Method and system for simulating an image generation tool response

Description

1 / 49 “METHOD AND SYSTEM FOR SIMULATING AN IMAGE GENERATION TOOL RESPONSE” Cross-Reference to Related Applications

[0001] This application claims the benefits of U.S. Non-Provisional Application No. 18 / 140,844, filed April 28, 2023, which is incorporated herein by reference. technical area

[0002] The present technology relates to the simulation of the performance of the image generation tool and, more specifically, to the simulation of the response of an image generation tool to changes in image generation properties and operating parameters. Background

[0003] Various imaging tools, such as electromagnetic imaging tools, have been developed to generate downhole images in boreholes. In particular, such tools can characterize the properties of a formation as part of downhole imaging in boreholes. A large number of operational parameters can be controlled in the operation of imaging tools. However, it can be difficult to select suitable values ​​for the operational parameters to control the imaging tools in imaging a formation. In particular, a large number of geological variables can define a formation and ultimately affect the operation of the imaging tools. Furthermore, the properties of the borehole, including the mud filling the borehole, can exhibit great variation.Therefore, the large number of geological and borehole-related variables, along with the variation of these variables in different boreholes, makes it difficult to select appropriate values ​​for the operational parameters of the image generation tools. Brief Description of the Figures

[0004] In order to describe the manner in which the resources and advantages of this disclosure can be obtained, a more specific description is provided with reference to specific modalities which are illustrated in the figures. Petition 870260040778, dated 04 / 30 / 2026, page 9 / 119 2 / 49 attached. Understanding that these figures represent only illustrative modalities of disclosure and, therefore, should not be considered limiting to its scope, the principles in this document are described and explained with specificity and additional detail through the use of the accompanying figures, in which:

[0005] FIGURE 1A is a schematic diagram of an example of an operational logging environment during wellbore drilling, according to various aspects of the technology in question;

[0006] FIGURE 1B is a schematic diagram of an example of a downhole environment with piping, according to various aspects of the technology in question;

[0007] FIGURE 2A illustrates a perspective view of an LWD electromagnetic imaging tool.

[0008] FIGURE 2B illustrates another perspective view of the LWD electromagnetic imaging tool.

[0009] FIGURE 2C illustrates another perspective view of the LWD electromagnetic imaging tool.

[0010] FIGURE 3 shows an example of current density generated by the electromagnetic sensor of the LWD electromagnetic imaging tool operating to measure a formation.

[0011] FIGURE 4 illustrates a schematic diagram of an example pad for an electromagnetic imaging tool, according to various aspects of the technology in question;

[0012] FIGURE 5 illustrates a circuit model of the example base shown in FIGURE 4, according to various aspects of the technology in question;

[0013] FIGURE 6 is a graph of the impedances measured by the electromagnetic imaging tool in relation to the formation resistivity Rt., according to various aspects of the technology in question;

[0014] FIGURE 7 is a graph of the absolute value of the measured impedance versus the formation resistivity that corresponds to the measurements shown in FIGURE 6, according to various aspects of the technology in question; Petition 870260040778, dated 04 / 30 / 2026, page 10 / 119 3 / 49

[0015] FIGURE 8 illustrates a flowchart of an example of a simulation method of a tool response in a synthetic formation according to one or both changes in the image generation properties and changes in the operational parameters of the tool, according to various aspects of the technology in question;

[0016] FIGURE 9A is a graph of an example of a resistivity profile of a synthetic medium, according to various aspects of the technology in question;

[0017] FIGURE 9B is a graph of a relative permittivity profile of the synthetic medium, according to various aspects of the technology in question;

[0018] FIGURE 9C is a profile of the separation of the synthetic medium in conjunction with an electromagnetic imaging tool operating in the synthetic medium, according to various aspects of the technology in question;

[0019] FIGURE 10A illustrates a schematic representation of an experimental setup to generate a response from the tool, according to various aspects of the technology in question;

[0020] FIGURE 10B illustrates a schematic representation of an alternative experimental setup for generating a response from the tool, according to various aspects of the technology in question;

[0021] FIGURE 11A is a graph of an example resistivity profile of a synthetic medium generated based on the resistivity profile shown in FIGURE 9A using the nearest neighbor approach, according to various aspects of the technology in question;

[0022] FIGURE 11B is a graph of a relative permittivity profile of the synthetic medium that is generated based on the relative permittivity profile shown in FIGURE 9B using the nearest neighbor approach, according to various aspects of the technology in question;

[0023] FIGURE 11C is a separation profile of the synthetic medium in conjunction with an electromagnetic imaging tool operating in the synthetic medium using the nearest neighbor approach, according to various aspects of the technology in question; Petition 870260040778, dated 04 / 30 / 2026, page 11 / 119 4 / 49

[0024] FIGURE 12 illustrates an example of GUI 1200 for controlling the synthesis of a formation and simulating a tool response on the synthesized formation, according to various aspects of the technology in question; and

[0025] FIGURE 13 illustrates an example of a computing device architecture that can be used to perform various steps, methods, and techniques disclosed in this document. Detailed Description

[0026] Various forms of disclosure are discussed in detail below. While specific implementations are discussed, it should be understood that this is done for illustrative purposes only. A person skilled in the art will recognize that other components and configurations may be used without departing from the spirit and scope of the disclosure.

[0027] Other features and advantages of disclosure will be presented in the following description and, in part, will be obvious from the description or may be learned by practicing the principles disclosed in this document. The features and advantages of disclosure can be realized and obtained through the instruments and combinations particularly indicated in the appended claims. These and other features of disclosure will become more evident from the following description and the appended claims or may be learned by practicing the principles set forth in this document.

[0028] It will be noted that, for simplification and clarity of illustration, where appropriate, reference numbers have been repeated among the different figures to indicate corresponding or analogous elements. Furthermore, numerous specific details are established in order to provide a complete understanding of the embodiments described in this document. However, it will be understood by those skilled in the art that the embodiments described in this document can be practiced without these specific details. In other cases, methods, procedures, and components have not been described in detail so as not to obscure the relevant related feature being described. The figures are not necessarily to scale, and the proportions of certain parts may be exaggerated to better illustrate details and features. The description should not be considered as limiting the scope of the embodiments described in this document. Petition 870260040778, dated 04 / 30 / 2026, p. 12 / 119 5 / 49

[0029] As discussed earlier, various imaging tools, such as electromagnetic imaging tools, have been developed to generate downhole images in boreholes. In particular, such tools can characterize the properties of a formation as part of downhole imaging in boreholes. A large number of operational parameters can be controlled in the operation of imaging tools. However, it can be difficult to select suitable values ​​for the operational parameters to control the imaging tools in imaging a formation. In particular, a large number of geological variables can define a formation and ultimately affect the operation of the imaging tools. Furthermore, the properties of the borehole, including the mud circulating within the borehole, can exhibit significant variations.Therefore, the large number of geological variables and those related to the borehole, along with the variation of these variables in different formations, make it difficult to select appropriate values ​​for the operational parameters of image generation tools.

[0030] The disclosed technology addresses the above by providing a task planner for downhole imaging tools. Specifically, a task planner can help predict tool performance by running processing algorithms on synthetic or experimental data that simulate the conditions of a future job. Furthermore, the task planner can simulate and help identify operational parameter values ​​associated with an imaging tool.

