Generative field development planning optimization

Abstract

The disclosed methods include: provisioning an artificial intelligence (AI) system; receiving, by a first data agent of the AI system and via a first LLM, natural language input; parsing, by the first data agent of the AI system, the natural language input and thereby generate query data for the AI system; generating, based on the query data, production analytics data for a resource site; selecting, based on one or more data elements in a database, at least one computing logic; determining, based on the production analytics data and the at least one computing logic, assessment data for fluid production optimization; and generating, based on the assessment data and using a second LLM of the one or more LLMs, a visualization on graphical display, the visualization comprising image or textual data indicating at least one data parameter for the fluid production optimization at the resource site.

Description

GENERATIVE FIELD DEVELOPMENT PLANNING OPTIMIZATIONCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Provisional Application No. 63 / 584,995, filed on September 25, 2023, titled "Generative Field Development Planning Optimization," which is incorporated herein by reference in its entirety for all purposes.TECHNICAL FIELD

[0002] Aspects of the present disclosure relate to integration of generative Al into the oil and gas industry, and in particular, to utilize generative Al for field development planning optimization, including modeling, simulation practices, making them more efficient, accurate, and actionable. Further, the generative Al can allow for deep advanced contextual analytics and optimal decision making.BACKGROUND

[0003] The energy (e.g., oil and gas) industry, with its intricate processes and vast data sets, has been at the forefront of technological innovation. However, this industry has long grappled with challenges such as the need for near real-time decision-making in reservoir modeling, the struggle of integrating diverse data sets, and the complexities of identifying optimal well locations under ever-changing reservoir conditions.

[0004] Additionally, designing and managing efficient waterflood program and understanding their impact on reservoir performance has been a persistent concern. Traditional methods often fall short in dynamically modifying reservoir models based on evolving field conditions, swiftly optimizing production, waterflood and enhanced oil recovery (EOR) strategies. Furthermore, assessing the operational feasibility of the results of waterflood programs along with drilling schedules and well designs has typically been a cumbersome process.

[0005] Moreover, field development plan (FDP) analysis and optimization associated with energy development is not only labor-intensive but is also error-prone leading to suboptimal FDP plans. In addition, FDP generation sometimes require deep domain and software expertise which disadvantageously extends the FDP lifecycle. Furthermore, currentFDP implementation struggles with best practice methodologies leading to the creation of unrealistic and inaccurate models associated with a resource site.

[0006] In addition, energy production optimization processes often require analysis of large daily volumes of data which can be labor-intensive and error prone leading to suboptimal decisions and insights. Furthermore, dynamic behavior of energy production fast outdates generated production models resulting in unrealistic and inaccurate production predictions. Moreover, energy production data can be siloed across different platforms which disadvantageously leads to poor data integration that can result in energy production losses.

[0007] As such, a solution is needed to address the unmet needs, as well as provide a holistic, agile, and efficient approach to field development planning and optimization.SUMMARY

[0008] Disclosed are methods, systems, and computer programs for generating energy assessment data for energy development. According to an embodiment, a method for generating energy assessment data for energy development comprises: provisioning an artificial intelligence (Al) system, the Al system comprising-one or more large language models (LLMs) configured to parse and transform natural language input queries, one or more data agent subsystems configured to coordinate data communication between two or more subsystems of the Al system, a database configured to store energy domain data, and a logic services subsystem configured to store a plurality of computing logic associated with energy development; receiving, by a first data agent of the one or more data agent subsystems of the Al system and via a first LLM of the one or more LLMs, natural language input associated with energy development; parsing, by the first data agent of the one or more data agent subsystems of the Al system, the natural language input and thereby generate query data for the Al system; generating, based on the query data, production analytics data for a resource site; selecting, based on one or more data elements in the database associated with the natural language input, at least one computing logic comprised in the plurality of computing logic of the logic services subsystem; determining, based on the production analytics data and the at least one computing logic, assessment data for fluid production optimization at the resource site; and generating, based on the assessment data and using a second LLM of the one or more LLMs, a visualizationon a graphical display, the visualization comprising image or textual data indicating at least one data parameter for the fluid production optimization at the resource site.

[0009] In other embodiments, a system and a computer program can include or execute the method described above. These and other implementations may each optionally include one or more of the following features.

[0010] In other embodiments, a system and a computer program can include or execute the method described above. These and other implementations may each optionally include one or more of the following features.

[0011] The Al system comprises a generative Al system, according to some embodiments.

[0012] In addition, the database is a vector database configured to store, based on the natural language input queries, data elements used to contextualize the natural language inputs.

[0013] Moreover, the plurality of computing logic comprise at least one of: statistical analysis computing logic; optimization computing logic; data processing and transformation computing logic; time series analysis computing logic; clustering computing logic; classification computing logic; and simulation computing logic.

[0014] In addition, the parsing can comprise conditioning the natural language input into computing instructions that are executable using the first data agent or a second data agent comprised in the one or more data agent subsystems of the Al system.

[0015] In some embodiments, the assessment data is associated with field development planning of an oil or gas resource at the resource site.

[0016] Furthermore, the field development planning comprises at least one of: seismic data analysis and interpretation associated with the resource site; reservoir model calibration associated with the resource site; well placement and trajectory design optimization associated with the resource site; waterflood and enhanced oil recovery optimization associated with the resource site; fluid production analysis associated with the resource site; well placement at the resource site; and petrophysical analysis associated with the resource site.

[0017] In some embodiments, the extracting step referenced above comprises: determining, based on the input query, the data elements of at least the database, such that the data elements of at least the database span a plurality of domains associated with energydevelopment; and combining, based on the determining, the data elements of at least the database to generate a multi-domain dataset associated with the input query.

[0018] Moreover, the applying step referenced above comprises executing at least one data simulation using the multi-domain dataset to generate the assessment data.

[0019] Furthermore, the plurality of domains comprises: an upstream domain associated with exploring and producing energy; a midstream domain associated with transporting and storing energy; or a downstream domain associated with refining energy.

[0020] In other embodiments, a method for generating energy assessment data for energy development comprises: provisioning an artificial intelligence (Al) system, the Al system comprising — one or more large language models (LLMs) configured to parse and transform natural language input queries, one or more data agent subsystems configured to coordinate data communication between two or more subsystems of the Al system, a database configured to store energy domain data, and a logic services subsystem configured to store a plurality of computing logic associated with energy development; receiving, by a first data agent of the one or more data agent subsystems of the Al system and via a first LLM of the one or more LLMs, natural language input associated with energy development; parsing, by the first data agent of the one or more data agent subsystems of the Al system, the natural language input and thereby generate query data for the Al system; generating, based on the query data, production analytics data for a resource site; selecting, based on one or more data elements in the database associated with the natural language input, at least one computing logic comprised in the plurality of computing logic of the logic services subsystem; determining, based on the production analytics data and the at least one computing logic, assessment data for fluid production optimization at the resource site; and generating, based on the assessment data and using a second LLM of the one or more LLMs, a visualization on a graphical display, the visualization comprising image or textual data indicating at least one data parameter for the fluid production optimization at the resource site.

[0021] In other embodiments, a system and a computer program can include or execute the method described above. These and other implementations may each optionally include one or more of the following features.

[0022] The Al system referenced above is a generative Al system.

[0023] Moreover, the parsing discussed in association with FIG. 12 comprises conditioning the natural language input into computing instructions that are executable using the first data agent or a second data agent comprised in the one or more data agent systems of the Al system.BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The disclosure is illustrated by way of example, and not by way of limitation in the figures of the accompanying drawings in which like reference numerals are used to refer to similar elements. It is emphasized that various features may not be drawn to scale and the dimensions of various features may be arbitrarily increased or reduced for clarity of discussion.

[0025] FIG. 1A depicts an exemplary computing or network system within which the disclosed methods, systems, and computer programs can be implemented according with some embodiments of this disclosure.

[0026] FIGS. 1B-1F illustrate exemplary schematic views of a resource site for which gas storage capacities may be determined according to some embodiments of this disclosure.

[0027] FIG. 1G illustrates a resource site for performing production operations in accordance with implementations of various technologies and techniques described herein.

[0028] FIG. lH illustrates a side view of a marine-based survey of a subterranean subsurface in accordance with one or more implementations of various techniques described herein.

[0029] FIG. II depicts a marine electromagnetic survey system in accordance with some implementations of this disclosure.

[0030] FIG. 1J illustrates one example of a system for performing seismic profiling that can employ simultaneous or near-simultaneous acquisition of seismic data.

[0031] FIG. 2 shows a first exemplary implementation of the disclosed generative Al system.

[0032] FIG. 3 shows an exemplary workflow associated with a field development plan(FDP).

[0033] FIG. 4 illustrates a high-level illustration of data processing components associated with developing an FDP.

[0034] FIG. 5 shows a first exemplary interconnection of subsystems of the disclosed generative Al system.

[0035] FIG. 6 shows a multi-dimensional map of an opportunity index associated with developing an oil and / or gas field.

[0036] FIG. 7 shows an exemplary workflow associated with energy production optimization.

[0037] FIG. 8 illustrates a high-level illustration of data processing components associated with energy production.

[0038] FIG. 9 shows a secondary exemplary interconnection of subsystems of the disclosed generative Al system.

[0039] FIG. 10 shows energy production data including example analysis data of specific energy productions systems.

[0040] FIG. 11 shows a first exemplary detailed workflow for generating assessment data for energy development.

[0041] FIG. 12 shows a second exemplary detailed workflow for generating assessment data for energy development.DESCRIPTION OF EMBODIMENTS

[0042] 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 disclosed technology. However, it will be apparent to one of ordinary skill in the art that the disclosed embodiments 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.

[0043] 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 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 disclosure. The first object orstep, and the second object or step, are both objects or steps, respectively, but they are not to be considered the same object or step.

[0044] The terminology used in the description of the disclosed techniques is for the purpose of describing particular embodiments and is not intended to be limiting. As used in the description of this disclosure 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 combination 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.

[0045] 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.

[0046] Those with skill in the art will appreciate that while some terms in this disclosure may refer to absolutes, for example, all of the components of a wavefield, all source receiver traces, each of a plurality of objects, etc., the methods and techniques disclosed herein may also be performed on fewer than all of a given thing, for example, performed on one or more components and / or performed on one or more source receiver traces. Accordingly, in instances in the disclosure where an absolute is used, the disclosure may also be interpreted to be referring to a subset.Computing Systems

[0047] FIG. 1A depicts an example computing system 100 in accordance with some embodiments. The computing system 100 can be an individual computer system 101 A or an arrangement of distributed computer systems. The computer system 101 A includes one or more geosciences analysis modules 102 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 geosciences analysis module 102 executes independently, or in coordination with, one or more processors 104, which is (or are) connected to one or more storage media 106. The processor(s) 104 is (or are) also connected to a network interface 108 to allow the computersystem 101 A to communicate over a data network 110 with one or more additional computer systems and / or computing systems, such as 101B, 101C, and / or 101D (note that computer systems 10 IB, 101C and / or 10 ID may or may not share the same architecture as computer system 101A, and may be located in different physical locations relative to each other or to computer system 101A. For example, computer systems 101A and 101B may be on a ship underway on the ocean, while in communication with one or more computer systems such as 101C and / or 10 ID that are located in one or more data centers on shore, other ships, and / or located in varying countries on different continents). Note that data network 110 may be a private network and may use portions of public networks and may include local or remote storage and / or application processing capabilities (e.g., cloud computing).

