AUTOMATED OIL FIELD OPERATIONS AND LOG PROCESSING

Abstract

Some implementations include a computer-implemented method for determining one or more subsurface properties from one or more graphical oil field logs created during oil field of one or more oil field operation. The computer-implemented method may include graphically analyzing the graphical oil field logs; determining one or more regions of interest in the graphical oil field logs; generating, based on the graphical analysis of the graphical oil field logs, a respective textual description for each respective region of interest in the graphical oil field logs; and determining, by a large language model (LLM), one or more lithologies for each respective region of interest based on the textual description for the respective region of interest.

Description

TECHNICAL FIELD

Some implementations relate to oil field operations. More specifically, some implementations relate to interpreting images of oil field logs to inform and/or guide oil field operations.

BACKGROUND

Oil field log interpretation typically relies on trained and experienced engineers to identify log patterns, recognize trends, and provide detailed, composite analysis based on previous experience. These tasks may not be automated. As a result, engineers may perform these tasks by visually inspecting logs and converting them into useful information. Furthermore, in some instances, complete data sets that include text encoded data (such as ASCII encoded data) are unavailable. In these instances, engineers may have to visually inspect image data (such as data in PDF format) to analyze oil field logs.

BRIEF DESCRIPTION OF THE DRAWINGS

Implementations of the disclosure may be better understood by referencing the accompanying drawings.

FIG. 1 is a block diagram illustrating an example oil field log image processor.

FIG. 2 is a diagrammatic representation of input into an output from an oil field log image processor.

FIG. 3 is a flow diagram illustrating operations for generating oil field information based on one or more images of one or more oil field logs.

FIG. 4 is a diagrammatic illustration of an example output from some implementations.

FIG. 5 is a diagram illustrating an image including hydraulic fracturing data.

FIG. 6 is a perspective view of an example drilling rig system.

DESCRIPTION OF IMPLEMENTATIONS

The description that follows may include example systems, methods, techniques, and program flows that embody implementations of the disclosure. However, this disclosure may be practiced without these specific details. For clarity, some well-known instruction instances, protocols, structures, and techniques may not be shown in detail.

Overview

Oil field logs may include text encoded data (such as data encoded in the American Standard Code for Information Interchange (ASCII) format), graphs, images, and other graphical information. In some instances, only portions of the oil field logs are available. For example, in some instances, only a PDF image file or screen capture of an oil field log may be available. Hence, text encoded data included in the oil field log may be unavailable. Some implementations include computerized components and operations that process images of oil field logs (such as PDF images) and generate oil field information (such as lithologies) that inspire or guide oil field operations (such as drilling operations).

Some implementations include an oil field log image processor capable of interpreting images of oil field logs when text encoded data is unavailable. The oil field log image processor may analyze the image data to determine information conveyed in the oil field logs. For example, the oil field log image processor may analyze image data to determine signal information (such as information conveyed by resistivity graphs, gamma ray graphs, and more), textual information that is in image format, and other information. The image data may include pump cards, logs, real-time charts, circle charts, etc. The oil field log image processor may convert text that is represented in image format into text encoded data (such as data represented as ASCII format). After analyzing the image data, the oil field log image processor may generate text encoded data describing the information indicated in the oil field logs. For example, the oil field log image processor may generate text encoded data indicating resistivity values, drill bit information, and other information for regions of interest. The oil field log image processor may include a large language model (LLM) that may receive the text encoded data as input and determine oil field information (such as lithologies) based on the text encoded data. The oil field log image processor also may output one or more graphical images and text annotations describing aspects of regions of interest. Oil field operators may select and perform drilling operations based on the oil field information output by the oil field log analyzer.

Example Implementations

The section will describe some example implementations. First, this section will describe some example inputs and outputs for some implementations. Next, this section will describe an example component architecture and example operations for processing graphical oil field logs and generating subsurface properties (such as lithologies and/or other information) based on those logs.