[0031] The task planner can model realistic formation geologies with different properties, such as resistivity, permittivity, offset, dispersion, dielectric loss values, and muds with different compositions, as in the case of image generation tools. A representative formation environment can be simulated for a well that can be logged. Furthermore, users can provide inputs, for example, by drawing or entering the parameter values ​​of the formation layers themselves, to simulate the formation. Additionally, formation properties can be obtained from correlation wells to simulate the formation. The properties related to the formation and Petition 870260040778, dated 04 / 30 / 2026, page 13 / 119 6 / 49 to the borehole can be adjusted by users for various reasons, for example, to adjust the roughness of a borehole, add features such as vugs, breaks and fractures, and adjust the sizes and properties of the features. The operation of the tool according to variable operating parameters can be simulated on the represented formation, and the effects of such variable operating parameters can be reproduced for a user, for example, through a graphical user interface (GUI). The responses of the tools to variable operating parameters can be simulated using synthetic data or experimental data. Specifically, interpolation can be applied to existing responses to simulate cases that do not correspond to existing data points, or the response of the closest match between existing responses can be used.Quantitative estimation algorithms can also be integrated into the task planner to better predict tool performance, for example, by varying tool parameters for a specific task.

[0032] The technology is described in this document with respect to an electromagnetic imaging tool. However, the technology, as described in this document, can be applied to an applicable downhole imaging tool, such as an oil-based electromagnetic mud imager, a water-based electromagnetic mud imager, an acoustic imager, and a density imager.

[0033] Returning to FIGURE 1A, a drilling arrangement is shown that exemplifies a Logging While Drilling (commonly abbreviated as LWD) configuration in a 100-hole drilling scenario. Logging While Drilling typically incorporates sensors that acquire formation data. Specifically, the drilling arrangement shown in FIGURE 1A can be used to collect formation data via an electromagnetic imaging tool as part of wellhole logging using the electromagnetic imaging tool. The drilling arrangement in FIGURE 1A also exemplifies what is called Measurement While Drilling (commonly abbreviated as MWD), which uses sensors to acquire data from the Petition 870260040778, dated 04 / 30 / 2026, page 14 / 119 7 / 49 which path and position of the wellbore in three-dimensional space can be determined. FIGURE 1A shows a drilling rig 102 equipped with a tower 104 supporting a winch 106 for raising and lowering a drill string 108. The winch 106 suspends a top drive 110 suitable for rotating and lowering the drill string 108 by means of a wellhead 112. A drill bit 114 can be connected to the lower end of the drill string 108. As the drill bit 114 rotates, it creates a wellbore 116 that passes through various subterranean formations 118. A pump 120 circulates the drilling fluid through a feed pipe 122 to the top drive 110, down the inside of the drill string 108 and out through the drill bit holes 114 to the wellbore. The drilling fluid returns to the surface through the annulus around the drill string 108 and to a retention well 124.Drilling fluid carries cuttings from wellbore 116 to the retention well 124, and the presence of drilling fluid in the annulus helps maintain the integrity of wellbore 116. Various materials can be used for drilling fluid, including oil-based fluids and water-based fluids.

[0034] Logging tools 126 can be integrated into the downhole assembly 125 near the drill bit 114. As the drill bit 114 extends into the wellbore 116 through the formations 118 and as the drill string 108 is pulled out of the wellbore 116, the logging tools 126 collect measurements related to various formation properties, as well as tool orientation and various other drilling conditions. The logging tool 126 can be an applicable tool for collecting measurements in a drilling scenario, like the electromagnetic imaging tools described in this document. Each of the logging tools 126 may include one or more tool components spaced apart from each other and communicatively coupled by one or more wires and / or other communication arrangement.126 profiling tools may also include one or more computing devices communicatively coupled to one or more components of the tool. The one or more computing devices may be configured to control or monitor performance. Petition 870260040778, dated 04 / 30 / 2026, page 15 / 119 8 / 49 of the tool, process profiling data and / or perform one or more aspects of the methods and processes of this disclosure.

[0035] The bottom logging assembly 125 may also include a telemetry sub 128 for transferring measurement data to a surface receiver 132 and for receiving commands from the surface. In at least some cases, the telemetry sub 128 communicates with a surface receiver 132 by wireless signal transmission, for example, using mud pulse telemetry, EM telemetry, or acoustic telemetry. In other cases, one or more of the logging tools 126 may communicate with a surface receiver 132 by means of a wire, such as a wired drill pipe. In some cases, the telemetry sub 128 does not communicate with the surface but stores logging data for later retrieval at the surface when the logging assembly is recovered. In at least some cases, one or more of the logging tools 126 may receive electrical power from a wire extending to the surface, including wires extending through a wired drill pipe.In other cases, energy is supplied by one or more batteries or through energy generated at the bottom of the well.

[0036] The collar 134 is a frequent component of a drill string 108 and generally resembles a very thick-walled cylindrical tube, typically with threaded ends and a hollow core for transporting drilling fluid. Several collars 134 may be included in the drill string 108 and are constructed and intended to be heavy-duty to apply weight to the drill bit 114 to aid the drilling process. Due to the thickness of the collar wall, pocket-type cutouts or other types of recesses may be made in the collar wall without negatively affecting the integrity (strength, stiffness, and the like) of the collar as a component of the drill string 108.

[0037] FIGURE 1B shows an example of system 140 for performing downhole measurements after at least a portion of a wellbore has been drilled and the drill string removed from the well. An electromagnetic imaging tool can be operated on the example system 140 shown in FIGURE 1B to profile the wellbore. A downhole tool having a tool body 146 is shown for performing logging and / or Petition 870260040778, dated 04 / 30 / 2026, page 16 / 119 9 / 49 Other operations. For example, instead of using the drill string 108 of FIGURE 1A to lower the downhole tool, which may contain sensors and / or other instruments to detect and profile features and conditions near the wellbore 116 and surrounding formations, a cable carrier 144 may be used. The tool body 146 may be lowered into the wellbore 116 by means of the cable carrier 144. The cable carrier 144 may be anchored to the drilling rig 142 or by a portable means such as a truck 145. The cable carrier 144 may include one or more wires, slicklines, cables and / or the like, as well as tubular carriers such as flexible tubing, joint tubing or other tubulars. The downhole tool may include an applicable tool for collecting measurements in a drilling scenario, such as the electromagnetic imaging tools described in this document.

[0038] The illustrated cable carrier 144 provides power and support for the tool, as well as enabling communication between the 148A-N data processors on the surface. In some examples, the cable carrier 144 may include electrical and / or fiber optic cabling to perform communications. The cable carrier 144 is sufficiently strong and flexible to tether the tool body 146 through the wellbore 116 and, at the same time, allows communication via the cable carrier 144 with one or more of the 148A-N processors, which may include local and / or remote processors. The 148A-N processors may be integrated as part of an applicable computing system, such as the computing device architectures described herein. Furthermore, power may be supplied via the cable carrier 144 to meet the power requirements of the tool.For slickline or flexible pipe configurations, power can be supplied at the bottom of the well with a battery or via a downhole generator.

[0039] FIGURE 2A illustrates a perspective view of an LWD 200 electromagnetic imaging tool. FIGURE 2B illustrates another perspective view of the LWD 200 electromagnetic imaging tool. FIGURE 2C illustrates another perspective view of the LWD 200 electromagnetic imaging tool. The imaging tool Petition 870260040778, dated 04 / 30 / 2026, page 17 / 119 The 10 / 49 electromagnetic LWD 200 / mud imaging tool can be integrated as part of an applicable LWD drilling system, such as the 126 logging tools in the LWD 100 scenario shown in FIGURE 1A.