[0048] A processor can include a microprocessor, microcontroller, processor module or subsystem, programmable integrated circuit, programmable gate array, or another control or computing device.

[0049] The storage media 106 can be implemented as one or more computer-readable or machine-readable storage media. Note that while in the example embodiment of FIG. 1A storage media 106 is depicted as within computer system 101A, in some embodiments, storage media 106 may be distributed within and / or across multiple internal and / or external enclosures of computing system 101 A and / or additional computing systems. Storage media 106 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 readonly 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), BluRays or any other type of optical media; or other types of storage devices. Note that the instructions discussed above can be provided on one computer- readable or machine-readable storage medium, or alternatively, can be provided on multiple computer-readable or machine-readable storage media distributed in a large system having possibly plural nodes and / or non-transitory storage means. Such computer-readable or machine-readable storage medium or media can be considered to be part of an article (or article of manufacture). An article or article of manufacture can refer to any manufactured single component or multiple components. The storage medium or media can be located either in themachine running the machine-readable instructions, or located at a remote site from which machine-readable instructions can be downloaded over a network for execution.

[0050] It is appreciated that computer system 101A is one example of a computing system, and that computer system 101 A may have more or fewer components than those shown and may combine additional components not depicted in the example embodiment of FIG. 1A, and / or computer system 101A may have a different configuration or arrangement of components relative to the components depicted in FIG. 1A. The various components shown in FIG. 1A 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.

[0051] It is appreciated that while no user input / output peripherals are illustrated with respect to computer systems 101A, 101B, 101C, and 101D, many embodiments of computing system 100 include computer systems with keyboards, mice, touch screens, displays, and other user peripheral systems or other input-output systems. Some computer systems in use in computing system 100 may be desktop workstations, laptops, tablet computers, smartphones, server computers, etc.

[0052] Further, the steps in the processing methods described herein may be implemented by running one or more functional modules in an 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 protection of the disclosed subject-matter.

[0053] FIGS. 1B-1E illustrate exemplary schematic views of a resource site (e.g., an oilfield 100) having subterranean formation 102 containing reservoir 104 therein in accordance with implementations of various technologies and techniques described herein. FIG. IB illustrates a survey operation being performed by a survey tool, such as seismic truck 106.1, to measure properties of the subterranean formation. The survey operation is a seismic survey operation for producing sound vibrations. In FIG. IB, one such sound vibration, e.g., sound vibration 112 is generated by source 110 such that the sound vibration reflects off horizons 114 in the earth formation 116. A set of sound vibrations may be received by sensors e.g., geophone-receivers 118) situated on the earth's surface. The data received 120 may be providedas input data to a computer 122.1 of a seismic truck 106.1, and responsive to the input data, computer 122.1 may generate seismic data output 124. This seismic data output may be stored, transmitted or further processed as the case may require.

[0054] FIG. 1C illustrates a drilling operation being performed by drilling tools 106.2 suspended by rig 128 and advanced into subterranean formations 102 to form wellbore 136. Mud pit 130 may be used to draw drilling mud into the drilling tools via flow line 132 to circulate drilling mud down to the drilling tools, then up the wellbore 136 and back to the surface. The drilling mud is typically filtered and returned to the mud pit. A circulating system may be used for storing, controlling, or filtering the flowing drilling mud. The drilling tools are advanced into subterranean formations 102 to reach reservoir 104. Each well may target one or more reservoirs. The drilling tools are adapted for measuring downhole properties using logging systems while drilling. The logging systems may also be adapted for taking core (e.g, soil) sample 133 as shown according to some embodiments.

[0055] Computer facilities may be positioned at various locations about the oilfield 100 (e.g., the surface unit 134) and / or at remote locations. Surface unit 134 may be used to communicate with the drilling tools and / or offsite operations, as well as with other surface or downhole sensors. Surface unit 134 is capable of communicating with the drilling tools to send commands to the drilling tools, and to receive data therefrom. Surface unit 134 may also collect data generated during the drilling operation and produce data output 135, which may then be stored or transmitted.

[0056] Sensors, such as gauges, may be positioned about oilfield 100 to collect data relating to various oilfield operations as described previously. In one embodiment, a sensor may be positioned in one or more locations around the drilling tools and / or at rig 128 to measure drilling parameters, such as weight on bit, torque on bit, pressures, temperatures, flow rates, compositions, rotary speed, and / or other parameters of the field operation. The sensors may also be positioned at one or more locations in the circulating system according to some embodiments.

[0057] Drilling tools 106.2 may include a bottom hole assembly (BHA) (not shown), near the drill bit (e.g., within several drill collar lengths from the drill bit). The bottom hole assembly may also include capabilities for measuring, processing, and storing information, aswell as communicating with surface unit 134. The bottom hole assembly may further include drill collars for performing various other measurement functions.

[0058] The bottom hole assembly may include a communication subassembly that communicates with surface unit 134. The communication subassembly may be adapted to send signals to and receive signals from the surface using a communications channel such as mud pulse telemetry, electro-magnetic telemetry, wireless technology, or a wired drill pipe communications system. The communication subassembly may include, for example, a transmitter that generates a signal, such as an acoustic or electromagnetic signal, which is representative of the measured drilling parameters. It will be appreciated by one of skill in the art that a variety of telemetry systems may be employed, such as wired drill pipe, electromagnetic or other telemetry systems.

[0059] According to one embodiment, the wellbore may be drilled according to a drilling plan that is established prior to drilling. The drilling plan may set forth equipment data, pressure data, trajectory information and / or other data parameters that define or otherwise specify the drilling process for a given wellsite associated with the resource site (e.g., oilfield 100). The drilling operation may then be performed according to the drilling plan. However, as information is gathered, the drilling operation may be optimized or updated to, for example, deviate from the drilling plan to satisfy efficient drilling operations. Additionally, as drilling or other operations are performed, the subsurface conditions may change. An earth model associated with the resource site may also updated or adjusted to account for the new information being collected about the resource site.

[0060] The data gathered by the sensors disposed about the resource site may be received by surface unit 134 and / or other data collection sources for analysis or other processing. The data collected by the sensors may be used alone or in combination with other data. The data may be received by, and / or stored in one or more databases and / or transmitted to an onsite location or an offsite as the case may require. The data may be historical data, real time data, or combinations thereof. The real time data may be used in real time operations or stored for later use. The real-time data may also be combined with historical data or other inputs for further analysis. According to one embodiment, the data collected at the resource site may be stored in separate databases or combined within a single database.

[0061] Surface unit 134 may include transceiver 137 to allow communications between surface unit 134 and various portions of the oilfield 100 or other locations. Surface unit 134 may also be provided with or functionally connected to one or more controllers (not shown) for actuating mechanisms at oilfield 100. Surface unit 134 may then send command signals to oilfield 100 in response to data received. Surface unit 134 may receive commands via transceiver 137 or may itself execute commands to the controller. A processor may be provided to analyze the data (locally or remotely), make the decisions and / or actuate the controller. In this manner, oilfield 100 may be selectively adjusted based on the data collected. This technique may be used to optimize (or improve) portions of the field operation, such as controlling drilling, weight on bit, pump rates, or other parameters. These adjustments may be made automatically based on computer protocol, and / or manually by an operator. In some cases, well plans may be adjusted to select optimum (or improved) operating conditions, or to avoid problems.

[0062] FIG. ID illustrates a wireline operation being performed using wireline tool 106.3 suspended by rig 128 and into wellbore 136 of FIG. 1C. Wireline tool 106.3 is adapted for deployment into wellbore 136 for generating well logs, performing downhole tests and / or collecting samples. Wireline tool 106.3 may be used to provide another method and apparatus for performing a seismic survey operation. Wireline tool 106.3 may, for example, have an explosive, radioactive, electrical, or acoustic energy source 144 that sends and / or receives electrical signals to surrounding subterranean formations 102 and fluids therein.

[0063] Wireline tool 106.3 may be operatively connected to, for example, geophones 118 and a computer 122.1 of a seismic truck 106.1 of FIG. IB. Wireline tool 106.3 may also provide data to surface unit 134. Surface unit 134 may collect data generated during the wireline operation and may produce data output 135 that may be stored or transmitted. Wireline tool 106.3 may be positioned at various depths in the wellbore 136 to provide a survey or other information relating to the subterranean formation 102.

[0064] Sensors, such as gauges, may be positioned about the resource site (e.g., oilfield100) to collect data relating to various field operations as described previously. According to one embodiment, the sensor may be positioned within wireline tool 106.3 to measure downhole parameters which relate to, for example porosity, permeability, fluid composition and / or other parameters of the field operation.

[0065] FIG. IE illustrates a production operation being performed by production tool106.4 deployed from a production unit or Christmas tree 129 and into completed wellbore 136 for drawing fluid from the downhole reservoirs into surface facilities 142. The fluid flows from reservoir 104 through perforations in the casing (not shown) and into production tool 106.4 in wellbore 136 and to surface facilities 142 via gathering network 146. According to one embodiment, sensors, such as gauges, may be positioned about oilfield 100 to collect data relating to various field operations as described previously. For example, the sensors may be positioned within production tool 106.4 or within or about an associated equipment, such as Christmas tree 129, gathering network 146, surface facility 142, and / or the production facility, to measure fluid parameters, such as fluid composition, flow rates, pressures, temperatures, and / or other parameters of the production operation. In one embodiment, one or more injection wells may be fluidly coupled to the reservoir for added fluid recovery. Furthermore, one or more gathering facilities may be operatively connected to one or more of the wellsites within the resource site (e.g., oilfield 100) for selectively collecting downhole fluids from the wellsite(s).

[0066] While FIG. 1C-1E illustrate tools used to measure properties of a resource site (e.g., oilfield 100), it is appreciated that the tools may be used in connection with non-oilfield operations, such as gas fields, mineral mines, aquifers, storage, or other subterranean facilities. Also, while certain data acquisition tools are depicted, it is appreciated that various measurement tools capable of sensing parameters, such as seismic two-way travel time, density, resistivity, production rate, etc., of the subterranean formation and / or its geological formations may be used. Various sensors may be located at various positions along the wellbore and / or coupled to or be situated within the monitoring tools to collect and / or monitor the desired data. Other sources of data may also be provided from offsite locations to supplement or otherwise enhance data captured at the resource site.

[0067] The field configurations of FIGS. 1B-1E are intended to provide a brief description of an example of a resource site usable with oilfield application frameworks. Part of, or the entirety, of oilfield 100 may be on land, water, and / or sea. Also, while data associated with a single resource site is indicated as being measured and / or processed at a single location within these figures, oilfield applications may be used with any combination of one or moreresource sites ( .g., a plurality of oilfields 100), one or more processing facilities, and one or more similar or dissimilar wellsites.

[0068] FIG. IF illustrates a schematic view, and in particular, a partial cross section of the resource site (e.g., referenced as oilfield 200 in the figure) that has data acquisition tools 202.1, 202.2, 202.3 and 202.4 positioned at various locations about the resource site for collecting data of subterranean formation 204 in accordance with implementations of various technologies and techniques described herein. Data acquisition tools 202.1-202.4 may be the same as data acquisition tools 106.1-106.4 of FIGS. 1B-1E, respectively, or others not depicted. As shown, data acquisition tools 202.1-202.4 may generate data plots or measurements 208.1- 208.4, respectively. These data plots are depicted along the resource site (e.g., oilfield 200) to demonstrate the data generated by the various operations.

