  • Figure 2 illustrates a model application framework 200, according to an embodiment.
  • the framework may develop generalized artificial intelligence for hydrocarbon related seismic anomaly detection with the direct scope of this development applied to a defined global play type such as Class II deep water channel sands.
  • the output of this framework may be an optimized deep learning pipeline that automatically identifies and rates seismic anomalies in service of accelerating and improving exploration processes and workstreams.
  • seismic data from basins 202, 204 may be applied to a trained model 208.
  • the trained model 208 may be used to classify seismic data from the basins 202, 204 with regard to a Class II play type.
  • a tuned model 210 may be produced by, for example, further training the trained model 208, using seismic data from basin 206 and/or training labels 212, to produce the tuned model 210.
  • the tuned model 210 may classify seismic data from the basin 206 with regard to the Class II play type and a Class III play type.
  • Outputs of the trained model 208 and/or the tuned model 210 then may be provided to exploration tasks 214, which may provide or include pay maps 216, confidence attributes 218, and risk and resource information 220.
  • Figure 3 illustrates a flowchart of a method 300 for detecting hydrocarbon-related seismic anomalies, according to an embodiment.
  • the method 300 may build and train seismic anomaly identification models.
  • the method 300 may be performed in close collaboration with interpreters, geophysicists, data scientists/or and Al-platform architects to build and validate model output in the context of industry exploration processes.
  • the output(s) of the method 300 may be or include interpretation training labels, geophysical attribute and anomaly inference volumes, and their respective trained models. These models may be used to detect hydrocarbon anomalies on new, unseen seismic or be used to quantify differences between anomalies within a seismic survey.
  • FIG. 3 An illustrative order of the method 300 is provided below; however, one or more portions of the method 300 may be performed in a different order, simultaneously, repeated, or omitted. At least a portion of the method 300 may be performed by a computing system (described below).
  • Figure 4 illustrates an interdisciplinary Al-model building framework 400 that may be used to perform at least a portion of the method 300, according to an embodiment.
  • the method 300 may include receiving input data related to a first reservoir, as at 305.
  • the input data may include an interpretation workstream (405A in Figure 4) that includes a well log interpretation, a geophysical interpretation, a stratigraphic interpretation, hydrocarbon anomaly interpretations and labels, or a combination thereof.
  • the hydrocarbon anomaly interpretations and labels may include a ID trace level classification mask, a 2D section level classification mask, and/or a 3D volume level classification mask that represent geological features related to seismic anomalies.
  • the input data may also or instead include a geophysical workstream (405B in Figure 4) that includes application or generation of seismic data, amplitude versus offset (AVO)-related seismic attributes, frequency-related seismic attributes, rock property-related seismic inversion, or a combination thereof.
  • the input data may also or instead include a data science workstream (405C in Figure 4) that includes supervised and/or unsupervised learning.
  • the method 300 may also include training an artificial intelligence (Al) model based upon the input data to produce a trained Al model, as at 310. This is shown at 410 in Figure 4.
  • the Al model may be trained based upon a subset of the hydrocarbon anomaly interpretations and labels and/or a subset of the geophysical workstream.
  • the subset of the hydrocarbon anomaly interpretations and labels may include the ID trace level classification mask, the 2D section level classification mask, and/or the 3D volume level classification mask.
  • the subset of the geophysical workstream may include the AVO-related seismic attributes.
  • the method 300 may also include classifying the seismic anomalies in the input data using the trained Al model to produce classified seismic anomalies, as at 315.
  • the method 300 may also include receiving direct hydrocarbon indicator (DHI) diagnostics related to the classified seismic anomalies, as at 320. This is shown at 420 in Figure 4.
  • Figure 5 illustrates a cross-sectional side view of a reservoir 510 where direct hydrocarbon indicator (DHI) diagnostics provide a model validation control point in a three- dimensional geologic context, according to an embodiment.
  • the reservoir 510 may include an updip wellbore 520 with oil pay and a downdip wellbore 530 that is wet.
  • the DHI diagnostics may lie away from a well control and between the updip wellbore and the downdip well bore, indicating a presence of a fluid contact 540.
  • the fluid contact 540 may be manifested as a phase change, a downdip amplitude conformance, an amplitude anomaly strength above background, a lateral amplitude conformance, a dim spot, a flat spot, or a combination thereof.
  • Figures 6A-6D illustrate images of seismic sections, according to an embodiment. More particularly, Figure 6A illustrates an image of a seismic section indicating direct hydrocarbon indicators, Figure 6B illustrates an image of a seismic section showing unconstrained seismic anomaly detection, Figure 6C illustrates an image of a seismic section showing DHI-focused seismic anomaly labels, and Figure 6D illustrates an image of a seismic section showing DHI- constrained seismic anomaly detection.
  • Figures 7A-7D illustrate indicative labels relevant to DHI anomaly facies in comparison to seismic waveforms, according to an embodiment. More particularly, Figure 7A illustrates stacked pay (on the left) in comparison to the corresponding seismic waveform (on the right), Figure 7B illustrates thin pay (on the left) in comparison to the corresponding seismic waveform (on the right), Figure 7C illustrates a fluid contact (on the left) in comparison to the corresponding seismic waveform (on the right), and Figure 7D illustrates wet (on the left) in comparison to the corresponding seismic waveform (on the right).
  • the method 300 may also include attempting to validate the trained Al model based upon the classified seismic anomalies and the DHI diagnostics, as at 325. Attempting to validate the trained Al model may include comparing the DHI diagnostics to the classified seismic anomalies to determine differences therebetween. The trained Al model may be determined to be valid in response to the differences being less than predetermined thresholds.
  • the method 300 may also include re-training the trained Al model in response to the differences being greater than the predetermined thresholds, as at 330.