[0040] The LWD 200 electromagnetic imaging tool includes an electromagnetic sensor 202 arranged along a collar of the LWD 200 electromagnetic imaging tool. The LWD 200 electromagnetic imaging tool shown in FIGURES 2A-2C also includes the first and second ultrasonic transducers 204 and 206; however, in several embodiments, the LWD 200 electromagnetic imaging tool does not have ultrasonic transducers arranged along the collar. Specifically, the LWD 200 electromagnetic imaging tool shown in FIGURES 2A-2C is only one example of an LWD 200 electromagnetic imaging tool, and in several embodiments, an LWD 200 electromagnetic imaging tool may have a different design.Specifically, a water-based LWD electromagnetic imaging tool may have similar designs and may offer fewer design and interpretation complications than oil-based LWD electromagnetic imaging tools, for example, due to the conductive nature of water-based sludge.

[0041] Electromagnetic LWD imaging tools can provide a high-resolution image of the formation surrounding a borehole, for example, when compared to other borehole bottom imaging tools. As a result, electromagnetic LWD imaging tools can be used to identify damaged sections of the borehole, provide better knowledge about thin beds, and also provide images that can be used to determine the dip angle of the formation bed.

[0042] The sensor topology of LWD electromagnetic imaging tools operating in an LWD environment should have minimal complexity and, more importantly, should not depend on contact with the borehole. With respect to the LWD 200 electromagnetic imaging tool shown in FIGURES 2A-C, the electromagnetic sensor 202 may include a Petition 870260040778, dated 04 / 30 / 2026, page 18 / 119 11 / 49 single measuring electrode (also called probe, button, or current) mounted on the side of the collar. The electromagnetic sensor 202 can be arranged in the collar so that it is located at a certain distance, also known as offset, from the borehole wall during the operation of the LWD electromagnetic imaging tool. In addition, the electromagnetic sensor 202 may include a shielding electrode that surrounds at least a portion of the button electrode. This electrode can be excited by an alternating current sinusoidal wave generator and can be coupled to the formation by means of a slurry, for example, an oil-based slurry. This slurry is non-conductive to oil-based slurries. As a result, the coupling to the formation is achieved by means of displacement currents in the slurry. This arrangement provides low sensitivity to offset changes in the resulting microresistivity image.

[0043] In the operation of the LWD 200 electromagnetic imaging tool, a measuring current enters the formation, which may have a much lower resistivity than the mud. In the formation, the current flows by conduction and penetrates the formation. Then, the current returns to the borehole, where it returns to the body of the LWD 200 electromagnetic imaging tool that encloses the electromagnetic sensor 202, for example, the tool body serves as a return electrode for the LWD 200 electromagnetic imaging tool. The tool body can remain at ground potential due to its large surface area.

[0044] Image generation using the LWD 200 electromagnetic imaging tool can be achieved by dividing the collected data / measurements into azimuthal compartments as the LWD 200 electromagnetic imaging tool rotates in the borehole during drilling. The LWD electromagnetic imaging tool can also include an additional mud resistivity sensor, for example, a mud cell. In image generation using the LWD 200 electromagnetic imaging tool, the actual components of the measurements made by the electromagnetic sensor 202 can be used to determine formation resistivity. Furthermore, mud resistivity measurements made by the mud resistivity sensor can be used to improve the determined formation resistivity measurements. Petition 870260040778, dated 04 / 30 / 2026, page 19 / 119 12 / 49

[0045] The LWD 200 electromagnetic imaging tool can be a multi-frequency tool. Specifically, the LWD 200 electromagnetic imaging tool can operate at various frequencies when collecting measurements. For example, a higher frequency in the MHz range can be used to overcome the non-conductive nature of oil-based muds when generating measurements, while a lower frequency in the 100 kHz range can be more sensitive to offset and therefore can be used in offset determination. Furthermore, the offset information collected can be used to identify features in the formation. For example, a thin band of increased resistivity may be due to an opening in the rock. In turn, this may be reflected in a jump in apparent offset.

[0046] FIGURE 3 shows an example of current density 300 generated by the electromagnetic sensor 202 of the LWD 200 electromagnetic imaging tool operating to measure a formation. A power source conducts a voltage between the return electrode, whose voltage relative to ground is represented by Vreturn, and the probe electrode, whose voltage relative to ground is represented by Vprobe. Furthermore, a circuit is implemented to maintain Vprobe equal to, or approximately equal to, Vfocus to focus the measurement current. The current transmitted by the electromagnetic sensor is measured, for example, by using a toroid. The ratio of the voltage difference between the probe and the return to the transmitted current is used to calculate a measured impedance.A basic model based on circuit theory relating measured impedance to mud formation and parameters, applicable to LWD and cable tools, will be provided after a discussion of electromagnetic cable tools.

[0047] The discussion now continues with a discussion of cable electromagnetic imaging tools. FIGURE 4 illustrates a schematic diagram of an example of a base 400 of a cable electromagnetic imaging tool, as described in FIGURE 1B. Specifically, the wireless electromagnetic imaging tool can be integrated into the tool body 146 of the downhole tool of FIGURE 1B. More specifically, the base 400 can be arranged on an external surface of the tool body 146 to make measurements as the tool Petition 870260040778, dated 04 / 30 / 2026, page 20 / 119 13 / 49 of the wellbore is operated within the wellbore. The electromagnetic imaging tool works to collect measurements during well logging, for example, for imaging purposes of a formation surrounding the wellbore. Specifically, the electromagnetic imaging tool can operate in drilling mud to collect measurements for imaging the formation surrounding the wellbore. The electromagnetic imaging tool can operate in an applicable type of drilling mud, such as oil-based mud or water-based mud, to profile the wellbore. Oil-based muds have much higher resistivities than water-based muds. Therefore, the mud effect is much stronger on measurements taken in oil-based muds.When operating to profile the wellbore, the electromagnetic imaging tool can gather applicable measurements that can be measured by the electromagnetic imaging tool. For example, measurements made by the electromagnetic imaging tool may include apparent specific impedance and impedance measurements in the electromagnetic imaging tool, complex impedance measurements in the electromagnetic imaging tool, voltage measurements in the electromagnetic imaging tool, current measurements in the electromagnetic imaging tool, phase measurements in the electromagnetic imaging tool, and absolute values ​​of impedance measurements in the electromagnetic imaging tool.

[0048] Measurements collected by the electromagnetic imaging tool can be used to identify formation values ​​and mud properties, also called imaging properties, associated with the electromagnetic imaging tool, for example, parameters inside and outside the wellbore. Imaging properties include applicable parameters that can be identified from measurements made by the electromagnetic imaging tool for imaging purposes, for example, through the wellbore. Furthermore, imaging properties may include applicable properties of a wellbore and of the formation in which the wellbore is formed that ultimately affect the imaging or logging of the formation through the wellbore. Petition 870260040778, dated 04 / 30 / 2026, page 21 / 119 14 / 49 For example, the imaging properties may include mud permittivity, mud resistivity, offset, formation permittivity of a wellbore formation, and wellbore formation resistivity. The values ​​of the imaging properties can be identified using the techniques described herein on a per-button basis for wired imaging. For example, formation resistivity, formation permittivity, mud resistivity, mud permittivity, and offset values ​​can be identified for each button included as part of a 402 button set on a 400 basis. For LWD imaging, measurements are generally obtained using a single button electrode. In this case, azimuthal coverage is obtained by dividing the measurements into azimuthal compartments as the tool rotates.Thus, these azimuthal compartments in an LWD tool serve the same purpose as the measurements made by multiple circumferentially spaced button electrodes around the tool in a cable tool. Although the origin of the measurements differs in LWD and cable tools, the processing methods described in this document apply equally to both types of tools.