FIG. 1 is a block diagram illustrating an example oil field log image processor. As shown, the oil field log image processor 102 includes components for performing operations described herein. For example, the oil field log image processor 102 may include an LLM 108. The LLM 108 may include or otherwise utilize a residual neural network, very deep and relational network (VGG), a Siamese network, or any other suitable neural network or machine learning device to perform operations described herein. The oil field log image processor 102 also may include an image-to-text generator 106, oil field information generator 110, and image analyzer 104. These components shown in FIG. 2 will be described in more detail with reference to FIGS. 2-3 and others herein.

FIG. 2 is a diagrammatic representation of example input provided to and example output received from an oil field log image processor 102. Some implementations of the oil field log image processor 102 may receive as input oil field log images 204-214. The oil field log images 204-214 may include a drill bit size image 204, gamma ray image 206, photoelectric factor image 208, neutron image 210, sonic image 212, and resistivity image 214. The oil field log images 204-214 may include graphs indicating data values, text in graphical format (such as text represented via pixels of the image), lines, and any other suitable graphical indicia indicating information in an oil field log. For example, the oil field log images 204-214 may include one or more gamma ray graphs, neutron-porosity graphs, formation density graphs, sonic graphs, resistivity graphs, and/or nuclear magnetic resonance graphs.

In some implementations, the oil field log image processor 102 may process the oil field log images 204-214. After processing the oil field log images 204-214, the oil field log image processor 102 may generate the oil field information 202. The oil field information 202 may include text data (such as text encoded data and/or graphical text data) and graphical content describing lithologies, subsurface properties for particular wellbore depths, and/or any other suitable oil field information. For example, the oil field information 202 may include text data and graphical data indicating a likelihood of shale at a given depth range. The oil field information 202 also may include additional information such as porosity, fluid type, and other information for specified depth ranges. Oil field operators may utilize the oil field information 202 to determine where to drill, what subsurface operations may be needed, how to modify subsurface operations, and other suitable aspects of subsurface operations. Hence, oil field operators may schedule, modify, or otherwise perform subsurface operations based on oil field information 202.

FIG. 3 is a flow diagram illustrating operations for generating oil field information based on one or more images of one or more oil field logs. In FIG. 3, the flow 300 begins at block 302 where the image analyzer 104 loads one or more images of one or more oil field logs. For example, oil field logs may be represented as one or more Portable Document Format (PDF) files or any other suitable file format. The image analyzer 104 may retrieve one or more image files from a storage device (such as a cloud storage device) and load them into memory of a computing device. In some implementations, a user may perform a screen capture that creates a graphical image of an oil field log. The image analyzer 104 may load the screen capture into memory for further analysis (as described herein). Flow may continue at block 304.

At block 304, the image analyzer 104 may identify log tracks and/or individual curves (such as graphs) in the oil field log image. The image analyzer 104 may compare the oil field log image to one or more reference images (or perform other image processing operations) to identify log tracks and/or individual curves. For example, when identifying log tracks, the image analyzer 104 may identify individual columns in the oil field log image that display various measurements taken in the wellbore. Each track may present data for specific property of rock encountered by one or more logging tools in the wellbore. The image analyzer 104 may identify tracks for gamma ray responses, resistivity measurements, porosity data, and other suitable information derived during drilling or other wellbore operations. The curves may include graphs or other indicia indicating wellbore data (such as resistivity, gamma ray responses, etc.).

At block 306, the image-to-text generator 106 may generate text data indicating names, sequences, indices for curves, and/or tracks that were identified in the oil field log image at block 304. As a result of blocks 304 and 306, the image-to-text generator 106 may generate ASCII text data corresponding to text information represented in graphical format in the image of the oil field log. For example, the image-to-text generator 106 may generate ASCII text data that describes a curve representing resistivity values. Hence, in some implementations, the text data indicates all information necessary for determining oil field information such as lithologies, subsurface properties, equipment conditions, and more (as described in more detail herein).

At block 308, the image analyzer 104 may identify one or more regions of interest in the oil field log image(s). The regions of interest may relate to user-defined depths in a wellbore or other user-provided information. In other instances, image analyzer 104 may identify noteworthy regions of interest in the graphical oil field log. For example, the image analyzer 104 may identify a region of interest by identifying changes in curves of the oil field log. As a more specific example, a particular change in a gamma ray response graph may be identified as region of interest.