  • the trained Al model may be re-trained based upon a different subset of the hydrocarbon anomaly interpretations and labels and a different subset of the geophysical workstream.
  • the different subset of the hydrocarbon anomaly interpretations and labels may be or include rock typing features, fluid types, stacked oil pay, thin gas pay, wet sand, or a combination thereof.
  • the rock typing features may include a channel axis, a channel margin, mudstone facies, or a combination thereof.
  • the different subset of the geophysical workstream may be or include near-far to emphasize the oil pay compared to sweetness to emphasize gas pay.
  • the method 300 may also include generating exploration tasks using the re-trained Al model, as at 335. This is shown at 435 in Figure 4.
  • the exploration tasks may be or include pay maps 436, confidence attributes 437, and/or risk resource determinations 438.
  • the pay maps may be or include a two-dimensional (2D) net thickness of hydrocarbon pay in the first reservoir.
  • the confidence attributes may include a likelihood of the hydrocarbon pay in the first reservoir.
  • the risk resource determinations may be or include an aggregate risk-weighted estimation of the net thickness and gross resources of the first reservoir.
  • Figure 8 illustrates an annotated seismic section demonstrating how DHI-calibrated seismic anomalies at a first wellbore and a second wellbore can be used to assess the likelihood of pay in a separate reservoir, according to an embodiment.
  • the exploration tasks may include evaluating a play that includes a plurality of reservoirs including the first reservoir 810, a second reservoir 820, and a potential/undrilled third reservoir 830.
  • the first reservoir 810 may include a first wellbore 812 with the oil pay.
  • the second wellbore 822 may include a sidetrack from the first wellbore 812 into the second reservoir 820.
  • the second reservoir 820 may be wet.
  • the classified seismic anomalies may be used to assess a likelihood of the oil pay in a planned wellbore in the potential/undrilled third reservoir 830.
  • the method 300 may also include displaying the exploration tasks, as at 340.
  • the method 300 may also include performing an action in response to the exploration tasks, as at 345.
  • the action may be or include generating and/or transmitting a signal that recommends, instructs, or causes a physical action to occur at a wellsite that is proximate to the reservoir.
  • the physical action may be or 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, or varying a concentration and/or flow rate of a fluid pumped into the wellbore.
  • the method 300 may generalize over a large set of success and failure instances and apply the same set of standards when assessing each case. This makes possible the detection of potential exploration successes or failures in a more consistent manner.
  • the method 300 may allow a user to train a model to identify deposits that are wet or have pay in a known geological setting and then apply the learnings to a new frontier area to identify prospects.
  • the method 300 may also allow the user to quantify differences between prospects within a given 3D survey and across surveys.
  • the method 300 may also allow the user to generate pay maps, update previous seismic interpretations, inform appraisal and development work, and/or identify drilling hazards.
  • the methods of the present disclosure may be executed by one or more computing systems.
  • Figure 9 illustrates an example of such a computing system 900, in accordance with some embodiments.
  • the computing system 900 may include a computer or computer system 901 A, which may be an individual computer system 901 A or an arrangement of distributed computer systems.
  • the computer system 901 A includes one or more analysis modules 402 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 902 executes independently, or in coordination with, one or more processors 904, which is (or are) connected to one or more storage media 906.
  • the processor(s) 904 is (or are) also connected to a network interface 907 to allow the computer system 901 A to communicate over a data network 909 with one or more additional computer systems and/or computing systems, such as 901B, 901C, and/or 901D (note that computer systems 901B, 901C and/or 901D may or may not share the same architecture as computer system 901A, and may be located in different physical locations, e.g., computer systems 901 A and 901B may be located in a processing facility, while in communication with one or more computer systems such as 901 C and/or 901D that are located in one or more data centers, and/or located in varying countries on different continents).
  • additional computer systems and/or computing systems such as 901B, 901C, and/or 901D
  • computer systems 901B, 901C and/or 901D may or may not share the same architecture as computer system 901A, and may be located in different physical locations, e.g., computer systems 901 A
  • a processor may include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.
  • the storage media 906 may be implemented as one or more computer-readable or machine-readable storage media. Note that while in the example embodiment of Figure 9 storage media 906 is depicted as within computer system 901A, in some embodiments, storage media 906 may be distributed within and/or across multiple internal and/or external enclosures of computing system 901A and/or additional computing systems.
  • Storage media 906 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), BLURAY® disks, or other types of optical storage, or other types of storage devices.
  • 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)
  • DVDs digital video disks
  • 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.
  • computing system 900 contains one or more method execution module(s) 908.
  • computer system 901A includes the method execution module 908.
  • a single method execution module may be used to perform some aspects of one or more embodiments of the methods disclosed herein.
  • a plurality of method execution modules may be used to perform some aspects of methods herein.
  • computing system 900 is merely one example of a computing system, and that computing system 900 may have more or fewer components than shown, may combine additional components not depicted in the example embodiment of Figure 9, and/or computing system 900 may have a different configuration or arrangement of the components depicted in Figure 9.
  • the various components shown in Figure 9 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.
  • 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.
  • ASICs general purpose processors or application specific chips, such as ASICs, FPGAs, PLDs, or other appropriate devices.
  • 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 900, Figure 9), 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.
  • a computing device e.g., computing system 900, Figure 9