[0049] When operating the cable electromagnetic imaging tool to collect measurements for imaging, a voltage difference can be applied to the 402 button assembly and the first and second return electrodes 404-1 and 404-2 (404 return electrodes) of the 400 base. This voltage difference can generate currents that pass from the 402 button assembly to the mud and surrounding formation. The 400 base also includes a 406 shielding electrode around the 402 button assembly. The same potential applied to the 402 button assembly can be applied to the 406 shielding electrode to concentrate all or a substantial portion of the emitted current into the mud and surrounding formation. Specifically, the current can be emitted substantially radially into the surrounding formation by applying the same potential to the 406 shielding electrode and the 402 button assembly.An applicable electrical and / or thermal insulating material, such as ceramic, may fill the remaining portions of base 400. For example, a ceramic material may be placed between the return electrodes 404 and the protective electrode 406. Base 400 is covered by... Petition 870260040778, dated 04 / 30 / 2026, page 22 / 119 15 / 49 less in part, by a 408 housing. The 408 housing, and consequently the 400 base through the 408 housing, can be connected to a chuck by means of a clamping mechanism. The clamping mechanism can be a movable mechanism that moves the 408 housing and the contained base 400 to maintain substantial contact with the formation. For example, the clamping mechanism may include an arm that opens and / or rotates to move the 408 housing and the contained base 400. By moving the 408 housing and the contained base to maintain good contact with the formation, the mud effect can be minimized for cable imaging tools.

[0050] Returning to the discussion about the mud effect and its impact on electromagnetic imaging tools, the mud effect, as described earlier, refers to the contribution of mud to the measured impedance. Furthermore, and as discussed previously, this effect is particularly severe if a formation has low resistivity and the distance between the outer surface of the button electrode and the borehole wall, for example, the formation, is high. In these cases, the measured impedance may have very low sensitivity to the formation features. Maintaining good contact between the 400 base and the formation can help cable imaging tools ensure that the electromagnetic imaging tool actually measures the formation and not just the mud when the formation has low resistivity.Since the mud effect is a function of clearance, the term clearance effect can be used interchangeably with mud effect in what follows.

[0051] FIGURE 5 illustrates a circuit model of the example base 400 illustrated in FIGURE 4. Although the exact tool design is different for LWD tools, as described in FIGURES 2A-3, the equations derived from the circuit model shown in FIGURE 5 are applicable to LWD tools. In the model, H denotes the housing (including the chuck), F denotes the formation, B or G denotes the button and guard assembly, and R denotes the return signal from the formation and / or slurry. Although most of the transmitted current may be returned to the return electrodes, some portion of the transmitted current may return through the housing and / or chuck. An impedance value for each button can be calculated by measuring the voltage between the buttons and the return electrodes and dividing the measured voltage by the current transmitted by each button in the assembly. Petition 870260040778, dated 04 / 30 / 2026, page 23 / 119 16 / 49 of buttons. Specifically, this technique is represented in Equation 1 shown below. In Equation 1, Z is the impedance of one of the buttons in the button assembly, Vbr is the button return voltage, and Ib is the button current. With respect to the LWD tools described in FIGURES 2A-C and Figure 3, Vbr can be replaced by the probe to return the voltage, and Ib can be replaced by the probe current.

[0052] Equation 1 Z = VBR IB

[0053] A calculated button impedance, for example, calculated by Equation 1, can be equal to the impedances of the button and protection assembly and the formation Zbf and to the return and formation impedances Zrf, as shown in the circuit model of FIGURE 5. Although Zbf and Zrf are indicated with respect to formation F, Zbf and Zrf can have contributions from both the mud and the formation. Thus, Zbf can be equivalently represented by Equation 2 shown below.

[0054] Equation 2 Z « ZBF= Zmud+ ZF

[0055] Thus, a measured button impedance, as shown in Equation 2, can have contributions from both the mud and the formation. If the imaginary parts of Zf and Zmud are primarily capacitive, and assuming that this capacitance is in parallel with the resistive portion, Zbf can also be written as shown in Equation 3 below.

[0056] Equation 3 ZBF= —1--r + —1—r CM fe+M

[0057] In Equation 3, R and C denote resistance and capacitance, and ω is the angular frequency (e.g., ω = 2nf, where f is the frequency in Hz). In Equation 3, the subscript M denotes the mud, while F denotes the formation. Both mud resistance and mud capacitance can increase with spacing and decrease with the effective areas of the buttons.

[0058] Equation 3 can only provide a basic approximation of the impedance measured by the electromagnetic imaging tool. However, Equation 3 can be useful for illustrating the effects of mud and formation properties on the measured impedance. Specifically, from Equation 3, Petition 870260040778, dated 04 / 30 / 2026, page 24 / 119 17 / 49 it can be deduced that high frequencies are necessary to reduce the contribution of the mud to the measured impedance.

[0059] Equation 3 can also be used to obtain basic performance curves of an imaging tool that are quite accurate in homogeneous formations. FIGURE 6 shows a graph of the real parts of the measured impedance collected by an electromagnetic imaging tool in relation to the formation resistivity. The imaginary part of the impedance can be significantly affected by the mud capacitance and is therefore not presented in this disclosure. The formation permittivity (er) is assumed to be 15, the mud permittivity (em) to be 6, and the mud resistivity (Pm) to be 8000 Ω-m. Results are shown for three different frequencies (1 MHz, 7 MHz, and 49 MHz) at 2 different offsets (1 mm and 3 mm). The offset may include the distance from the outer surface of the base to the borehole wall.

[0060] As shown in FIGURE 6, interpreting the tool response is not easy. Specifically, the tool response does not vary linearly with formation resistivity. Instead, it is a complicated function of the formation and mud properties (resistivity and permittivity), as well as the offset. The dominant effect at low formation resistivities and low frequencies can be the offset effect. Small variations in offset can cause a large difference in the impedance reading if these raw measurements are used. For high formation resistivities and high frequencies, the formation permittivity may begin to have the greatest contribution to the measured impedance. This can cause the apparent resistivity curve to decrease after a certain formation resistivity (the resistivity value at which this effect begins to appear depends on the formation and the tool); therefore, it is called dielectric shear.

[0061] FIGURE 7 is a graph of the absolute value of the measured impedance versus the formation resistivity that corresponds to the measurements shown in FIGURE 6. As shown in FIGURE 7, the absolute value of the impedance does not suffer a clipping due to the dielectric effect at high formation resistivities. However, the sensitivity of the tool to resistivity can be quite reduced. Petition 870260040778, dated 04 / 30 / 2026, page 25 / 119 18 / 49 as demonstrated by the absolute value of the impedance, which is nearly flat with changes in formation resistivity.

[0062] The disclosure now continues with a discussion of task planner technology for imaging tools, such as the electromagnetic imaging tools discussed in relation to FIGURES 3 to 7. As demonstrated in the previous discussion, mud can significantly affect the performance of an oil-based mud imaging tool at low formation resistivities, while the dielectric effect due to formation permittivity can be more significant at high formation resistivities. These effects can be reduced through appropriate selection of operating parameter values, for example, the tool's operating frequencies. However, there may be a limit to the number of frequencies a tool can employ, for example, due to limitations on the data that can be transmitted upwell in real time.Alternatively, data can be saved in the bottom hole, but even in that case, hardware limitations may restrict the number of frequencies in most practical applications to fewer than 5.