At block 310, the description generator 112 may generate text encoded data describing each of the one or more regions of interest. The text encoded data generated at block 310 may be based on text generated at block 306 (the text at block 306 describes graphs, curves, ranges, indexes, and other information from oil field log images). The text encoded data generated at block 310 may be used by the LLM 108 as described with reference to block 312.

At block 312, the LLM 108 may compare patterns in the text encoded data that describes a region of interest (text generated at block 310) to known text patterns. When a text pattern for a region of interest is similar to a known pattern, the LLM 108 may assign a similarity score indicating a strength of similarity between the patterns. There may be a plurality of know patters similar to the text pattern for the region of interest. The known patterns may identify subsurface properties such as lithography, porosity, fluid type, or other suitable subsurface properties. Each known pattern may be associated with a reference image depicting the subsurface property.

At block 314, the flow begins a loop for each region of interest.

At block 316, the LLM 108 may rank reference images based on the similarity score. As noted, each known text pattern may have an associated reference image depicting a subsurface property. For example, reference images may depict or otherwise indicate oil field information such as lithologies (such as shale, sandstone, limestone, and others) or other information. As noted, the LLM 108 may have found a plurality of known text patterns similar to a text pattern for the region of interest. The reference image associated with the most similar known text pattern may be ranked highest, whereas all other reference images may be ranked according to their relative degree of similarity to the text pattern for the region of interest.

At block 318, the LLM 108 may present the highest ranked reference image.

At block 320, the LLM may annotate the highest ranked reference image with additional information indicating aspects of the subsurface property. For example, the LLM 108 may annotate an image representing shale with text data indicating the image is shale. In some instances, the LLM 108 may have determined (such as from the text pattern comparison) information related to equipment, oil field conditions, or other aspects of oil field operations. In these instances, the LLM 108 may annotate reference image (or a final output image) accordingly. For example, the LLM 108 may have determined that a drill bit or pipe was stuck in the borehole at a given depth. Therefore, the LLM 108 may annotate the reference image (or final output image) to indicate the drill bit or pipe was stuck at the given depth. Therefore, some implementations enable operators to learn about the equipment malfunctions and other aspects of oil field operations.

At block 322, if there are more regions of interest to process, flow continues at block 310. With each additional loop, the LLM 108 may add reference images and annotations to form a compound image that includes a plurality of reference images and annotations. The oil field information 202 shown in FIG. 2 is an example of a compound image made from a plurality of reference images and annotations. If there are no more regions of interest, the flow ends.

FIG. 4 is a diagrammatic illustration of an example output from some implementations. In FIG. 4, the output 400 includes a lithology column 402 indicating at particular depths 404. The output 400 also includes a legend 406 identifying the various lithologies indicated in the lithology column 402. The legend 406 shows that the lithology column 402 includes imagery representing a bad hole, sandstone, sandy shale, shale, shaly sand, and unspecified properties. In some implementations, the lithology column 402 is a compound image built from unitary images selected as a result of one or more operations of FIG. 3. However, some implementations may create a unitary image that includes imagery similar to the various reference images determined as a result of one or more operations of FIG. 3. As shown, the output 400 may include portions of graphs taken from the oil field log images which were used as input into the oil field log image processor 102.

As noted, in addition to lithologies, output may include other information about subsurface operations. In some implementations, the LLM 108 may be trained to identify conditions related to a broad range of equipment types used in the subsurface operations. As a result, annotations included in the output 400 may inform oil field operators about pending equipment failures, necessary maintenance, and other aspects related to equipment used for oil field operations.

Some implementations may perform the operations described herein on images other than well logs images. The oil field log image processor 102 also may be configured to process mud logs, logging while drilling (LWD) logs, image logs, any suitable oil field graphs. Some implementations may be configured to process a series of images to detect rates of change shown in the pictures (such as consumption of materials, flow rates, etc.). Some implementations may be configured to reconstruct an approximate log database from an image, such as by sampling and reading log response values and indexing and selecting a range of values for the database.