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Geophysics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Geophysics And Detection Of Objects (AREA)

Abstract

Un procédé de détection d'anomalies sismiques liées à des hydrocarbures consiste à recevoir des données d'entrée associées à un réservoir. Le procédé consiste également à entraîné un modèle d'intelligence artificielle (IA) sur la base des données d'entrée pour produire un modèle d'IA entraîné. Le procédé consiste en outre à classer des anomalies sismiques dans les données d'entrée à l'aide du modèle d'IA entraîné pour obtenir des anomalies sismiques classées. Le procédé consiste également à générer des tâches d'exploration à l'aide du modèle d'IA entraîné sur la base, au moins partiellement, des anomalies sismiques classées. Les tâches d'exploration comprennent la détermination de cartes d'exploitabilité, d'attributs de confiance et/ou de ressources à risque.
PCT/US2025/020932 2024-03-21 2025-03-21 Identification d'anomalies liées à des hydrocarbures assistée par ia à l'aide d'un flux de travail spécifique à une tâche d'apprentissage profond optimisé Pending WO2025199452A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202463568265P 2024-03-21 2024-03-21
US63/568,265 2024-03-21

Publications (1)

Publication Number Publication Date
WO2025199452A1 true WO2025199452A1 (fr) 2025-09-25

Family

ID=97140319

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2025/020932 Pending WO2025199452A1 (fr) 2024-03-21 2025-03-21 Identification d'anomalies liées à des hydrocarbures assistée par ia à l'aide d'un flux de travail spécifique à une tâche d'apprentissage profond optimisé

Country Status (1)

Country Link
WO (1) WO2025199452A1 (fr)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110272161A1 (en) * 2010-05-06 2011-11-10 Krishnan Kumaran Windowed Statistical Analysis For Anomaly Detection In Geophysical Datasets
US20130064040A1 (en) * 2010-05-28 2013-03-14 Matthias G. Imhof Method for seismic hydrocarbon system analysis
US20140278115A1 (en) * 2013-03-15 2014-09-18 Exxonmobil Upstream Research Company Context based geo-seismic object identification
US20180128940A1 (en) * 2016-11-04 2018-05-10 Robert J. Ferderer Global Inversion of Gravity Data Using the Principle of General Local Isostasy for Lithospheric Modeling
US20210102457A1 (en) * 2018-04-20 2021-04-08 Schlumberger Technology Corporation Well log correlation and propagation system
US20210349227A1 (en) * 2020-04-28 2021-11-11 Xi'an Jiaotong University Method of stripping strong reflection layer based on deep learning
US20220206176A1 (en) * 2019-05-10 2022-06-30 Schlumberger Technology Corporation System and method for identifying subsurface structures
US20230041525A1 (en) * 2020-01-25 2023-02-09 Schlumberger Technology Corporation Automatic model selection through machine learning
WO2023055581A1 (fr) * 2021-09-29 2023-04-06 ExxonMobil Technology and Engineering Company Procédé et système de détection d'anomalie sismique
US20240053500A1 (en) * 2018-05-12 2024-02-15 Schlumberger Technology Corporation Seismic data interpretation system