[0063] The effects of drift are exacerbated under certain conditions. For example, if proper base pressure is not applied, bases may exhibit greater drift variations and occasionally loss of contact with the borehole wall. In a rough borehole, the high impedance may be seen by the transmitters, thus increasing the power requirements for transmission by the transmitters. In addition, higher logging speeds may reduce signal-to-noise ratios and decrease tool resolution.

[0064] The applicable operational parameters, including the operational parameters described above, can be selected with the help of a task planner that implements the technology described in this document, effectively optimizing the operational parameters of a given tool operating in a given formation. The operational parameters, as used in this document, include applicable parameters that can be varied in relation to the operation of a tool. Petition 870260040778, dated 04 / 30 / 2026, page 26 / 119 19 / 49 downhole imaging for a specific imaging task. For example, operating parameters may include, for instance, in the case of an electromagnetic imaging tool, operating frequencies, logging speeds, base pressures, base-to-curvature mismatch, and power requirements. Operating parameters may also include the selection of an appropriate base curvature, for example, based on the drill bit size used in the wellbore.

[0065] In addition, other effects can be visualized to improve understanding of the tool's response and aid in the interpretation of measurements. For example, different environments may have different amounts of thermal noise, which can affect image quality. It may be possible to simulate the effect of noise on expected responses using the proposed task planner. Noise can be added to the tool's response, as will be described later. The amount of uncertainty for a given noise level can be calculated from the deviation of the results of a quantitative estimation process, which will also be described in detail later, for the noisy case compared to the results for the noise-free case. This, in turn, can be used to help select the operating frequencies of the image generation tool, as discussed earlier.The effect of the curvature differences between the base and the tool can also be visualized.

[0066] The task planner can also be configured to take into account different image generation properties. Image generation properties can include applicable parameters that define or characterize a formation in which an image generation tool operates downhole. These image generation properties can be human-controlled parameters that create features within the formation. Examples of image generation properties include formation properties such as vugs, breaks, and fractures, which can define a formation and affect the tool's response in the formation imaging operation. Image generation properties can also include applicable parameters related to creating a wellhole in a formation and ultimately defining the wellhole within the formation. For example, image generation properties can include the Petition 870260040778, dated 04 / 30 / 2026, page 27 / 119 20 / 49 Mud properties, including mud permittivity variation, mud resistivity variation, and mud oil-to-water ratio variation related to the type of mud used in a specific well, can affect the image feature appearance. In most cases, a borehole can already be selected with a specific mud. In these cases, it can be instructive to inspect the appearance of different formation features at different operating frequencies for the specific mud used in the well. In other cases, the job planner can be used to select a specific mud for drilling a well hole in a formation.Thus, analysts can visualize the expected responses for the provided image generation parameters and use these expected responses to select the operational parameters that lead to a more straightforward interpretation while simultaneously satisfying other requirements, such as profiling time and energy consumption. Furthermore, this can aid analysts in interpreting the images.

[0067] Analysts can more easily discern the underlying causes that produce observed features when actual image generation profiling is obtained, once they are equipped with a tool that shows the expected response for certain operational parameters and image generation properties. This tool can help analysts understand the underlying geology, identifying potential problems and their root causes, as well as determining the noise level of the environment.

[0068] The described task planner can also be used for educational purposes, so that image analysts can become more familiar with a specific image generation tool for a variety of conditions and help improve their interpretation skills. An instructor can explain the different components of the task planner's GUI and demonstrate how the raw response and quantitative estimation results vary in different scenarios. To ensure repeatability in these scenarios, users can have the option to set the seed of the random means generator.

[0069] FIGURE 8 illustrates a flowchart of an example of a simulation method for the tool's response in a synthetic formation, according to one or both changes in the image generation properties and changes in the Petition 870260040778, dated 04 / 30 / 2026, page 28 / 119 21 / 49 operational parameters of the tool. The method shown in FIGURE 8 is provided as an example, as there are several ways to execute the method. Furthermore, although the example method is illustrated with a specific order of steps, those skilled in the art will know that FIGURE 8 and the modules shown in it can be executed in any order and may include fewer or more modules than those illustrated. Each module shown in FIGURE 8 represents one or more steps, processes, methods, or routines of the method.

[0070] In step 800, a synthetic formation is generated based on one or more image generation properties. The image generation properties, as will be discussed in more detail later, can be selected based on input received from a user. Specifically, a user can provide information about image generation property values ​​to be used in the synthesis of a formation through a GUI. For example, a user can provide mud properties to form a well hole in a formation, which ultimately affects the image characteristics and features within the image. The tool's response to the synthetic formation implemented through a formation generator and the other image generation properties and operational parameters can be simulated using an applicable technique. Specifically, the image generation tool's response can be simulated by applying one or more applicable models.Furthermore, the tool's response can be simulated based on data from one or more reference logs. For example, a reference log of actual measurements taken on a specific formation or on a formation adjacent to that specific formation can be used to simulate the tool's response.

[0071] In step 802, the response of an image generation tool operating according to one or more operational parameters to generate images of the synthetic formation is simulated to generate a response from the synthetic tool. Specifically, the values ​​of the operational parameters can be selected for a given task. More specifically, a user can provide information related to the selection of operational parameter values ​​for a given task. For example, a user can specify operating frequencies. Then, the operation of the image generation tool in Petition 870260040778, dated 04 / 30 / 2026, page 29 / 119 22 / 49 synthetic formation is simulated for the given mud properties and according to the selected operating parameter values. The tool response can be simulated using an applicable technique. Specifically, the tool response can be simulated by applying one or more models. For example, the tool response can be simulated using an advanced model. The advanced model can be run on demand using simulation code. Furthermore, the advanced model can be applied based on previous simulation results from one or more imaging tools. Additionally, the tool response can be simulated based on previous experimental measurements. For example, previous measurements generated in the simulation of the tool response on earlier versions of the simulated formation can be used in the simulation of a current tool response.

[0072] As will be discussed in more detail later, the synthetic formation generated in step 800 can be implemented using a random or pseudo-random generator. A random or pseudo-random generator can include a system that generates random or pseudo-random variations in one or both imaging properties and operational parameters. For example, a random or pseudo-random generator can generate variations in imaging properties that comprise at least one of the complex formation resistivities and relative permittivity. The response of the imaging tool operating to image the synthetic formation simulated in step 802 can be implemented using the techniques mentioned above.

[0073] In step 804, a change is identified in at least one or more image generation properties and one or more operational parameters. Changes in image generation properties and operational parameters can be identified based on input received from a user. For example, a user might specify simulating the tool's response on a synthetic formation with variable formation properties and offset values. In turn, the formation properties and offset values, for example, as part of the image generation properties, can be adjusted according to the input received from the user. Petition 870260040778, dated 04 / 30 / 2026, page 30 / 119 23 / 49

[0074] In step 806, the tool response according to the change in at least one or more image generation properties and one or more operational parameters is simulated to generate a modified synthetic tool response. Specifically, the tool response can be simulated again based on the changed image generation properties and / or operational parameters using the techniques described in this document. More specifically, and in the case of changed image generation properties, the synthetic formation can be modified based on the changed image generation properties to generate a modified synthetic formation. In turn, the tool response can be simulated on the modified synthetic formation.Furthermore, in the case of altered operational parameters, the tool response can be simulated again according to the altered operational parameters on the same synthesized formation in which the tool response was simulated. Alternatively, the tool response can be simulated according to the altered operational parameters on a modified synthetic formation that is generated based on the altered image generation properties.