FIG. 5 is a diagram illustrating an image including hydraulic fracturing data. In FIG. 5, the image includes a graph 510 including plots 502-506, line 508, a plurality of scales on the Y-axis, and a scale on the x-axis. In some implementations, the oil field log image processor 102 may perform operations similar to those described with reference to FIG. 3 on the image 500. As a result, some implementations may be configured to generate text describing information shown in the image 500, compare patterns in the text to known patterns, and provide output indicating various aspects of the hydraulic fracturing operations associated with the graph 510.

FIG. 6 is a perspective view of an example drilling rig system. In FIG. 6, the system 664 may form a portion of a drilling rig 602 located at the surface 604 of a well 606. Drilling of oil and gas wells may utilize a string of drill pipes connected together so as to form a drilling string 608 that may be lowered through a rotary table 610 into a wellbore or borehole 612. Here a drilling platform 686 may be equipped with a derrick 688 that supports a hoist. A computer 690 may be communicatively coupled to any of the devices attached to the system 664. The computer 690 may include the oil field log image processor (or any component thereof) and may be configured to process logging information (such as graphical oil field logs) collected by any component of the system 664 (as described herein). Some implementations may process logging information (such as graphical oil field logs) collected by any oil field device such as hydraulic fracturing devices and/or any other suitable devices. For example, graphical image oil field logs may be generated during construction activities including logging while drilling, wireline, cementing, well fracking, artificial lift, and others. The oil field log image processor 102 may be remote from the system 664 and may remotely process any suitable logging information collected by any one or more of the components of the system 664.

The drilling rig 602 may thus provide support for the drill string 608. The drill string 608 may operate to penetrate the rotary table 610 for drilling the borehole 612 through subsurface formations 614. The drill string 608 may include a Kelly 616, drill pipe 618, and a bottom hole assembly 620, located at the lower portion of the drill pipe 618.

The bottom hole assembly 620 may include drill collars 622, a down hole tool 624, and a drill bit 626. The drill bit 626 may operate to create a borehole 612 by penetrating the surface 604 and subsurface formations 614. The down hole tool may comprise any of a number of different types of tools including MWD tools, LWD tools, and others. The down hole tool 624 and other tools may (alone or in concert with other devices) generate one or more oil field logs that may be processes as described herein.

During drilling operations, the drill string 608 (including the Kelly 616, the drill pipe 618, and the bottom hole assembly 620) may be rotated by the rotary table 610. In addition to, or alternatively, the bottom hole assembly 620 may also be rotated by a motor (e.g., a mud motor) that may be located down hole. The drill collars 622 may be used to add weight to the drill bit 626. The drill collars 622 may also operate to stiffen the bottom hole assembly 620, allowing the bottom hole assembly 620 to transfer the added weight to the drill bit 626, and in turn, to assist the drill bit 626 in penetrating the surface 604 and subsurface formations 614.

During drilling operations, a mud pump 632 may pump drilling fluid (sometimes known by those of ordinary skill in the art as “drilling mud”) from a mud pit 634 through a hose 636 into the drill pipe 618 and down to the drill bit 626. The drilling fluid may flow out from the drill bit 626 and be returned to the surface 604 through an annular area 640 between the drill pipe 618 and the sides of the borehole 612. The drilling fluid may then be returned to the mud pit 634, where such fluid may be filtered. In some embodiments, the drilling fluid may be used to cool the drill bit 626, as well as to provide lubrication for the drill bit 626 during drilling operations. Additionally, the drilling fluid may be used to remove subsurface formation 614 cuttings created by operating the drill bit 626. It may be the images of these cuttings that many implementations operate to acquire and process.

Any operations of the equipment shown in FIG. 6 may be performed in response to output from the oil field log image processor 102 or as a result of one or more operations described herein. Additionally, planning and implementation of subsurface operations (such as hydraulic fracturing, operating tools, drilling, etc.) may be performed in response to output from the oil field log image processor 102 or as a result of one or more operations described herein.

FIGS. 1-6 and the operations described herein are examples meant to aid in understanding example implementations and should not be used to limit the potential implementations or limit the scope of the claims. None of the implementations described herein may be performed exclusively in the human mind nor exclusively using pencil and paper. None of the implementations described herein may be performed without computerized components such as those described herein. Some implementations may perform additional operations, fewer operations, operations in parallel or in a different order, and some operations differently. Some implementations may perform the operations with different components.