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110272161A1 (en) * 2010-05-06 2011-11-10 Krishnan Kumaran Windowed Statistical Analysis For Anomaly Detection In Geophysical Datasets
US20130064040A1 (en) * 2010-05-28 2013-03-14 Matthias G. Imhof Method for seismic hydrocarbon system analysis
US20140278115A1 (en) * 2013-03-15 2014-09-18 Exxonmobil Upstream Research Company Context based geo-seismic object identification
US20180128940A1 (en) * 2016-11-04 2018-05-10 Robert J. Ferderer Global Inversion of Gravity Data Using the Principle of General Local Isostasy for Lithospheric Modeling
US20210102457A1 (en) * 2018-04-20 2021-04-08 Schlumberger Technology Corporation Well log correlation and propagation system
US20240053500A1 (en) * 2018-05-12 2024-02-15 Schlumberger Technology Corporation Seismic data interpretation system
US20220206176A1 (en) * 2019-05-10 2022-06-30 Schlumberger Technology Corporation System and method for identifying subsurface structures
US20230041525A1 (en) * 2020-01-25 2023-02-09 Schlumberger Technology Corporation Automatic model selection through machine learning
US20210349227A1 (en) * 2020-04-28 2021-11-11 Xi'an Jiaotong University Method of stripping strong reflection layer based on deep learning
WO2023055581A1 (fr) * 2021-09-29 2023-04-06 ExxonMobil Technology and Engineering Company Procédé et système de détection d'anomalie sismique

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
GENG ZHI; WANG HANQING; FAN MENG; LU YUNHU; NIE ZHEN; DING YUNHONG; CHEN MIAN: "Predicting seismic-based risk of lost circulation using machine learning", JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, vol. 176, 1 January 1900 (1900-01-01), NL , pages 679 - 688, XP085621054, ISSN: 0920-4105, DOI: 10.1016/j.petrol.2019.01.089 *
OYEYEMI KEHINDE DAVID, OLOWOKERE MARY TAIWO, AIZEBEOKHAI AHZEGBOBOR PHILIPS: "Hydrocarbon resource evaluation using combined petrophysical analysis and seismically derived reservoir characterization, offshore Niger Delta", JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY, vol. 8, no. 1, 1 January 2018 (2018-01-01), pages 99 - 115, XP093360553, ISSN: 2190-0558, DOI: 10.1007/s13202-017-0391-6 *

Similar Documents

Publication Publication Date Title
US12313803B2 (en) Automated offset well analysis
US12372683B2 (en) Autonomous operations in oil and gas fields
US9074454B2 (en) Dynamic reservoir engineering
US8103493B2 (en) System and method for performing oilfield operations
US12229689B2 (en) Hybrid modeling process for forecasting physical system parameters
US20230408723A1 (en) Machine learning synthesis of formation evaluation data
US12153183B2 (en) Machine learning proxy model for parameter tuning in oilfield production operations
US12252979B2 (en) Event detection from pump data
WO2022026988A1 (fr) Corrélation de puits à l'aide de modèles d'apprentissage automatique globaux et locaux
US20230359793A1 (en) Machine-learning calibration for petroleum system modeling
WO2025199452A1 (fr) Identification d'anomalies liées à des hydrocarbures assistée par ia à l'aide d'un flux de travail spécifique à une tâche d'apprentissage profond optimisé
US20250377477A1 (en) Petrophysical evaluation from non-radioactive measurements and mudlogging data through density and neutron porosity log reconstruction
US20240094433A1 (en) Integrated autonomous operations for injection-production analysis and parameter selection
US20260080134A1 (en) Automated wellbore analysis
US20250347215A1 (en) Subsurface knowledge enhancement using data science-constrained inverse modelling
US20250389860A1 (en) Elastic full wave inversion with machine learning estimated elastic properties
US20240201417A1 (en) System for building machine learning models to accelerate subsurface model calibration
US20250342285A1 (en) System and method for computing relative confidence of seismic interpretation
WO2025199437A1 (fr) Identification d'anomalie d'hydrocarbure assistée par ia
WO2025199448A1 (fr) Méthodologie de modèle de fondation pour analyse souterraine et identification d'hydrocarbures
WO2025097002A1 (fr) Analyse intelligente de fairway de jeu et mappage de chance de réussite
WO2026059763A1 (fr) Marquage automatique de données pendant un forage directionnel
EP4627188A1 (fr) Expertise logicielle et suivi de métadonnées associé
WO2025184184A1 (fr) Simulation d'écoulement multiphase dans des réservoirs fracturés

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25774191

Country of ref document: EP

Kind code of ref document: A1