[0075] In step 808, a representation of the modified synthetic tool response is reproduced to show an effect of changing at least one or more of the imaging properties and one or more of the operational parameters of the tool response. Specifically, and as will be discussed in detail later, the simulated tool response can be presented to a user. This can allow the user to visualize the effects of changing the imaging properties and / or operational parameters on the tool response. In this way, the user can adequately plan an actual wellbore drilling task and / or formation imaging task. Examples of graphs that can be visualized include the synthetic medium properties (if they have not already been visualized), the raw tool response, the processed tool response, and the quantitative estimation results.

[0076] Next, the user can compare the results of the simulated tool's response, for example, the quantitative estimate, with the ground data, for example, the properties of the generated synthetic medium. This Petition 870260040778, dated 04 / 30 / 2026, page 31 / 119 24 / 49 can be used to quantify the tool's performance. Additionally, a quality indicator can also be produced at this stage, for example, based on a comparison of the results with ground sight data. Furthermore, the user can further adjust the operational parameters and / or image generation properties based on the raw response, the processed response, the quantitative estimation results, the comparison of the quantitative estimation results with ground sight results, quality indicators, and the like. Parameters and properties can continue to be adjusted until the desired results are achieved. In turn, task parameters can be used to guide decisions in a future task, for example, a task for which the tool's response is simulated.

[0077] Alternatively, or in conjunction with the flowchart shown in FIGURE 8, additional image generation properties and / or operational parameters can be added. The formation can then be further modified based on the additional image generation properties to generate a new or otherwise modified synthetic formation. Furthermore, the tool response can be re-simulated on a synthetic formation or on a modified synthetic formation based on the additional operational parameters to generate the modified tool response. The additional image generation properties and additional operational parameters can include parameters that were not selected, specified, or included in previous formation generations and tool response simulations. For example, it is possible to simulate a tool response that does not take into account variations in offset values.Subsequently, the offset variation parameter can be applied to generate additional modified simulations of the tool's response.

[0078] Regarding formation synthesis, a GUI can be presented to generate a formation profile in a synthetic manner. Specifically, mud properties can be entered or loaded from an external file via the GUI. Mud properties can include mud resistivity, mud permittivity, and mud angle, for example, mud impedance phase angle, mud loss tangent, and other applicable mud-related properties. Mud properties can be based on a prediction. Petition 870260040778, dated 04 / 30 / 2026, page 32 / 119 25 / 49 of the type of mud that can be used in the well or can be based on an actual mud measurement. Mud measurements can be taken at a known temperature, and the GUI can include options to enter the measurement temperature and the predicted bottomhole temperature. Thus, the mud properties at the measurement temperature can be used to predict the mud properties at the borehole temperature. Mud properties can be determined by combining oil and water components with known properties. Mud properties can also be determined based on the oil-to-water ratio (OWR) and can be adjusted based on the predicted response obtained from the planner.

[0079] Image generation property graphs, such as formation resistivity, formation permittivity, and offset, can be generated by a formation generator and presented to a user as part of the synthetic formation simulation. An example of a formation generator could be a random or pseudorandom media generator. The ranges of the formation generator parameters, such as the minimum and maximum values ​​of formation resistivity, can be entered as inputs via the GUI. The thickness and width of the features can be controlled by adjusting the correlation lengths in the GUI box.

[0080] Some of the image generation parameters can be correlated with each other. For example, it is known that permittivity and formation resistivity generally have an inverse correlation. Such a correlation between properties can be used in the simulation of both properties, for example, simultaneously. Specifically, the properties can be simulated based on the correlation as negatively correlated random variables. Furthermore, the properties can be simulated by first simulating one of them and then using the simulated results to obtain a scaled image of the second property. For example, formation permittivity can be generated after the generation of the formation resistivity profile, taking the reverse image of the resistivity profile and scaling the range of permittivity values ​​so that it falls within the limits entered by the user via the GUI. Petition 870260040778, dated 04 / 30 / 2026, page 33 / 119 26 / 49

[0081] FIGURES 9A-C are representations of a synthesized formation generated using the technology described in this document. Specifically, FIGURE 9A is a graph of an example resistivity profile of a synthetic medium. FIGURE 9B is a graph of a relative permittivity profile of the synthetic medium. FIGURE 9C shows a drift profile of the synthetic medium in conjunction with an electromagnetic imaging tool operating on the synthetic medium. As shown in FIGURES 9A and 9B, resistivity and permittivity are inversely correlated.

[0082] Existing logs or other measurements made by various image generation tools can be used to generate the synthetic formation. For example, if a correlation well or LWD image is available, selected sections of that image can be used to obtain the synthetic formation. Users can load correlation wells and select the relevant section via a GUI. Correlation well data can be processed through quantitative estimation, a process that will be described in more detail later. Additionally, correlation well data can include raw data or raw data that has undergone some processing other than quantitative estimation. Correlation well data can be used as a substitute for the synthesized formation layer, which can be populated with scaled formation properties within the expected range.This filling process can be done by correlating the level of the formation properties with a feature of the raw data. For example, resistivity can be correlated with the real part of the measured impedance, while offset can be correlated with the absolute value of the measured impedance. Furthermore, the layers determined from the raw data can be filled with randomly or pseudo-randomly selected values ​​within an expected range of an image-generating property.

[0083] Logs generated by tools other than the tool that is the subject of a current task plan can be used to generate the synthesized formation. For example, if the synthesized formation is being created to simulate the response of the acoustic imaging tool, the resistivity logs Petition 870260040778, dated 04 / 30 / 2026, page 34 / 119 27 / 49 or dielectric logs from an existing well or adjacent wells can be used to synthesize the formation. Specifically, reference logs can serve as a constraint on the imaging properties selected for the synthesized formation.

[0084] By providing information via a GUI about image generation properties, the user can draw the outline of the formation layers or enter their dimensions via the GUI. Users can also directly enter values ​​for layer properties. For example, users can enter a range for layer property values, and the properties can be randomly changed within the desired range. In another example, users can enter a mean and standard deviation value for layer property values. In some cases, layer properties can be fully or partially randomized within a user-specified range that is entered via the GUI.

[0085] The dispersive nature of the formation and mud can be ignored in the generation of the synthesized formation. Furthermore, the formation permittivity can be considered complex, and the real and imaginary components of the synthesized formation can be generated. If the mud response is based on measurements, the dispersive nature of the mud properties can already be described by measurements taken at different frequencies. Similarly, if the formation response is based on experiments, the dispersive nature of the formation can be obtained from the experiment that most closely approximates the desired profile. In some examples, a synthesized formation that is closest to the user-created formation can be selected.