[0069] Data plots 208.1-208.3 are examples of static data plots that may be generated by data acquisition tools 202.1-202.3, respectively; however, it is appreciated that data plots 208.1-208.3 may include data plots that are updated in real time or near-real time. These measurements may be analyzed to better define the properties of the formation(s) and / or determine the accuracy of the measurements and / or for checking for errors. The plots of each of the respective measurements may be aligned and scaled for comparison and verification of the properties.

[0070] Static data plot 208. l is a seismic two-way response over a period of time. Static plot 208.2 is core sample data measured from a core sample of the formation 204. The core sample may be used to provide data, such as a graph of the density, porosity, permeability, or some other physical property of the core sample over the length of the core. Tests for density and viscosity may be performed on the fluids in the core at varying pressures and temperatures. Static data plot 208.3 is a logging trace that can provide, for example, a resistivity measurement or some other measurements of the formation at various depths. Also shown in the figure is a production decline curve or graph 208.4 which indicates a dynamic data plot of the fluid flow rate over time. The production decline curve can provide the production rate as a function of time. As fluid flows through the wellbore, measurements may be taken of fluid properties, such as flow rates, pressures, composition, etc., according to some embodiments.

[0071] According to some implementations, other data may also be collected or captured or associated with the resource site, such as historical data, user input data, economicdata, and / or other sensor data and / or other parametric data associated with one or more models of the resource site. As described below, static and dynamic measurements may be analyzed and / or used to generate models of the subterranean formation to determine characteristics thereof. Similar or dissimilar measurements may also be used to measure, or track changes a geological formation associated with the resource over time.

[0072] In one embodiment, the subterranean structure 204 may have a plurality of geological formations 206.1-206.4. As shown in FIG. IF, this geological formations may comprise several formations or layers, including a shale layer 206.1, a carbonate layer 206.2, a shale layer 206.3 and a sand layer 206.4. A fault 207 may extend through the shale layer 206.1 and the carbonate layer 206.2. In addition, the static data acquisition tools may be adapted to take measurements and detect characteristics of the aforementioned formations and / or other geological structures within the subterranean structure 204. While a specific subterranean formation with specific geological structures is depicted FIG. IF, it is appreciated that the resource site (e.g., oilfield 200) may contain a variety of geological structures and / or formations, sometimes having extreme complexity than those depicted. In some locations within the subterranean structure 204 may be below the water line such that fluid may occupy pore spaces of the one or more formations depicted. Each of the measurement devices may be used to measure properties of the formations and / or other geological features within the subterranean structure 204. While each acquisition tool is shown as being in specific locations at the resource site (e.g., oilfield 200), it will be appreciated that one or more types of measurement may be taken at one or more locations across one or more fields or other locations for comparison and / or for analysis and / or for integration with data captured at the resource site. The data captured from various sources, such as the data acquisition tools of FIG. IF, may then be processed and / or evaluated. In some embodiments, seismic data may be displayed in a static data plot 208.1 from the data acquisition tool 202. 1 and may be used to determine characteristics of the subterranean formations and other geological features associated with the resource site. The core data shown in the static plot 208.2 and / or log data from the well log 208.3 may be used to determine various characteristics of the subterranean formation. The production data from graph 208.4 may also be used to determine fluid flow reservoir characteristics as the case may require. In one embodiment, the captured data from the resource site may be used togenerate models that facilitate additional analysis of the subterranean structure 204 of the resource site.

[0073] FIG. 1G illustrates a resource site (e.g., oilfield 300) for performing production operations in accordance with implementations of various technologies and techniques described herein. As shown, the resource site has a plurality of wellsites 302 operatively connected to central processing facility 354. The resource site configuration of FIG. 1G is not intended to limit the scope of the oilfield application system. Part, or all, of the resource site may be on land and / or sea. Also, while a single resource site with a single processing facility and a plurality of wellsites is depicted, any combination of one or more resource sites, one or more processing facilities 354 and one or more wellsites 302 may be present according to some embodiments.

[0074] Each wellsite 302 may have equipment associated with one or more wellbores 336 within the subterranean formation 306 of the resource site. In particular, the wellbores 336 may extend through or into the subterranean formations 306 including reservoirs 304. These reservoirs 304 may contain liquid and / or gaseous fluids, such as hydrocarbons. In one embodiment, the wellsites 302 may draw fluid to and / or from the reservoirs and may pass said fluids to processing facilities via surface networks 344. The surface networks 344 may have tubing and control mechanisms for controlling the flow of fluids from the wellsite 302 to processing facility 354.

[0075] Attention is now directed to FIG. 1H, which illustrates a side view of a marinebased survey 360 of a subterranean subsurface 362 in accordance with one or more implementations of various techniques described herein. Subsurface 362 may include seafloor surface 364. Seismic sources 366 may include marine sources such as vibroseis or airguns, which may propagate seismic waves 368 (e.g., energy signals) into the Earth over an extended period of time or at a nearly instantaneous energy level provided by impulsive or pulse sources. The seismic waves may be propagated by marine sources as a frequency sweep signal. For example, marine sources of the vibroseis type may initially emit a seismic wave at a low frequency (e.g., 5 Hz) and increase the seismic wave frequency to a high frequency (e.g., 80- 90 Hz) over time. In one embodiment, the component(s) of the seismic waves 368 may be reflected and converted by seafloor surface 364 (i.e., reflector), and seismic wave reflections 370 may be received by a plurality of seismic receivers 372. Seismic receivers 372 may bedisposed on a plurality of streamers (i.e., streamer array 374). The seismic receivers 372 may generate electrical signals representative of the received seismic wave reflections 370. The electrical signals may be embedded with information regarding the subsurface 362 and captured as a record of seismic data. In some implementations, each streamer (e.g., comprised in the streamer array 374) may include streamer steering devices such as a bird, a deflector, a tail buoy and the like, which are not illustrated in FIG. 1H. The streamer steering devices may be used to control the position of the streamers (e.g., comprised in the streamer array 374) in accordance with the techniques described herein. In one embodiment, seismic wave reflections 370 may travel upward and reach the water / air interface at the water surface 376, a portion of reflections 370 may then reflect downward again (i.e., sea-surface ghost waves 378) and be received by the plurality of seismic receivers 372. The sea-surface ghost waves 378 may be referred to as surface multiples. The point on the water surface 376 at which the wave is reflected downward is may be referred to as the downward reflection point.

[0076] According to some implementations, the electrical signals may be transmitted to a vessel 380 via transmission cables, wireless communication or the like. The vessel 380 may then transmit the electrical signals to a data processing center. Alternatively, the vessel 380 may include an onboard computer capable of processing the electrical signals (i.e., seismic data). Those skilled in the art having the benefit of this disclosure will appreciate that this illustration is highly idealized. For instance, surveys may be of formations deep beneath the surface. The formations may typically include multiple reflectors, some of which may include dipping events, and may generate multiple reflections (including wave conversion) for receipt by the seismic receivers 372. In one implementation, the seismic data may be processed to generate a seismic image of the subsurface 362.

[0077] Typically, marine seismic acquisition systems may tow each streamer comprised in the streamer array 374 to the same depth (e.g., 5-10 m) within a body of water (e.g., the sea). However, marine based survey 360 may tow each streamer comprised in streamer the array 374 to a plurality of different depths as indicated in FIG. 1H such that seismic data may be acquired and processed in a manner that avoids the effects of destructive interference due to sea-surface ghost waves. For instance, marine-based survey 360 of FIG. IH illustrates eight streamers towed by vessel 380 at eight different depths. The depth of each streamer may be controlled and maintained using the birds disposed on each streamer.

[0078] Attention is now directed to FIG. II that depicts a marine electromagnetic survey system 382 in accordance with some implementations of this disclosure. The electromagnetic survey system 382 may use controlled-source electromagnetic (CSEM) survey techniques, but other electromagnetic survey techniques may also be used. In particular, marine electromagnetic surveying may be performed by a survey vessel 384 that moves in a predetermined pattern along the surface 385 of a body of water such as a lake or the ocean. The survey vessel 384 may be configured to pull a towfish (an electric source) 386, which is connected to a pair of electrodes 388. During the survey, the survey vessel 384 may stop and remain stationary for a period of time while obtaining measurements, while in some circumstances, the survey vessel 384 may remain underway while obtaining measurements. Furthermore, the survey vessel 384 may be coupled via a signal line 394 to one or more sensor devices 395 and 396 which are configured to work independently or in association with the towfish 386 and / or electrodes 388.

[0079] At the towfish 386, a controlled electric current may be generated and sent through the pair of electrodes 388 into the seawater. For instance, the electric current generated may be in the range between about 0.01 Hz and about 20 Hz. In one embodiment, the current creates an electromagnetic field 390 in the subsurface 392 to be surveyed below the sea floor 393. The electromagnetic field 390 may also be generated by magneto-telluric currents instead of the source 386. The survey vessel 384 may also be configured to tow a sensor cable 394. In one embodiment, the sensor cable 394 may be a marine towed cable. The sensor cable 394 may contain sensor housings 395, telemetry units 396, and current sensor electrodes (not illustrated). The sensor housings 395 may contain voltage potential electrodes for measuring the electromagnetic field 390’s strength created in the subsurface area 392 during the surveying period. The pair of electrodes 388 may be used to measure electric field strength in directions transverse to the direction of the sensor cable 394 (e.g., the y- and z-directions). The telemetry units 399 may contain circuitry configured to determine the electric field strength using the electric current measurements made by the pair of electrodes 388. While a marine-based electromagnetic survey is described in regard to FIG. II, a land-based electromagnetic survey may also be used in accordance with implementations of various techniques described herein.

[0080] Attention is now directed to FIG. 1J that depicts an embodiment of seismic system 20 in which a plurality of tow-vessels 22 are employed to enable seismic profilingincluding, for example, three-dimensional vertical seismic profding or rig / offset vertical seismic profding. In FIG. 1 J, a marine system is illustrated as including a rig 50, a plurality of vessels 22, and one or more acoustic receivers 28. Although a marine system is illustrated, other embodiments of the disclosure may not be limited to this example. It is appreciated that the disclosed approach may be implemented for land or onshore energy development systems. However, offshore systems are described herein to simplify the disclosure and to facilitate the explanation of the disclosed techniques.

[0081] Although two vessels 22 are illustrated in FIG. 1J, a single vessel 22 with multiple source arrays 24 or multiple vessels 22 each with single or multiple sources 24 may be used. In some applications, at least one source / source array 24 may be located on the rig 50 as represented by the rig source in FIG. 1J. As the vessels 22 travel on predetermined or systematic paths, their locations may be recorded through the use of navigation system 36. In some cases, the navigation system 36 uses a global positioning system (GPS) 38 to record the position, speed, direction, and other parameters of the tow-vessels 22.

[0082] As illustrated, the global positioning system 38 may use or work in cooperation with satellites 52 which operate on a suitable communication protocol, e.g., VS AT communications. The VSAT communications may be used, among other things, to supplement VHF and UHF communications. The GPS information can be independent of the VSAT communications and may be input to a computer processing system or other suitable processors to predict the future movement and position of the vessels 22 based on real-time information. In addition to predicting future movements, the computer processing system can also be used to provide directions and coordinates as well as to determine initial shot times, as described above. A control system associated with the vessels 22 can effectively use the computer processing system in cooperation with a source controller and synchronization unit to synchronize the sources 24 with the downhole data acquisition system 26.