As used herein, a phrase referring to “at least one of” a list of items refers to any combination of those items, including single members. As an example, “at least one of: a, b, or c”is intended to cover: a, b, c, a-b, a-c, b-c, and a-b-c.

The various illustrative logics, logical blocks, modules, circuits, and algorithm processes described in connection with the implementations disclosed herein may be implemented as electronic hardware, computer software, or combinations of both. The interchangeability of hardware and software has been described in terms of functionality, and illustrated in the various illustrative components, blocks, modules, circuits and processes described throughout. Whether such functionality is implemented in hardware or software depends upon the particular application and design constraints imposed on the overall system.

The hardware and data processing apparatus used to implement the various illustrative logics, logical blocks, modules and circuits described in connection with the implementations disclosed herein may be implemented or performed with a general purpose single-or multi-chip processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general-purpose processor may be a microprocessor or any conventional processor, controller, microcontroller, or state machine. A processor also may be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. In some implementations, particular processes and methods may be performed by circuitry that is specific to a given function.

In one or more implementations, the functions described may be implemented in hardware, digital electronic circuitry, computer software, firmware, including the structures disclosed in this specification and their structural equivalents thereof, or in any combination thereof. Implementations of the subject matter described in this specification also may be implemented as one or more computer programs, such as one or more modules of computer program instructions stored on a computer storage media for execution by, or to control the operation of, a computing device.

If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. The processes of a method or algorithm disclosed herein may be implemented in a processor-executable instructions which may reside on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that may be enabled to transfer a computer program from one place to another. Storage media may be any available media that may be accessed by a computer. By way of example, and not limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store desired program code in the form of instructions or data structures and that may be accessed by a computer. Also, any connection may be properly termed a computer-readable medium. Disk and disc, as used herein, includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-Ray™ disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. Combinations also may be included within the scope of computer-readable media. Additionally, the operations of a method or algorithm may reside as one or any combination or set of codes and instructions on a machine readable medium and computer-readable medium, which may be incorporated into a computer program product.

Various modifications to the implementations described in this disclosure may be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other implementations without departing from the spirit or scope of this disclosure. Thus, the claims are not intended to be limited to the implementations shown herein but are to be accorded the widest scope consistent with this disclosure, the principles and the novel features disclosed herein.

Certain features that are described in this specification in the context of separate implementations also may be implemented in combination in a single implementation. Conversely, various features that are described in the context of a single implementation also may be implemented in multiple implementations separately or in any suitable subcombination. Moreover, although features may be described as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination may in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.

Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. Further, the drawings may schematically depict one more example process in the form of a flow diagram. However, some operations may be omitted and/or other operations that are not depicted may be incorporated in the example processes that are schematically illustrated. For example, one or more additional operations may be performed before, after, simultaneously, or between any of the illustrated operations. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the implementations described should not be understood as requiring such separation in all implementations, and the described program components and systems may be integrated together in a single software product or packaged into multiple software products. Additionally, other implementations are within the scope of the following claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve desirable results.

Some parts of this disclosure refer to the “trained plug movement detector” to clarify that the plug movement detector has completed training with the training data set. However, references to the “plug movement identifier” that do not include “trained” may nevertheless be referring to instances for which training is complete.

Example Clauses

Some implementations may include the following clauses.

• • Clause 1: A computer-implemented method for determining one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the computer-implemented method comprising: graphically analyzing each of the graphical oil field logs; determining at least one respective region of interest for each respective graphical oil field log; generating, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and determining, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.
  • Clause 2: The method of clause 1 further comprising: The computer-implemented method of claim 1, wherein the determining at least one of the subsurface properties further comprises: determining a respective reference image that best describes each respective textual description; determining respective annotations that describe each respective reference image; presenting the reference images and annotations on a media presentation device.
  • Clause 3: The method of any one or more of clauses 1-2 further comprising: performing an oil field operation in a wellbore based on at least one of subsurface properties.
  • Clause 4: The method of any one or more of clauses 1-3, wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph.
  • Clause 5: The method of any one or more of clauses 1-4, wherein the graphically analyzing the graphical oil field logs includes: loading a respective image of each respective one or more graphical oil field logs; identifying log traces in each of the respective graphical oil field log; and identifying curve names, ranges, and indexes in each respective graphical oil field log.
  • Clause 6: The method of any one or more of clauses 1-5, wherein the graphical oil field logs include images but do not include text encoded data.