[0086] A numerical electromagnetic solver can be used as an advanced model to simulate tool response. Specifically, when simulations are used to obtain tool response, numerical electromagnetic solvers can be used to simulate the tool response. Numerical electromagnetic solvers can employ methods such as Finite Difference Time Domain (FDTD), Finite Element Method (FEM), and Method of Moments (MoM). Petition 870260040778, dated 04 / 30 / 2026, page 35 / 119 28 / 49

[0087] The formation response to the synthesized formation can be generated on demand. In other cases, to account for the significant computational time required by this simulation, the simulated responses can be stored in a library. Then, simulated responses for a tool operating on a specific synthesized medium can be generated by selecting the nearest available point in the library or by performing multidimensional interpolation. In the on-demand version, the generated random media can be simulated in their entirety. That is, all random media can be the input to the advanced model. In the case of using the library response to simulate the response, the library can include responses for a homogeneous formation (excluding the borehole) as the formation properties, mud properties, borehole radius, and spacing are varied.Next, responses can be generated pixel by pixel with the simplifying assumption that the environmental properties immediately in front of an electrode are the only ones that have a significant effect on the response.

[0088] Furthermore, a simple description of a tool's circuit, such as the circuit-based model for electromagnetic imaging tools described in this document, can be used to simulate the tool's response. Because these models are generally very fast, they can alleviate the need for a library and can be run on demand. In some modes, analytical models can be calibrated based on actual tool responses to increase accuracy. Even responses obtained using more complex computational models can be calibrated in some modes.

[0089] The disclosure now moves on to the discussion of an example experiment that can be used to generate a library of tool responses and / or calibrate a model to simulate a tool response. Specifically, FIGURE 10A illustrates a schematic representation of an experiment setup 1000 for generating a tool response. In experiment setup 1000, a tool base 1002 is placed in a fluid 1004 contained in a compartment 1006. The fluid 1104 may have known properties. Specifically, the fluid properties may be known by Petition 870260040778, dated 04 / 30 / 2026, page 36 / 119 29 / 49 using existing literature or measurements. For example, a vector network analyzer can be used to determine fluid properties over a frequency range. The tool's responses in experiment configuration 1000 can be stored, and the experiment can be repeated for a range of formation properties.

[0090] FIGURE 10B illustrates a schematic representation of an alternative experiment configuration 1050. In the experiment configuration 1050 shown in FIGURE 10B, the tool base 1002 is placed in compartment 1006 with a divider 1008 separating the fluid 1004 from a remaining portion of an enclosed area defined by compartment 1006. The divider 1008 may be formed by one or more layers of applicable material, such as a thin plastic film layer. The fluid 1004 may simulate the formation, while the region formed by the divider 1008 may simulate a slurry layer adjacent to the formation. The offset of the base 1002 may be simulated by placing plates on the divider 1008. Specifically, the offset from the formation may be altered by placing plates of known thickness on the divider 1008 and leaving the base 1002 on top of the plates. Such an arrangement can be more versatile and provide more realistic experimental responses by including the effect of mud.The properties of the mud and formation can be altered by replacing fluid 1004 with other fluids or by modifying the properties of fluid 1004, for example, by adding salt.

[0091] When using a tool response library to generate a simulated tool response, the nearest neighbors of the entries in the library can be used to generate a tool response for a specific synthetic formation, for example, a randomly synthesized formation. FIGURES 11A-C represent tool response measurements that are synthesized using nearest neighbor entries in a tool response library. Specifically, FIGURE 11A is a graph of an example resistivity profile of a synthetic medium that is generated based on the resistivity profile shown in FIGURE 9A using the nearest neighbor approach. FIGURE 11B is a graph of a relative permittivity profile of the synthetic medium generated based on the relative permittivity profile shown in FIGURE 9B using the nearest neighbor approach. FIGURE 11C shows Petition 870260040778, dated 04 / 30 / 2026, page 37 / 119 30 / 49 a distancing profile of the synthetic medium in conjunction with an electromagnetic imaging tool operating on the synthetic medium using the nearest neighbor approach. When generating the responses shown in FIGURES 11A-C, the properties of a response from the synthetic tool are combined with the elements of a response in the response library on a specific basis, for example, on a pixel-by-pixel basis.

[0092] A quantitative estimation component can be integrated into the task planner. Specifically, a quantitative estimation process can be used to compare the results of changing operational parameters and image generation properties in a tool response to the actual values ​​of a formation. This comparison can be used to quantify tool performance by comparing the quantitative estimation results with the synthetic medium properties for the selected operational parameters and image generation properties.

[0093] An inversion approach or a machine learning-based approach can be used for quantitative estimation. Specifically, a tool response can be simulated for inversion using an applicable advanced model, such as those described in this document. Then, the model parameters, including image generation properties such as formation resistivity, formation permittivity, formation loss tangent, offset, mud angle, mud permittivity, and mud resistivity, which minimize the difference between the response generated by random or pseudo-random means, as described previously, and the model response corresponding to these parameters, can be returned as the inversion output. An iterative process can be used for this purpose, such as the Gauss-Newton method. Model responses can be simulated beforehand on a grid within the expected parameter range.In some modes, this may be the same library used in creating the tool's synthetic response for the given random means. Then, the response for the desired parameters can be found through multidimensional interpolation if it is not on the grid, as mentioned earlier. Petition 870260040778, dated 04 / 30 / 2026, page 38 / 119 31 / 49

[0094] Equation 4 shows the essence of the inversion process; that is, finding the set of parameters (X, where the double bar represents that the set of parameters can be a matrix) that minimizes the difference between the synthetic measurements of the image generator (denoted as I) for the random medium =M created by the task planner and the modeled response (I) corresponding to a given set of parameters. Equation 4 ar,g^mm|| / — / M(%)||

[0095] Note that a vector is a special case of a matrix with a single row, in the case of a column vector, or a single column, in the case of a row vector. Furthermore, matrices can be flattened to obtain vectors. Therefore, these two terms are used interchangeably. Double bars denote the norm operation, i.e., minimization is in the least squares sense, which is one of the possible implementations. The function that is minimized is called the cost function. In some embodiments, a regularization term can be added to the cost function. Inversion can be done pixel by pixel; for example, a set of parameters can be solved for each measurement point in an image associated with the operation of a tool. Furthermore, in several embodiments, some of the parameters can be considered constant, at least in a zone of the created random media. For example, mud parameters can be considered constant in the generated image.Regularization can also be used to restrict sudden jumps in the inverted parameters. Note that the synthetic measurement matrix and the corresponding modeled response may include elements from each of the available frequencies. Ideally, the number of measurements should be equal to or greater than the number of unknowns. Otherwise, Equation 4 will be underdetermined, and a unique solution may not be obtained. In some cases, data from some frequencies may have greater weights in Equation 4 than data from other frequencies. For example, weights may be determined based on a noise estimate from the tool for a given frequency.

[0096] In other implementations, a regression function can be trained based on machine learning techniques using simulated data or measurements in known environments. Then, the response of a Petition 870260040778, dated 04 / 30 / 2026, p. 39 / 119 32 / 49 synthesized medium can be fed into the regression function to find the unknown formation and / or mud parameters as outputs. Applicable machine learning techniques, such as neural networks, random forests, or support vector regression techniques, can be used for this purpose. In some implementations, more than one regression function can be trained. The output of these regression functions can be a subset of the desired unknown mud and / or formation parameters. The inputs of these regression functions can also be different. For example, responses generated for the task planner's random medium from a different subset of frequencies can be used as inputs to different regression functions based on the sensitivities of their outputs to those frequencies.

[0097] It is also possible to use a hybrid machine learning and inversion approach. The hybrid approach can maintain the higher accuracy of the inversion approach while improving the computational time required to execute the approach compared to the pure inversion approach.