[0083] As illustrated, the one or more vessels 22 may each tow one or more acoustic sources / source arrays 24. The source arrays 24 include one or more seismic signal generators 54 including, for example, air guns, configured to create a seismic / sonic disturbance. In the embodiment illustrated, the tow-vessels 22 comprise a master source vessel 56 (Vessel A) and a slave source vessel 57 (Vessel B). However, other numbers and arrangements of tow-vessels 22 may be employed to accommodate the parameters of a given seismic profiling application.For example, one source 24 may be mounted at rig 50 or at another suitable location, and both vessels 22 may serve as slave vessels with respect to the source 24 or with respect to a source at another location.

[0084] However, a variety of source arrangements and implementations may be provided as desired for a given application. When using dithered timing between the sources, for example, the master and slave locations of the sources can be adjusted according to the parameters of the specific seismic profiling application. In some applications, one of the source vessels 22 (e.g., source vessel A in FIG. 1 J) may serve as the master source vessel while the other source vessel 22 serves as the slave source vessel with dithered firing. However, an alternate source vessel 22 (e.g., source vessel B in FIG. 1 J) may serve as the master source vessel while the other source vessel 22 serves as the slave source vessel with dithered firing.

[0085] Similarly, the source 24 may serve as the master source while one of the source vessels 22 (e.g., vessel A) serves as the slave source vessel with dithered firing. The source 24 also may serve as the master source while the other source vessel 22 (e.g., vessel B) serves as the slave source vessel with dithered firing. In some applications, the source 24 may serve as the master source while both of the source vessels 22 serve as slave source vessels each with dithered firings. These and other arrangements may be used in achieving the desired synchronization of sources 24 with the downhole acquisition system 26.

[0086] The acoustic receivers 28 of data acquisition system 26 may be deployed in borehole 30 via a variety of delivery systems, such as wireline delivery systems, slickline delivery systems, and other suitable delivery systems. Although a single acoustic receiver 28 could be used in the borehole 30, the illustrated embodiment comprises a plurality of receivers 28 that may be located in a variety of positions and orientations. The acoustic receivers 28 may be configured for sonic and / or seismic reception. Additionally, the acoustic receivers 28 may be communicatively coupled with processing equipment 58 located downhole. By way of example, processing equipment 58 may comprise a telemetry system for transmitting data from acoustic receivers 28 to additional processing equipment 59 located at the surface, e.g., on the rig 50 and / or vessels 22.

[0087] Depending on the specifics of a given data communication system, examples of surface processing equipment 59 may comprise a radio repeater 60, an acquisition and logging unit 62, and a variety of other and / or additional signal transfer components and signalprocessing components. The radio repeater 60 along with other components of processing equipment 59 may be used to communicate signals, e.g., UHF and / or VHF signals, between vessels 22 and rig 50 and to enable further communication with downhole data acquisition system 26.

[0088] It should be noted the UHF and VHF signals can be used to supplement each other. In general, the UHF band supports a higher data rate throughput but can be susceptible to obstructions and has less range. The VHF band is less susceptible to obstructions and has increased radio range, but its data rate throughput is lower. In FIG. 1 J, for example, the VHF communications are illustrated as "punching through" an obstruction in the form of a production platform.

[0089] In some applications, the acoustic receivers 28 are coupled to surface processing equipment 59 via a hardwired connection. In other embodiments, wireless or optical connections may be employed. In still other embodiments, combinations of coupling techniques may be employed to relay information received downhole via the acoustic receivers 28 to an operator and / or control system (e.g., control system 34) located at least in part at the surface.

[0090] In addition to providing raw or processed data uphole to the surface, the coupling system, e.g., downhole processing equipment 58 and surface processing equipment 59, may be designed to transmit data or instructions downhole to the acoustic receivers 28. For example, the surface processing equipment 59 may comprise a synchronization unit which coordinates the firing of sources 24, e.g., dithered (delayed) source arrays, with the acoustic receivers 28 located in borehole 30. According to one embodiment, the synchronization unit uses a coordinated universal time system to ensure accurate timing. In some cases, the coordinated universal time system is employed in cooperation with global positioning system 38 to obtain coordinated universal time (UTC) data from the global positioning system (GPS) receivers of GPS system 38.

[0091] FIG. 1J illustrates one example of a system for performing seismic profiling that can employ simultaneous or near-simultaneous acquisition of seismic data. By way of example, the seismic profiling may comprise three-dimensional vertical seismic profiling, but other applications may use rig / offset vertical seismic profiling or seismic profiling employingwalkaway lines. An offset source can be provided by a source 24 located on rig 50, on a stationary vessel 22, and / or on another stationary vessel or structure.

[0092] As an example, the overall seismic system 20 may employ various arrangements of sources 24 on vessels 22 and / or rig 50 with each location having at least one source / source array 24 to generate acoustic source signals. The acoustic receivers 28 of downhole acquisition system 26 are configured to receive the source signals, at least some of which are reflected off a reflection boundary 64 located beneath a sea bottom 36. The acoustic receivers 28 generate data streams that are relayed uphole to a suitable processing system (e.g., a computing processing system), via downhole telemetry / processing equipment 58.

[0093] While the acoustic receivers 28 generate data streams, the navigation system 36 determines a real-time speed, position, and direction of each vessel 22 and also estimates initial shot times accomplished via signal generators 54 of the appropriate source arrays 24. The source controller 42 may be part of surface processing equipment 59 (located on rig 50, on vessels 22, or at other suitable locations) and is designed to control firing of the acoustic source signals so that the timing of an additional shot time (e.g. a shot time via slave vessel 57) is based on the initial shot time (e.g. a shot time via master vessel 56) plus a dither value (e.g, signal phase value).

[0094] The synchronization unit referenced above, for example, of the surface processing equipment 59, can coordinate the firing of dithered acoustic signals (e.g., altered phase signals) with recording of acoustic signals by the downhole acquisition system 26. The computing processor system may be configured to separate a data stream of the initial shot and a data stream of the additional shot via a coherency filter. As discussed above, however, other embodiments may employ pure simultaneous acquisition and / or may not perform separation of the data streams. In such cases, the dither may be effectively set to a zero value.

[0095] After an initial shot time at T = 0 (TO) is determined, subsequent firings of acoustic source arrays 24 may be offset by a dither (e.g., phase value). The dithers can be positive or negative and sometimes are created as pre-defined random delays. Use of dithers facilitates the separation of simultaneous or near-simultaneous datasets to simplify the data processing. The ability to have the acoustic source arrays 24 fire in simultaneous or near- simultaneous patterns reduces the overall amount of time used for three-dimensional vertical seismic profiling source acquisition. This, in turn, reduces rig time. As a result, the overallcost of the seismic operation is reduced, rendering the data intensive process much more accessible and efficient.

[0096] If the acoustic source arrays used in the seismic data acquisition are widely separated, the difference in move-outs across the acoustic receiver array of the wave fields generated by the acoustic sources 24 can be sufficient to obtain a clean data image via processing the data without further special considerations (e.g., minimizing the use of sophisticated hardware with associated costs and complexities). However, even when the acoustic sources 24 are substantially co-located in time, data acquired by any of the methods involving dithering of the firing times of the individual sources 24 described herein can be processed to a formation image leaving hardly any artifacts in the final image. This is accomplished by taking advantage of the incoherence of the data generated by one acoustic source 24 when seen in the reference time of the other acoustic source 24.Embodiments

[0097] Attention is now directed to methods, techniques, and workflows for processing and / or transforming collected data 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.

[0098] Those with skill in the art will recognize that in the geosciences and / or other multi-dimensional data processing disciplines, various interpretations, sets of assumptions, and / or domain models such as velocity models, may be refined in an iterative fashion; this approach may be applicable to the procedures, methods, techniques, and workflows discussed herein. In particular, this iterative refinement can include the use of feedback loops executed based on computing logic, such as at a computing device (e.g., computing system 100 of FIG. 1A), and / or through user control mechanisms that make determinations regarding whether a given step or stage, action, template, or model has become sufficiently accurate.

[0099] In one embodiment, a generative Al system specifically designed for the energy domain (e.g., oil and gas industry) is disclosed. In particular, the disclosed methods and systems include a generative Al system which enable reservoir modeling, reservoir simulation, and prediction in order to optimize field development planning operations. Furthermore, the generative Al system can include Al models and micro-services that can, for example, allowusers to interact conversationally and perform tasks including, but not limited to, deep analytics and optimal well placement.

[0100] According to one embodiment, the disclosed generative Al systems can include a system with multiple engines, including but not limited to a generative NLP communicator subsystem, master Al subsystem, domain micro-services subsystem, and a logic services subsystem. Each of the aforementioned subsystems can serve a specific purpose and can, in combination (or collaboration), enhance efficiency and precision.

[0101] In some embodiments, the generative Al system can interpret user prompts and thereby generate actionable insight data as well as delegate tasks to appropriate engines to ensure optimal outcomes and continuous learning and evolution of one or more computing models associated with the generative Al system. In addition, the generative Al system can specialize in domain specific tasks that are related to, for example, reservoir modeling and simulation workflows. Furthermore, the generative Al system can include integration of various machine learning methods and systems to address specific needs with precision.

[0102] Accordingly, the generative Al system can receive one or more requests related to, for example, statistical outputs, data transformations, classification, and risk assessment scenarios. In addition, the advanced integration of the generative Al system with modeling and simulation software (e.g., ECLIPSE software, INTERSECT software, and Petrel software) can establish and / or develop a user-centric, prompt-based system. The generative Al system can, for example, enable automatic setup of simulation cases that can be tailored and / or customized for user-provided scenario(s). Additionally, the generative Al system can interpret and / or act upon user prompts in order to provide data insights and actions related to field development planning optimization. Some examples of such data insights and actions can include model calibration, quality control and assurance, well placement, waterflood, enhanced oil recovery (EOR), gas injection, gas lift along with deep contextual analytics on reservoir, well, completion properties along production and injection data, etc. Further, the generative Al system can, for example, identify optimal well placements, interpret seismic data, and optimize waterflood operations. In doing so, the generative Al system can make field development planning more efficient and effective.

[0103] According to one embodiment, the generative Al system can be tailored or otherwise customized for the energy domain (e.g., oil and gas industry) and the specificrequirements and needs thereof. For example, the generative Al system can include reservoir modeling, simulation and prediction practices, which can be essential for field development planning optimization. Further, the generative Al system can allow users to: interact (e.g., conversationally) seamlessly with one or more applications and data; and prompt the generative Al system to perform a wide range of tasks, including deep analytics and optimal well placements computing operations. The generative Al system can comprise a suite of Al models and microservices as well as multiple engines (e.g., data engines), where each engine can serve a distinct purpose yet collaboratively drive the generative Al system to operate efficiently and precisely.

[0104] In this workflow, a user’s prompt(s) 202 can be received by a generative natural language processing (NLP) communicator 204 of the generative Al system. According to one embodiment, the generative NLP communicator 204 can interpret and translate user prompt(s) into, for example, actionable insights. Furthermore, the generative NLP communicator 204 can serve as an interactive frontend of the generative Al system. The generative NLP communicator 204 can integrate generative Al models, a subset of the NLP, that in turn can ensure that a user’s inputs are accurately understood and appropriately routed for further action. As such the generative NLP communication 204 can enable generation of coherent and contextually relevant responses based on the input (e.g., natural language input) received by the generative Al system.