Clause 7: The method of any one or more of clauses 1-6 wherein the graphical analysis includes reading respective textual image data in each respective graphical oil field log, and wherein the computer-implemented method further comprises: aligning the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.

• • Clause 8: One or more computer-readable mediums including instructions that, when executed by one or more processors, cause the processor to perform operations to determine one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the instructions comprising: instructions to graphically analyze each of the graphical oil field logs; instructions to determine at least one respective region of interest for each respective graphical oil field log; instructions to generate, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and instructions to determine, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.
  • Clause 9: The one or more computer-readable mediums of claim 8, wherein the instructions to determine at least one of the subsurface properties further comprise: instructions to determine a respective reference image that best describes each respective textual description; instructions to determine respective annotations that describe each respective reference image; instructions to present the reference images and annotations on a media presentation device.
  • Clause 10: The one or more machine-readable mediums of clause of any one or more of clauses 8-9 further comprising: instructions to perform an oil field operation in a wellbore based on at least one of subsurface properties.
  • Clause 11: The one or more machine-readable mediums of clause of any one or more of clauses 8-10, wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph.
  • Clause 12: The one or more machine-readable mediums of clause of any one or more of clauses 8-11, wherein the graphically instructions to analyze the graphical oil field logs includes: instructions to load a respective image of each respective one or more graphical oil field logs; instructions to identify log traces in each of the respective graphical oil field log; and instructions to identify curve names, ranges, and indexes in each respective graphical oil field log.
  • Clause 13: The one or more machine-readable mediums of clause of any one or more of clauses 8-12, wherein the graphical oil field logs include images but do not include text encoded data.
  • Clause 14: The one or more machine-readable mediums of clause of any one or more of clauses 8-13, wherein the instructions to graphically analyze include instructions to read respective textual image data in each respective graphical oil field log, and wherein the one or more computer-readable mediums further comprise: instructions to align the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.
  • Clause 15: A system comprising: one or more processors; one or more computer-readable mediums including instructions that, when executed by one or more processors, cause the one or more processors to perform operations to determine one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the instructions including, instructions to graphically analyze each of the graphical oil field logs; instructions to determine at least one respective region of interest for each respective graphical oil field log; instructions to generate, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and instructions to determine, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.
  • Clause 16: The system of clause 15, wherein the instructions to determine at least one of the subsurface properties further comprise: instructions to determine a respective reference image that best describes each respective textual description; instructions to determine respective annotations that describe each respective reference image; instructions to present the reference images and annotations on a media presentation device.
  • Clause 17: The system of any one or more of clauses 15-16 further comprising: instructions to perform an oil field operation in a wellbore based on at least one of subsurface properties.
  • Clause 18: The system of any one or more of clauses 15-17, wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph.
  • Clause 19: The system of any one or more of clauses 15-18, wherein the instructions to graphically analyze the graphical oil field logs includes: instructions to load a respective image of each respective one or more graphical oil field logs; instructions to identify log traces in each of the respective graphical oil field log; and instructions to identify curve names, ranges, and indexes in each respective graphical oil field log.
  • Clause 20: The system of any one or more of clauses 15-19, wherein the instructions to graphically analyze include instructions to read respective textual image data in each respective graphical oil field log, and wherein the one or more computer-readable mediums further comprise: instructions to align the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.

Claims

1. A computer-implemented method for determining one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the computer-implemented method comprising:

graphically analyzing each of the graphical oil field logs;

determining at least one respective region of interest for each respective graphical oil field log;

generating, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and

determining, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.

2. The computer-implemented method of claim 1, wherein the determining at least one of the subsurface properties further comprises:

determining a respective reference image that best describes each respective textual description;

determining respective annotations that describe each respective reference image;

presenting the reference images and annotations on a media presentation device.