[0105] One or more of the disclosed NLP models associated with the generative NLP communicator 204 can be trained to effectively interpret prompts and execute computing tasks in the context of reservoir modeling and simulation for field development planning applications. To do this a diverse and domain-specific dataset is required. Exemplary training datasets for the disclosed models of the generative Al system include:1. Domain-Specific Texts (e.g., energy domain texts):• Documents: In some implementations, these include manuals, reports, papers, and articles related to the energy domain and / or associated with energy domain software (e.g., Petrel, ECLIPSE, INTERSECT, Techlog).• Operational Instructions: According to one embodiment, these include guidelines, Standard Operating Procedures (SOPs), and protocols associated with energy development (e.g., field development planning, drilling, production, etc.).• Technical Specifications: According to some embodiment, these include documents detailing the specifications of equipment and other energy related structures (e.g., wells, reservoirs in the field, etc.). r Interaction Data:• User Prompts: In exemplary cases, these includes a diverse set of exemplary user- derived data prompts and / or other input data or input commands that cover a plurality of contexts, scenarios, computing operations, and data queries.• Command Logs: In an embodiment, these include historical data logs associated with one or more prompts, input commands and / or data queries derived from user inputs to existing or non-existing systems. ion Execution Data:• Action Logs: According to one embodiment, these include logs detailing the computing operations executed by the generative Al system in response to user prompts or commands. These actions or computing operations can be linked to an Al subsystem (e.g., Master Al 206 of FIG. 2) of the generative Al system, domain micro-services 208 and / or logic services 210 all of which power the generative Al system.• Feedback Data: These include user feedback on the system’s responses and actions, which can help in refining the model’s understanding and execution of actions, if available. otated Data:• Labeled Prompts: In exemplary implementations, these include prompts data (e.g. , user or non-user prompts) annotated with a corresponding set of computing operations together with any relevant parameters or entities.• Intent and Entity Annotations: In one embodiment, these include data annotated with intent information e.g., intent data associated with users) and / or entity data that facilitates training one or more computing models of the disclosed generative Al system to understand or otherwise optimally analyze intent data and thereby extract relevant information from user prompts or prompts data. ulated Data:• Synthetic Prompts: According to an embodiment, these include generated prompts data associated with simulating possible user interactions. This approach may beneficially enables anticipating prompt data especially in scenarios where there is limited real-world interaction data available. For instance, this disclosure provides one or more contextual data associated with various scenarios involving energy development operations. Each process associated with energy development (e.g., reservoir modeling and simulation computing processes) may have a specific set of workflows assigned which can be leveraged as needed.• Augmented Data: In some cases, this include data variations of existing data created using the disclosed techniques including paraphrasing existing data to, for example, increase the diversity of the training dataset.6. Domain-Specific Knowledge Base:• Industry Terminology: According to an embodiment, this includes a comprehensive list or database terminologies, acronyms, and phrases used in the energy domain (e.g., reservoir modeling and simulation).• Contextual Information: According to an embodiment, this includes information or data that provides context about the energy domain (e.g., reservoir modeling and simulation-specific concepts, processes, and equipment associated with oil and gas exploration).7. General Language Data:• General Text Corpora: In some instances, this includes large text corpus from diverse sources that can be used to train one or more computing models associated with the generative Al system on general language understanding before fine-tuning on domain-specific (e.g., energy domain) data.

[0106] Turning back to FIG. 2, the master Al subsystem 206 of the generative Al system can receive interpreted commands and / or queries from the generative NPL communicator 204. Based on the received interpreted commands and / or queries, the master Al subsystem 206 can orchestrate workflows associated with the generative Al system and thereby ensure a seamless interaction between different components and / or subsystems of the disclosed generative Al system. For example, the master Al subsystem 206 can analyze the interpretedinputs from the generative NLP communicator 204. Furthermore, the master Al subsystem 206 can be powered by generative Al models. Additionally, the master Al subsystem 206 can delegate tasks to other subsystems appropriate subsystems of the disclosed generative Al system, which can in turn ensure optimal outcomes.

[0107] The master Al subsystem 206 can be trained to orchestrate workflows, manage interactions between different components, make informed decisions, and optimize the overall system performance effectively within the reservoir modeling and simulation context by meticulously integrating diverse and representative data categories. This approach ensures the master Al’s adaptability, reliability, and efficiency in managing complex scenarios and diverse interactions in real-world applications.

[0108] According to some embodiments, the following data may also be leveraged by the disclosed generative Al system:1. Interaction Management Data:• Component Interaction Protocols: This data may be used to develop structured protocols detailing data interactions and / or data communications between the master Al subsystem 206 and various subsystems of the generative Al system.• Delegated Task Logs: This includes: data logs that detail one or more tasks delegated by the master Al subsystem 206 to appropriate subsystems of the generative Al system; and the data outcomes of the one or more tasks.2. Workflow and Scenario Data:• Workflow Scenarios: According to one embodiment, this data facilitates integrating diverse scenarios and / or contexts representing a range of workflows and interactions that the master Al subsystem can orchestrate and manage.• Decision-Making Scenarios: In some cases, this data facilitates incorporating various scenarios and / or contexts that depict different decision-making processes and outcomes managed by the master Al subsystem 206.3. System Optimization Data:• Performance Metrics and Logs: This data comprises metric data and / or log data that can be used to detail the performance and optimizations of the disclosed generative Al system and its subsystems in various scenarios or contexts.• Optimization Scenarios: This data comprises data integrations of various scenario or context data and data related to optimizations and refinements made by the master Al subsystem 206 based on performance evaluations.4. Compliance and Security Protocols:• Security Protocols and Logs: These logs facilitate developing and integrating robust security measures, protocols, and logs used by the master Al subsystem 206 to ensure secure interactions and sensitive information sharing by the subsystems for the disclosed generative Al system.• Compliance Protocols and Logs: These logs incorporate protocols and logs related to the master Al subsystem’s adherence to relevant regulations and industry standards (e.g., energy industry standards).

[0109] According to one embodiment, the master Al subsystem 206 can also continuously learn and evolve by refining the control logic managed by the logic services subsystem 210 to adapt to new data, user interactions, and feedback. Accordingly, the continuous learning and evolution of the master Al subsystem 206 can ensure that the disclosed generative Al system remains at the forefront of technological advancement.

[0110] As part of the orchestration by the master Al subsystem 206, task execution commands can be provided to domain micro-services subsystem 208 and the logic services subsystem 210 to perform domain specific tasks and / or actions and / or computing operations as the case may require. In turn, the domain micro-services subsystem 208 and logic services subsystem 210 can provide results and / or responses 212 which, according to some embodiments, can be fed back to the master Al subsystem 206. In some cases, the task execution commands and results and / or responses can continue iteratively between the master Al subsystem and the domain micro-services subsystem 208 and the logic services subsystem 210 until a final response and / or result 212 is outputted.

[0111] The domain micro-services subsystem 210 is configured to handle domainspecific tasks and operations related to reservoir modeling and simulation workflows. The domain micro-services subsystem 210 can include a suite of micro-services, each of which can be fine-tuned to perform specific functions including seismic computing operations, petrophysical interpretation computing operations, geological modeling computing operations, or well placement operations and / or optimization computing operations, etc. According to oneembodiment, these functions beneficially enable executing a range of tasks including data quality assurance and control, interpretation, and analysis — each of which can advantageously enhance reservoir modeling and simulation computing operations.

[0112] Each of the domain micro-services 208 can integrate various machine learning methods, ranging from modeling computing logic (e.g., decision trees, gradient boosting machines, ensemble models, clustering algorithms, anomaly detection algorithms, etc.) to advanced deep learning models (e.g., feedforward neural networks, convolutional neural networks, recurrent neural networks, graph neural networks, long short-term memory networks, autoencoders, transformer models, deep reinforcement learning algorithms, etc.). Additionally, the domain micro- services 208 can provide a diverse set of tools to address specific domain e.g., energy domain) needs with precision and expertise. According to an embodiment, deep convolutional neural networks associated with the energy domain can be used to undertake seismic data conditioning, relative geologic time (RGT) and horizon picking, fault identification, and performing seismic stratigraphy interpretation computing operations. In another example from the petrophysics sector, the disclosed generative Al system can be used to aid in tasks like data quality assurance or data quality control, saturation height modeling, rock typing, and permeability modeling.

[0113] Additionally, the disclosed generative Al system, including Generative Adversarial Networks (GANs) can be extensively used to generate a geologically realistic facies model or other reservoir properties with associated multi-dimensional (e.g., 2-dimensional (2D) or 3-dimensional (3D)) visualization data that can be conditioned to generate seismic data, petrophysics data, and / or fluid production data. The integration of machine learning in reservoir engineering domain, specifically using a deep learning encoder-decoder transformer architecture, to construct smart proxies, can accelerate and / or optimize time-consuming history matching processes.

[0114] Furthermore, modeling and simulation software (e.g., ECLIPSE software, INTERSECT software, and / or Petrel software) can be enhanced with prompt-based modeling and simulation features through integration of the disclosed generative Al system using, for example, a transformer architecture. This integration can establish the development of a usercentric, prompt-based system that enable automatic setup of simulation cases tailored or otherwise customized to user-provided scenarios.

[0115] According to some embodiments, the disclosed generative Al system with attendant models (e.g., fluid models) can be used for fluid modeling, such that the fluid models can execute: comprehensive quality assurance or quality control processes on fluid laboratory data within seconds; conduct regression computing operation; and calibrate fluid state equations based on laboratory data. Furthermore, in the drilling domain, the disclosed generative Al system can be used to develop machine learning logic for deploying and forecasting an effective combination of drilling parameters to enhance the rate of penetration and / or aid in selecting an optimal drill string to reduce tool failures related to drill motors and / or drill bits.

[0116] In one embodiment, the domain micro-services 208 of FIG. 2 can act as a comprehensive toolbox, housing a diverse array of subsurface reservoir modeling and simulation workflows. This is because some geological modeling and certain aspects of reservoir engineering can predominantly use advanced computing logic to expedite horizontal well calibration, optimize well placement hotspot identification and trajectory optimization, and execute waterflood optimization scenarios. The workflows can be invoked by the master Al subsystem 206 to execute a series of tasks, each of which can be tailored and / or customized to meet the specific demands and nuances of the respective domain. The training methodologies for each of these workflows can be inherently unique, involving a distinct set of data meticulously chosen depending on the task at hand and the specific domain it addresses. This ensures that each workflow is optimally trained, allowing for the execution of tasks with unparalleled precision and adaptability, catering to multifaceted needs of the energy industry.

[0117] This beneficially obviates the need for extensively reviewing documentation associated with energy development software such as ECLIPSE or INTERSECT to determine the appropriate querying semantics and / or querying syntax to set up a simulation case. In one embodiment, a transformer architecture can be used by the disclosed generative Al system together with advanced contextual understanding and learning, to allow swift and accurate translation of diverse user inputs into structured, coherent simulation setups. This enhancement not only streamlines user interaction, rendering tools more user-friendly and adaptable, but also fortifies the reliability and precision of simulations, ensuring they are configurable or otherwise adaptable to the evolving needs and sophisticated demands of the energy industry. It is appreciated that the disclosed approach can be leveraged for unparalleled specialization andadaptability of the disclosed generative Al system and customized for a wide array of energy industry needs with precision and expertise.

[0118] Turning back to FIG. 2, logic services subsystem 210 can be configured to enable integrate reliable and established methods or computing operations for tasks including statistical analysis computing operations, optimization computing operations, data processing and transformation computing operations, time series analysis computing operations, clustering computing operations, and classification and simulation computing operations. It is appreciated that the logic services subsystem 210 can handle requests related to deriving statistical outputs, such as calculating descriptive and inferential statistics, and other optimization computing operations. Furthermore, the disclosed logic services subsystem 210 can perform data transformations, classify data based on specific characteristics, and run scenario-based computing operations for risk assessment, thereby blending reliability with innovative capabilities of other components of the disclosed generative Al system.

[0119] According to one embodiment, the logic services subsystem 210 does not require training on data in the manner that machine learning models require but can be rather engineered to use pre-defined, rule-based computing logic to execute specific tasks. The logic services subsystem 210, for example, can be a repository of customized computing logic such that each computing logic comprised in the repository of customized computing logic can be designed to perform a specific function or solve a particular problem, based on mathematical computing methods and / or statistical / stochastic computing methods. When a task aligns with the capabilities of a given computing logic, the master Al subsystem 206 can call upon the logic services subsystem 210 to execute the task and subsequently output results as the final response / results 212. In such cases, this ensures that tasks are addressed with the most suitable methodologies, combining the adaptability of the disclosed generative Al system with the precision and reliability of energy domain logic to deliver accurate and efficient results.

[0120] Each subsystem of the generative Al system of FIG. 2 can form a cohesive and powerful ecosystem, wherein each component can contribute unique capabilities to create the disclosed generative Al system that is greater than the sum of its parts. The synergy between the advanced Al (e.g., master Al subsystem 206), specialized domain services (e.g., domain micro-services 208), reliable logic subsystem (e.g., logic services subsystem 210) positions thedisclosed generative Al system as a revolutionary tool that is efficient, accurate, and adaptable for a plurality of energy domain scenarios.

[0121] Some examples of the functionality of the disclosed generative Al system include:• Deep Advanced Contextual Analytics:This can involve analyzing reservoir data, well data, development completion data, fluid data, rock data, petrophysical data, geological data, seismic properties data, along with production and injection data. For example, upon receiving the prompt: “Provide a breakdown of the well types and their performance,” the disclosed generative Al system leverages well data, reservoir data, production data, and injection data associated with a well under consideration and offers a detailed breakdown of well types, including statistical percentiles of well performance in terms of production and injection associated with the well under consideration at a resource site.• Interpretation:This can involve processing seismic data, petrophysical data, geological data, fluid data, rock data, fluid production data, fluid injection data, and drilling data associated with a given subterranean formation. In addition, the interpretation process can comprise seismic (e.g., fault identification, horizon picking, etc.) interpretation computing operations, petrophysical (e.g., saturation height modeling, rock typing, etc.) interpretation computing operations, and geological (e.g., well tops interpretation, property distribution, etc.) interpretation computing operations. For example, upon receiving the prompt; “Can you perform conditioning of the seismic data and identify all the faults and horizons,” the disclosed generative Al system performs seismic conditioning and interpretation by outputting relevant fault and / or horizon data associated with a resource site under consideration.• Reservoir Model Calibration:This can involve introducing changes to both static and dynamic reservoir models based on user prompts. For example, upon receiving the prompt: “Can you change the well tops to ensure all the horizontal wells are fitted to reservoir layers," the disclosed generative Alsystem can adjust the reservoir layers accordingly and execute any necessary commands based on the prompt or query. As another example, upon receiving the prompt or query “Can you identify poor matching wells and adjust the reservoir properties around the wells following the constraints,” the disclosed generative Al system can modify static / dynamic and / or other reservoir properties to obtain a reservoir simulation matched to historical data associated with a resource site under consideration.• Well Placement & Trajectory Design Optimization:This can involve identifying drilling "hotspots" for maximum recovery (e g., maximum fluid recovery). In some embodiments, this involves generating optimal well trajectories based on user-defined constraints. For example, upon receiving the query or prompt: “Can you identify potential hotspots to drill in 2025,” the disclosed generative Al system evaluates reservoir conditions with relevant properties data together with historical production data and injection data to pinpoint (e.g., surgically pinpoint) or otherwise determine the most promising drilling locations relative to other drilling locations at a given resource site under consideration.• Waterflood & Enhanced Oil Recovery Optimization:This can involve analyzing and optimizing waterflood sectors data, geological patterns data, injector-producer pairs data, sweep efficiencies data, etc. In addition, this may involve providing insight data on optimal production and injection rate allocations at a given resource site, drilling of alternative injector and production pairs at said resource site, etc. For example, in response to receiving the query, input, or prompt: “How can I improve waterflood to maximize injection efficiency,” the disclosed generative Al system can suggest alternative injector-producer rate adjustments data to enhance recovery and can set up and launch context-based simulation to assess results associated with the query or prompt.

[0122] The following are prompt examples and scenarios illustrating interactions with the disclosed generative Al system:Historical Production Analysis:Prompt: “Show PIO, P50, and P90 of historical producers.”Generative Al system: “Analyzing... PIO: 5000 bbl / day, P50: 3500 bbl / day, P90: 2000 bbl / day.”• Infill Well Analysis:Prompt: “How many new infdl wells were drilled in the reservoir after 2023?” Generative Al system: “Post-2023, 25 new infill wells have been drilled in the reservoir. See the detailed breakdown by date and their average performance.”• Well Positioning Sensitivity:Prompt: “Is the development plan sensitive to having very accurate well positioning?” Generative Al system: “Analyzing... Yes, the development plan shows a 15% efficiency drop with a positioning error greater than 50 ft.”• Operational Feasibility Check:Prompt: “Is the drilling schedule and well design operationally feasible?”Generative Al system: “Reviewing the design... The drilling schedule is feasible, but the well design for Well-47 might encounter operational challenges due to its proximity to a fault line.”• Seismic Interpretation:Prompt: “Identify seismic faults in the northern sector of the reservoir.”Generative Al system: “Processing seismic data... 3 major faults identified in the northern sector. Would you like a visual representation?”• Petrophysical Analysis:Prompt: “Perform QA / QC on the saturation height modeling for the western wells.” Generative Al system: “Analyzing... 2 out of 15 wells in the western region show discrepancies in matching their water saturation. Recommend a review.”Geological Insights:Prompt: “Distribute the rock properties across the reservoir based on well tops interpretation.”Generative Al system: “Interpreting well tops... Rock properties have been distributed. The southeastern region shows higher porosity values but low permeability values.”• Enhanced Oil Recovery (EOR) Strategy:Prompt: “Evaluate the efficiency of gas injection in the central sector.”Generative Al system: “Evaluating... Gas injection in the central sector has increased oil recovery by 12% over the past year.”• Waterflood Pattern Analysis:Prompt: “Are all my sectors evenly depleted, and is the sweep efficiency harmonic?” Generative Al system: “Analyzing sweep efficiencies... Sector B4 and C3 show uneven depletion. Recommend adjusting waterflood patterns for better harmony.”• Optimal Allocation for Injection Efficiency:Prompt: “Adjust the rates between injector and producer pairs in the eastern sector to optimize injection efficiency.”Generative Al system: “Optimizing... Rates adjusted. Projected to achieve a 10% increase in injection efficiency for the eastern sector.”• Optimal Drilling Schedule to Minimize Emissions:Prompt: “Set up a drilling schedule that is both operationally feasible and that will result in reduction in emissions.”Generative Al system: “Setting up... Drilling schedule updated. Projected to achieve 20% reduction emissions while maintaining the same level incremental oil production.”

[0123] The prompt examples and scenarios illustrated above are demonstrative of the versatility and depth of the disclosed generative Al system for addressing a wide range of operational challenges and tasks in the energy domain (e.g., oil and gas industry). According to some embodiments, the disclosed generative Al system as described herein further includes the following features that overcome many of the challenges faced in the oil and gas industry:• Unified Data Integration & Interpretation: Traditional reservoir management often requires disparate tools for different data types, leading to fragmented insights and potential inconsistencies. Instead of juggling multiple tools, the disclosed generative Al system can seamlessly integrate and analyze diverse datasets, from seismic datasets to production datasets. This holistic approach ensures that insight data are derived from a comprehensive understanding of all available data, reducing potential errors that can arise from disjointed data handling and enhancing the accuracy of data predictions. The disclosed generative Al system can also perform (e.g., simultaneously or concurrently perform) interpretation of seismic data, petrophysical data, geological and production data, and thereby provide comprehensive insight data.• Real-time Analytics & Decision Making: Conventional tools might offer delayed analytics due to computational constraints and laborious nature of workflows which cannot be performed mentally. By processing user prompts instantly, the disclosed generative Al system can facilitate real-time analytics, interpretations, and recommendations. This agility accelerates the decision-making process, enabling engineers to respond promptly to evolving energy conditions (e.g., reservoir conditions).• Reservoir Modeling & Calibration: Traditional reservoir modeling tools might be rigid and not easily adaptable to new data or insight data. With the disclosed generative Al system, users can easily introduce changes to reservoir models based on new data or new insight data. The disclosed generative Al system can adjust these models dynamically, ensuring that simulations and data predictions are based on the most current and relevant data.• Intelligent Well Placement: Traditional methods of identifying drilling locations can be time-consuming and might not always yield the most efficient results. Leveraging advanced algorithms and vast datasets, the disclosed generative Al system can swiftly identify the promising drilling locations, optimizing well placements for maximum fluid recovery and efficiency.• Optimized Waterflood Management: Waterflood optimization has traditionally been a complex, highly inefficient manual and iterative process. The disclosed generative Al system can analyze waterflood patterns, predict their impact on reservoir performance, and provide recommendations for optimization. This ensures that waterflooding operations are both efficient and effective in enhancing oil recovery.• Enhanced Oil Recovery (EOR) Strategy Enhancement: Traditional EOR strategy development can be resource-intensive, requiring extensive testing. The disclosed generative Al system can swiftly analyze and optimize EOR strategies, eliminating the need for extensive iterative testing and ensuring that recovery methods are as efficient as possible.• Operational Feasibility Analysis: Assessing the feasibility of operational plans has traditionally been a separate, often lengthy process. By cross-referencing drilling schedules and well designs with geological and operational data, the disclosed generative Al system can provide immediate feedback on the feasibility of operational plans. This ensures that strategies are not only efficient but also practical and executable.• Emissions Impact Analysis: While environmental considerations are becoming paramount, many existing tools do not provide integrated emissions impact analysis. Evaluating the emissions impact of field development plan activities, helping companies adhere to environmental regulations and reduce their carbon footprint.

[0124] Accordingly, the disclosed generative Al system can offer a comprehensive, agile, and data-driven approach that can directly address unmeet needs in the energy (e.g., oil and gas) industry as well as revolutionize field development planning and optimization operations.