3. The computer-implemented method of claim 1 further comprising:

performing an oil field operation in a wellbore based on at least one of subsurface properties.

4. The computer-implemented method of claim 1, wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph.

5. The computer-implemented method of claim 1, wherein the graphically analyzing the graphical oil field logs includes:

loading a respective image of each respective one or more graphical oil field logs;

identifying log traces in each of the respective graphical oil field log; and

identifying curve names, ranges, and indexes in each respective graphical oil field log.

6. The computer-implemented method of claim 1, wherein the graphical oil field logs include images but do not include text encoded data.

7. The computer-implemented method of claim 1, wherein the graphical analysis includes reading respective textual image data in each respective graphical oil field log, and wherein the computer-implemented method further comprises:

aligning the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.

8. One or more computer-readable mediums including instructions that, when executed by one or more processors, cause the processors to perform operations to determine one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the instructions comprising:

instructions to graphically analyze each of the graphical oil field logs;

instructions to determine at least one respective region of interest for each respective graphical oil field log;

instructions to generate, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and

instructions to determine, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.

9. The one or more computer-readable mediums of claim 8, wherein the instructions to determine at least one of the subsurface properties further comprise:

instructions to determine a respective reference image that best describes each respective textual description;

instructions to determine respective annotations that describe each respective reference image;

instructions to present the reference images and annotations on a media presentation device.

10. The one or more computer-readable mediums of claim 8 further comprising:

instructions to perform an oil field operation in a wellbore based on at least one of subsurface properties.

11. The one or more computer-readable mediums of claim 8, wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph.

12. The one or more computer-readable mediums of claim 8, wherein the graphically instructions to analyze the graphical oil field logs includes:

instructions to load a respective image of each respective one or more graphical oil field logs;

instructions to identify log traces in each of the respective graphical oil field log; and

instructions to identify curve names, ranges, and indexes in each respective graphical oil field log.

13. The one or more computer-readable mediums of claim 8, wherein the graphical oil field logs include images but do not include text encoded data.

14. The one or more computer-readable mediums of claim 8, wherein the instructions to graphically analyze include instructions to read respective textual image data in each respective graphical oil field log, and wherein the one or more computer-readable mediums further comprise:

instructions to align the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.

15. A system comprising:

one or more processors;

one or more computer-readable mediums including instructions that, when executed by the one or more processors, cause the one or more processors to perform operations to determine one or more subsurface properties from one or more graphical oil field logs created during one or more oil field operations, the instructions including,

instructions to graphically analyze each of the graphical oil field logs;

instructions to determine at least one respective region of interest for each respective graphical oil field log;

instructions to generate, based on the graphical analysis of each of the graphical oil field logs, a respective textual description for each respective region of interest; and

instructions to determine, by a large language model (LLM), at least one of the subsurface properties for each respective region of interest based on the respective textual description for the respective region of interest.

16. The system of claim 15, wherein the instructions to determine at least one of the subsurface properties further comprise:

instructions to determine a respective reference image that best describes each respective textual description;

instructions to determine respective annotations that describe each respective reference image;

instructions to present the reference images and annotations on a media presentation device.

17. The system of claim 15 further comprising:

instructions to perform an oil field operation in a wellbore based on at least one of subsurface properties.

18. The system of claim 15, wherein the graphical oil field logs include at least one of a gamma ray graph, a neutron-porosity graph, a formation density graph, a sonic graph, a resistivity graph, and a nuclear magnetic resonance graph.

19. The system of claim 15, wherein the instructions to graphically analyze the graphical oil field logs includes:

instructions to load a respective image of each respective one or more graphical oil field logs;

instructions to identify log traces in each of the respective graphical oil field log; and

instructions to identify curve names, ranges, and indexes in each respective graphical oil field log.

20. The system of claim 15, wherein the instructions to graphically analyze include instructions to read respective textual image data in each respective graphical oil field log, and wherein the one or more computer-readable mediums further comprise:

instructions to align the respective textual image data in each respective graphical oil field log to a portion of a curve of a graph in the respective graphical oil field log.