[0125] Incorporating the disclosed generative Al system into a product revolutionizes the oil and gas industry by addressing several inherent challenges of current technologies. Traditional systems, often fragmented, struggle with the seamless integration of diverse datasets, from seismic to production data. The disclosed Al-driven approach not only offersunified data integration and interpretation but also facilitates real-time analytics, enabling swift decision-making in response to evolving reservoir conditions. Furthermore, the dynamic adaptability of the disclosed methods and systems ensures that reservoir models are continuously calibrated, optimizing well placements and enhancing waterflood management. In essence, the disclosed methods and systems stands poised to deliver unparalleled efficiency, accuracy, and operational agility of oil and gas operators, setting a new benchmark.

[0126] In some embodiments, the disclosed generative Al system can be integrated with one or more software program products, including but not limited to ECLIPSE software, INTERSECT software, Petrel software, OFM software, PIPESIME software, OLGA software, Symmetry software, Techlog software, DELFI software (e.g., DrillPlan, PetroTechnical Suite, FDPlan, Agile Reservoir Modeling, etc.). By integrating into software program products with the disclosed generative Al system, there is no need for: sifting through extensive documentation which are nearly impossible to achieve considering the voluminous amounts of data; and performing laborious and time-consuming manual modeling workflows and analysis of same.

[0127] In addition to the embodiments and features of the disclosed generative Al system described herein, the following are additional embodiments, features, or uses of the generative Al system:• Automated Drilling: Integrating the Al with drilling equipment to automate the drilling process, ensuring optimal drilling based on real-time data and predictions.• Integration with loT: Combining the disclosed generative Al system with Internet of Things (loT) devices such as AGORA for real-time data collection and analysis, further enhancing the accuracy of predictions and recommendations.Virtual Reality (VR) & Augmented Reality (AR) Integration: Using VR and AR for immersive data visualization, training, and on-site assistance, providing field engineers with real-time insights and guidance.Alternative Energy Exploration: Adapting the disclosed generative Al system for use in renewable energy sectors, such as geothermal energy exploration, to optimize drilling and production.• Carbon Capture and Storage (CCS) Optimization: Using the Al to optimize the process of capturing carbon dioxide emissions at their source and storing them, aiding in the fight against climate change.

[0128] In an ever-evolving landscape of the energy sector, the applications of the disclosed generative Al system are vast. As technology advances and the industry's needs change, the disclosed methods and systems not only is capable of meeting current challenges but can also be adapted and expanded to address new challenges and opportunities.

[0129] FIG. 3 shows an exemplary workflow associated with a field development plan (FDP). In this workflow, domain experts 302 (e g., simulation engineer, reservoir engineer, field development planner, etc.) leverage, via one or more computing systems, a streamlined and automated FDP analysis and optimization tool 304 based on the disclosed generative Al system. The streamlined and automated FDP analysis and optimization tool 304 may advantageously facilitate a plurality of benefits 306 including: generating optimal FDPs; reducing analysis time associated with FDS generation and utilization; providing consistent results with minimal errors; and providing access mechanisms that are accessible by all stakeholders including the domain experts 302.

[0130] FIG. 4 illustrates a high-level illustration of data processing components associated with developing an FDP. According to an embodiment, generating an FDP comprises creating one or more scenarios or simulation contexts 402 for / or associated with a user input or a query. This can involve automating the creation of the one or more scenarios to enhance accuracy of results generated by the disclosed generative Al system as well as reduce the execution time for generating said results by the generative Al system.

[0131] Furthermore, FDP development may comprise generating FDP assessment data 404 based on the one or more scenarios or simulation contexts 402. In one embodiment, the FDP assessment data assesses or otherwise evaluates a plurality of development plan scenariosto provide actionable insights and recommendation strategies for developing an energy resource associated with a resource site.

[0132] In some cases, the FDP assessment data 404 may be further optimized to generate optimized FDP assessment data 406. This can involve enhancing the FDP assessment data 404 to ensure the creation of efficient and effective FDP strategies.

[0133] FIG. 5 shows a first exemplary interconnection of subsystems of the disclosed generative Al system. In the illustrated implementation, a data input, prompt, or query 502 can be received and / or managed and / or routed and / or analyzed by one or more data agent subsystems 504, 506, 508, and 510 of the disclosed generative Al system. After receiving the query 502, the generative Al system may leverage, via one of its agent subsystems 506, data elements 512 associated with the energy domain and / or the query, to accurately generate or extract vector data 514, and / or configure vector data 514, and / or combine the data elements 512 to generate the vector data 514. According to one embodiment, the vector data 514 may be retrieved by an agent subsystem of the generative Al system to generate context data 520 associated with the query received by the generative Al system. In some cases, the generative Al system also conducts data analysis on one or more of the data elements generate analytics data 518. Other agent subsystems (e.g., agent subsystem 510) of the generative Al system can also access, based on a transformed or otherwise analyzed query input, one or more control logic or functions comprised in a logic services or domain functions subsystem 516. The accessed or extracted control or computing logic 522 can be used to execute one or more data computations or computing operations including: seismic computing operations; petrophysical interpretation computing operations; geological modeling computing operations; well placement operations; and / or optimization computing operations. The computing operations may also include interpretation computing operations, petrophysical (e.g., saturation height modeling, rock typing, etc.) interpretation computing operations, and geological (e.g., well tops interpretation, property distribution, etc.) interpretation computing operations. In some embodiment, the computing operations include statistical analysis computing operations, optimization computing operations, data processing and transformation computing operations, time series analysis computing operations, clustering computing operations, and classification and simulation computing operations. It is appreciated that the extracted computing logic 522 can be associated with, or rather, based on the prompt or query 502, and / or based on one ormore data elements 512 associated with the query 502, and / or based on one or more vector data 514.

[0134] Data outputs or results 524 generated by the computing logic 522 may be combined or otherwise processed in conjunction with the context data 520, and / or processed in combination with the analytics data 518 to generate an updated prompt or query 528 which in turn is used to generate assessment data 532. According to one embodiment, one or more large language models 528 may be used by the disclosed generative Al system to facilitate data translations, and / or data transitions, and / or data transformations and / or data formatting: from natural language inputs / queries to computing instructions, and / or from computing results to readable assessment data outputs comprised in the assessment data 532. In an exemplary embodiment, the assessment data 532 may be used to generate the multi-dimensional visualization shown in FIG. 6, which indicates, for example, a multi-dimensional (e.g., 2- dimensional) map of an opportunity index associated with developing an oil and / or gas field.

[0135] FIG. 7 shows an exemplary workflow associated with energy production optimization. In this workflow, domain experts 702 (c.g, production engineer, production operations engineer, petroleum engineer, etc.) leverage, via one or more computing systems, a rapid, efficient, and automated daily production and optimization tool 704 based on the disclosed generative Al system. The rapid, efficient, and automated daily production and optimization tool 704 may advantageously facilitate a plurality of benefits 706 including: optimizing production via data insights; reducing analysis time associated with daily energy production; reducing access to inactive energy sources (c.g, inactive wells); and bridging data and process gaps associated with energy extraction.

[0136] FIG. 8 illustrates a high-level illustration of data processing components associated with energy production. According to an embodiment, generating production data using the disclosed approach comprises assessing various aspects of well performance and providing actionable data insights 802 based on the assessments. Following this, the actionable insights are leveraged in an automatic process to create computing models (c.g, energy production computing models) with attendant performance data as indicated in component 804. In one embodiment, the generated computing models can be used in one or more data workflows (e.g., computing logic or functions) to generate production forecast data and or other production insight data as indicated in component 806.

[0137] FIG. 9 shows a secondary exemplary interconnection of subsystems of the disclosed generative Al system. It is appreciated that the various subsystems illustrated in FIG. 9, functionally correspond to one or more subsystems shown in FIG. 5: query 502 can be functionally equivalent to query 902; agent subsystems 504, 506, 508, and 510 can correspond to agent subsystems 904, 906, 908, and 910; logic services subsystem 516 can operate similar to logic services subsystem 920. It is however appreciated that the subsystem interconnections shown in FIG. 9 beneficially allow leveraging data from a database 912 and from a modeling simulator 914 to generate analytics data 916 together with simulation data 918 which are both used, according to one embodiment, in combination with an executed computing logic 922 selected based, at least on a query input or prompt 902, to generate an updated prompt 926. As done in FIG. 5, one or more large language models 930 may be used by the disclosed generative Al system to facilitate data translations, and / or data transitions, and / or data transformations and / or data formatting: from natural language inputs / queries to computing instructions, and / or from computing results to readable assessment data outputs comprised in the assessment data 932. In one embodiment, the assessment data comprises energy production data including example analysis data of specific energy productions systems (e.g., an oil well) is indicated in FIG. 10

[0138] FIG. 11 shows a first exemplary detailed workflow 1100 for generating assessment data for energy development. It is appreciated that a data engine stored in a memory device may cause a computer processor to execute the various processing stages of the workflow 1100. For example, the disclosed techniques may be implemented as a data engine of a computing platform associated with a geological software tool such that the data engine enables optimally executing modeling subterranean structures at a resource site.

[0139] At block 1102, the data engine may provision an artificial intelligence (Al) system, the Al system comprising: one or more large language models (LLMs) configured to parse and transform natural language input queries; one or more data agent subsystems configured to coordinate data communication between two or more subsystems of the Al system; a database configured to store energy domain data; and a logic services subsystem configured to store a plurality of computing logic associated with energy development.

[0140] At block 1104, the data engine may coordinate receiving, by a first data agent of the one or more data agent subsystems of the Al system and via a first LLM of the one or moreLLMs, natural language input (e.g., a data query in natural language) associated with energy development.

[0141] At block 1106, the data engine may coordinate parsing, by the first data agent of the one or more data agent subsystems of the Al system, the natural language input and thereby generate query data for the Al system.

[0142] Turning to block 1108, the data engine may extract, based on the query data, data elements of at least the database to create scenario or context data associated with the natural language input.

[0143] In addition, the data engine may apply, based on the extracting, at least one computing logic comprised in the plurality of computing logic of the logic services subsystem, to the scenario or context data associated with the natural language input and thereby generate assessment data at block 1110.

[0144] At block 1112, the data engine may generate, based on the assessment data and using a second LLM of the one or more LLMs, a visualization on a graphical display device, the visualization comprising image or textual data indicating at least a strategy for energy development at a resource site.

[0145] In other embodiments, a system and a computer program can include or execute the method described above. These and other implementations may each optionally include one or more of the following features.

[0146] The Al system comprises a generative Al system, according to some embodiments.

[0147] In addition, the database is a vector database configured to store, based on the natural language input queries, data elements used to contextualize the natural language inputs.

[0148] Moreover, the plurality of computing logic comprise at least one of: statistical analysis computing logic; optimization computing logic; data processing and transformation computing logic; time series analysis computing logic; clustering computing logic; classification computing logic; and simulation computing logic.

[0149] In addition, the parsing can comprise conditioning the natural language input into computing instructions that are executable using the first data agent or a second data agent comprised in the one or more data agent subsystems of the Al system.

[0150] In some embodiments, the assessment data is associated with field development planning of an oil or gas resource at the resource site.

[0151] Furthermore, the field development planning comprises at least one of: seismic data analysis and interpretation associated with the resource site; reservoir model calibration associated with the resource site; well placement and trajectory design optimization associated with the resource site; waterflood and enhanced oil recovery optimization associated with the resource site; fluid production analysis associated with the resource site; well placement at the resource site; and petrophysical analysis associated with the resource site.

[0152] In some embodiments, the extracting step referenced above comprises: determining, based on the input query, the data elements of at least the database, such that the data elements of at least the database span a plurality of domains associated with energy development; and combining, based on the determining, the data elements of at least the database to generate a multi-domain dataset associated with the input query.

[0153] Moreover, the applying step referenced above comprises executing at least one data simulation using the multi-domain dataset to generate the assessment data.

[0154] Furthermore, the plurality of domains comprises: an upstream domain associated with exploring and producing energy; a midstream domain associated with transporting and storing energy; or a downstream domain associated with refining energy.

[0155] FIG. 12 shows a second exemplary detailed workflow 1200 for generating assessment data for energy development. It is appreciated that a data engine stored in a memory device may cause a computer processor to execute the various processing stages of the workflow 1200. For example, the disclosed techniques may be implemented as a data engine of a computing platform associated with a geological software tool such that the data engine enables optimally executing modeling subterranean structures at a resource site.

[0156] At block 1202, the data engine may provision an artificial intelligence (Al) system, the Al system comprising: one or more large language models (LLMs) configured to parse and transform natural language input queries; one or more data agent subsystems configured to coordinate data communication between two or more subsystems of the Al system; a database configured to store energy domain data; and a logic services subsystem configured to store a plurality of computing logic associated with energy development.

[0157] At block 1204, the data engine may coordinate receiving, by a first data agent of the one or more data agent subsystems of the Al system and via a first LLM of the one or more LLMs, natural language input associated with energy development.

[0158] Turning to block 1206, the data engine may coordinate parsing, by the first data agent of the one or more data agent subsystems of the Al system, the natural language input and thereby generate query data for the Al system.

[0159] In addition, the data engine may generate, based on the query data, production analytics data for a resource site as shown at block 1208.

[0160] At block 1210, the data engine may select, based on one or more data elements in the database associated with the natural language input, at least one computing logic comprised in the plurality of computing logic of the logic services subsystem.

[0161] Turning to block 1212, the data engine may determine, based on the production analytics data and the at least one computing logic, assessment data for fluid production optimization at the resource site.

[0162] At block 1214, the data engine may generate, based on the assessment data and using a second LLM of the one or more LLMs, a visualization on a graphical display, the visualization comprising image or textual data indicating at least one data parameter for the fluid production optimization at the resource site.

[0163] In other embodiments, a system and a computer program can include or execute the method described above. These and other implementations may each optionally include one or more of the following features.

[0164] The Al system referenced above is a generative Al system.

[0165] Moreover, the parsing discussed in association with FIG. 12 comprises conditioning the natural language input into computing instructions that are executable using the first data agent or a second data agent comprised in the one or more data agent systems of the Al system.

[0166] 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 protection of this disclosure.

[0167] Many processing techniques for collected data, including one or more of the techniques and methods disclosed herein, may also be used successfully with collected data types other than seismic data. While certain implementations have been disclosed in the context of seismic data collection and processing, those with skill in the art will recognize that one or more of the methods, techniques, and computing systems disclosed herein can be applied in many fields and contexts where data involving structures arrayed in a multi-dimensional space and / or subsurface region of interest may be collected and processed, e.g., medical imaging techniques such as tomography, ultrasound, MRI and the like for human tissue; radar, sonar, and LIDAR imaging techniques; mining area surveying and monitoring, oceanographic surveying and monitoring, and other appropriate multi-dimensional imaging problems.

[0168] Many examples of equations and mathematical expressions have been provided in this disclosure. But those with skill in the art will appreciate that variations of these expressions and equations, alternative forms of these expressions and equations, and related expressions and equations that can be derived from the example equations and expressions provided herein may also be successfully used to perform the methods, techniques, and workflows related to the embodiments disclosed herein.

[0169] While any discussion of or citation to related art in this disclosure may or may not include some prior art references, applicant neither concedes nor acquiesces to the position that any given reference is prior art or analogous prior art.

[0170] 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 to limit the invention to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The embodiments were chosen and described in order to explain the principles of the invention and its practical applications, to thereby enable others skilled in the art to utilize the invention and various embodiments with various modifications as are suited to the particular use contemplated.

Claims

CLAIMSWhat is claimed is:

1. A method for generating assessment data for energy development, the method comprising: provisioning an artificial intelligence (Al) system, the Al system comprising: one or more large language models (LLMs) configured to parse and transform natural language input queries, one or more data agent subsystems configured to coordinate data communication between two or more subsystems of the Al system, a database configured to store energy domain data, and a logic services subsystem configured to store a plurality of computing logic associated with energy development; receiving, by a first data agent of the one or more data agent subsystems of the Al system and via a first LLM of the one or more LLMs, natural language input associated with energy development; parsing, by the first data agent of the one or more data agent subsystems of the Al system, the natural language input and thereby generate query data for the Al system; extracting, based on the query data, data elements of at least the database to create scenario or context data associated with the natural language input; applying, based on the extracting, at least one computing logic comprised in the plurality of computing logic of the logic services subsystem, to the scenario or context data associated with the natural language input and thereby generate assessment data; and generating, based on the assessment data and using a second LLM of the one or more LLMs, a visualization on a graphical display, the visualization comprising image or textual data indicating at least a strategy for energy development at a resource site.

2. The method of Claim 1, wherein the Al system is a generative Al system.

3. The method of Claim 1 , wherein the database is a vector database configured to store, based on the natural language input queries, data elements used to contextualize the natural language inputs.

4. The method of Claim 1, wherein the plurality of computing logic comprise at least one of: statistical analysis computing logic, optimization computing logic, data processing and transformation computing logic, time series analysis computing logic, clustering computing logic, classification computing logic, and simulation computing logic.

5. The method of Claim 1, wherein the parsing comprises conditioning the natural language input into computing instructions that are executable using the first data agent or a second data agent comprised in the one or more data agent subsystems of the Al system.

6. The method of Claim 1, wherein the assessment data is associated with field development planning of an oil or gas resource at the resource site.

7. The method of Claim 6, wherein the field development planning comprises at least one of: seismic data analysis and interpretation associated with the resource site, reservoir model calibration associated with the resource site, well placement and trajectory design optimization associated with the resource site, waterflood and enhanced oil recovery optimization associated with the resource site, fluid production analysis associated with the resource site, well placement at the resource site, and petrophysical analysis associated with the resource site.

8. The method of Claim 1, wherein the extracting comprises: determining, based on the input query, the data elements of at least the database, such that the data elements of at least the database span a plurality of domains associated with energy development, and combining, based on the determining, the data elements of at least the database to generate a multi-domain dataset associated with the input query.

9. The method of Claim 8, wherein the applying comprises executing at least one data simulation using the multi-domain dataset to generate the assessment data.

10. The method of Claim 8, wherein the plurality of domains comprises: an upstream domain associated with exploring and producing energy, a midstream domain associated with transporting and storing energy, or a downstream domain associated with refining energy.

11. A system for generating assessment data for energy development, the system comprising: a computing platform comprising a database system, a data processing system, and a machine learning engine; a computer processor; and memory storing instructions which are executable by the computer processor to: provision an artificial intelligence (Al) system, the Al system comprising: one or more large language models (LLMs) configured to parse and transform natural language input queries, one or more data agent subsystems configured to coordinate data communication between two or more subsystems of the Al system, a database configured to store energy domain data, and a logic services subsystem configured to store a plurality of computing logic associated with energy development;receive, by a first data agent of the one or more data agent subsystems of the Al system and via a first LLM of the one or more LLMs, natural language input associated with energy development; parse, by the first data agent of the one or more data agent subsystems of the Al system, the natural language input and thereby generate query data for the Al system; extract, based on the query data, data elements of at least the database to create scenario or context data associated with the natural language input; apply, based on the extracting, at least one computing logic comprised in the plurality of computing logic of the logic services subsystem, to the scenario or context data associated with the natural language input and thereby generate assessment data; and generate, based on the assessment data and using a second LLM of the one or more LLMs, a visualization on graphical display, the visualization comprising image or textual data indicating at least a strategy for energy development at a resource site.

12. The system of Claim 11, wherein the plurality of computing logic comprise at least one of: statistical analysis computing logic, optimization computing logic, data processing and transformation computing logic, time series analysis computing logic, clustering computing logic, classification computing logic, and simulation computing logic.

13. The system of Claim 11, wherein the parsing comprises conditioning the natural language input into computing instructions that are executable using the first data agent or a second data agent comprised in the one or more data agent subsystems of the Al system.

14. The system of Claim 11, wherein the assessment data is associated with field development planning of an oil or gas resource at the resource site.

15. A method for generating energy assessment data for energy development, the method comprising: provisioning an artificial intelligence (Al) system, the Al system comprising: one or more large language models (LLMs) configured to parse and transform natural language input queries, one or more data agent subsystems configured to coordinate data communication between two or more subsystems of the Al system, a database configured to store energy domain data, and a logic services subsystem configured to store a plurality of computing logic associated with energy development; receiving, by a first data agent of the one or more data agent subsystems of the Al system and via a first LLM of the one or more LLMs, natural language input associated with energy development; parsing, by the first data agent of the one or more data agent subsystems of the Al system, the natural language input and thereby generate query data for the Al system; generating, based on the query data, production analytics data for a resource site; selecting, based on one or more data elements in the database associated with the natural language input, at least one computing logic comprised in the plurality of computing logic of the logic services subsystem; determining, based on the production analytics data and the at least one computing logic, assessment data for fluid production optimization at the resource site; and generating, based on the assessment data and using a second LLM of the one or more LLMs, a visualization on a graphical display, the visualization comprising image or textual data indicating at least one data parameter for the fluid production optimization at the resource site.

16. The method of Claim 15, wherein the Al system is a generative Al system.

17. The method of Claim 15, wherein the parsing comprises conditioning the natural language input into computing instructions that are executable using the first data agent or a second data agent comprised in the one or more data agent systems of the Al system.

18. A system for generating assessment data for energy development, the system comprising: a computing platform comprising a database system, a data processing system, and a machine learning engine; a computer processor; and memory storing instructions which are executable by the computer processor to: provision an artificial intelligence (Al) system, the Al system comprising: one or more large language models (LLMs) configured to parse and transform natural language input queries, one or more data agent subsystems configured to coordinate data communication between two or more subsystems of the Al system, a database configured to store energy domain data, and a logic services subsystem configured to store a plurality of computing logic associated with energy development; receive, by a first data agent of the one or more data agent subsystems of the Al system and via a first LLM of the one or more LLMs, natural language input associated with energy development; parse, by the first data agent of the one or more data agent subsystems of the Al system, the natural language input and thereby generate query data for the Al system; generate, based on the query data, production analytics data for a resource site; select, based on one or more data elements in the database associated with the natural language input, at least one computing logic comprised in the plurality of computing logic of the logic services subsystem; determine, based on the production analytics data and the at least one computing logic, assessment data for fluid production optimization at the resource site; and generate, based on the assessment data and using a second LLM of the one or more LLMs, a visualization on a graphical display, the visualization comprising image or textual data indicating at least one data parameter for the fluid production optimization at the resource site.

19. The system of Claim 18, wherein the Al system is a generative Al system.

20. The system of Claim 18, wherein the parsing comprises conditioning the natural language input into computing instructions that are executable using the first data agent or a second data agent comprised in the one or more data agent systems of the Al system.

Images