[0098] Noise can be added to the synthetic responses created for the synthesized formations to make the results more realistic. Users can change the noise level and observe the effect on the quality of the raw measurements as well as on the results of the quantitative estimate. Noise can be simulated as Gaussian noise with a given mean and standard deviation value. The mean can be set to 0, while the standard deviation can be estimated based on experimental data. Noise can be included in the responses additively or multiplicatively. Equation 5 is a representation of the additive introduction of noise. Equation 5 IN= I + A x β(μ,σ)

[0099] In Equation 5, A is the amplitude of the Gaussian noise, which may depend on the signal level and can be adjusted by the user. In several modes, A can be transformed into a percentage of the average or minimum signal level. In other cases, it may indicate an absolute quantity. G denotes a Gaussian distribution with mean μ and standard deviation σ. The upper bars indicate that the mean Petition 870260040778, dated 04 / 30 / 2026, page 40 / 119 33 / 49 and the standard deviation can be a function of parameters such as frequency or button index. IN is the response matrix after adding noise.

[0100] In several modes, a formation can be simulated to have a dip. A dip angle can be adjusted by a user from the GUI. Formations dipped onto a cylindrical surface would appear as sinusoidal features when projected onto an image. A random or pseudo-random media generator can first create sinusoidal layers with random thicknesses and then overlay additional random variations onto the layers. Alternatively, a random medium can be generated and tilted according to the desired tilt angle. This random medium can represent a cylindrical surface which can then be mapped onto a planar image to create the sinusoidal features.Similarly, formations can be drawn by a user using a sinusoidal feature of a given amplitude corresponding to a specific dip angle, or the generated formation can be subsequently tilted according to the desired tilt angle.

[0101] In several embodiments, a tool curvature radius and the planned borehole radius will have a mismatch. This mismatch can be called a geometric factor. Additionally, some of the button electrodes on the tool may have a greater offset than others. For example, if the borehole radius is larger than the tool curvature radius, and assuming the tool is not tilted, the center electrodes may touch the formation and the electrodes at the edges may have an inherent offset. The borehole radius can be entered via the GUI in the task planner and can be calculated considering a centered tool without tilt and incorporated into the synthetic tool response calculation. Users may have the option to view the effects of unusual circumstances, such as a tilted base.

[0102] Even without a mismatch between the tool and the borehole wall, different electrodes can behave differently due to their position in the assembly. This effect can also be known as a type of geometric factor. For example, the currents of the center electrodes Petition 870260040778, dated 04 / 30 / 2026, page 41 / 119 34 / 49 electrodes may be better focused, while electrodes at the edges may spread more. This inherent difference can be resolved if the data used in calculating the tool's response comes from experiments or accurate numerical modeling of the tool. Otherwise, if a simpler analytical formulation is used, this effect can be introduced empirically or through model calibration, as previously suggested.

[0103] In other cases, users may have the ability to add other more specialized features beyond the generated formation. Such features may include vugs, fractures, and ruptures. Such features can be created from basic shapes, such as rectangles and circles, whose dimensions, resistivities, and locations can be adjusted via the GUI. In some implementations, these features can be pasted onto the underlying formation, and by right-clicking on the feature, its properties can be modified. In some cases, users can drag and expand the shape's edges to distort and alter the shape, or draw a polyline on a graph as the feature's boundary. In some embodiments, multiple graphs can be linked to each other, so that the feature in one graph can also be displayed in the other graphs.For example, a vug added to the formation resistivity image may also appear in the formation permittivity and offset images. Users can change all material properties by right-clicking on a graph, or right-clicking on different graphs may give access to different properties. For example, editing the feature permittivity may only be allowed in the formation permittivity image.

[0104] Other processing techniques can be incorporated into the task planner and their effects can be simulated. One example of such processing codes is a signal processing-based image enhancement algorithm that attempts to reduce the effects of noise and other artifacts, such as the geometric factor. Another processing algorithm that can be incorporated into the planner is a combination algorithm that attempts to combine data of different frequencies based on a rule to obtain a combined image. Petition 870260040778, dated 04 / 30 / 2026, page 42 / 119 35 / 49

[0105] In several modes, a user can select a subset of operating frequencies from among the tool's possible operating frequencies. This can be done, for example, via a dropdown box in the GUI. The selection of frequencies can affect the tool's response at different frequencies, as well as the results of processing algorithms, such as quantitative estimation. By inspecting the results of different frequency combinations, a user can select the ideal frequencies for a future task.

[0106] In several modalities, a quality indicator relative to a simulated tool response can be generated and provided to a user. For example, this quality indicator might be the norm of the differences between ground-firing properties, such as image-generating properties including mud and offset properties, and the corresponding properties provided by the quantitative estimation process. This quality indicator can be used to help users determine the ideal task parameters, including operational parameters and adjustable image-generating properties such as mud properties. In some modalities, a scan of the task parameters can be performed to determine the highest quality task parameters based on the quality indicator. This ideal set of task parameters can be displayed to the user.In turn, a user can choose to implement these task parameters or use them as a starting point to further adjust the parameters based on their preferences.

[0107] In several modalities, base pressure can be correlated with an increase in roughness, as reduced pressure will lead to less contact with the borehole wall. This relationship can be empirically quantified in a test well or in an experimental setup. Then, based on the selected base pressure, the roughness, for example, the offset profile, of the generated random medium can be adjusted. It may be desirable to select the lowest amount of base pressure that provides a given minimum image quality, as higher base pressures can lead to higher adhesion and slip events and greater energy requirements. Petition 870260040778, dated 04 / 30 / 2026, page 43 / 119 36 / 49

[0108] In several modes, the effects of profiling speed can also be visualized using a task planner. While increasing profiling speed may be desirable to reduce the total probe time, it can also lead to a lower signal-to-noise ratio. Thus, the task planner may increase the noise level of the images based on an input profiling speed. Tool resolution can also be negatively affected by increasing profiling speed, as the tool may have contributions from surrounding pixels in the response. This latter effect can be visualized by applying a smoothing filter to the underlying response generated at high resolution.

[0109] In several modalities, measurements from a previous log, such as gauge measurements, can also be used to estimate borehole roughness. This information, along with base pressure and logging speed, can be used to estimate the variation in tool offset. As mentioned above, the prediction of the offset effect can be made based on an empirical model determined from previous field or experimental data, and the base pressure and / or logging speed can be adjusted until an acceptable image quality is obtained.

[0110] In several modalities, a 2D formation profile can be considered with the radial depth of the features ignored. However, features can also vary in the radial direction. The techniques described in this document can be adapted to take into account the variation of features in the radial direction.

[0111] FIGURE 12 illustrates an example of GUI 1200 for controlling the synthesis of a formation and simulating a tool response on the synthesized formation. Region 1202 allows the selection of operational parameters such as operating frequencies, logging speed, and base pressure, as well as other mud and borehole properties such as borehole radius, mud resistivity, and relative mud permittivity. Region 1204 allows the user to add more specific features to the generated random media. Regions 1206, 1208, and 1210 provide functionalities for generating the Petition 870260040778, dated 04 / 30 / 2026, page 44 / 119 37 / 49 formation resistivity, relative formation permittivity, and offset properties, respectively. In this specific implementation, a random media generator can be used. A user can change the minimum and maximum values, the correlation lengths in the depth and azimuthal directions, and the random seed used in the random media generation. Enabling the generation button allows the user to view the random media created for each property. Other features can be accessed through the menu button. For example, the tool version can be selected, and the image generator responses for the selected frequencies can be plotted via the menu. The menu can also include other options, such as the ability to add random noise to the generated images, as well as apply processing algorithms and quantitative estimation.

[0112] FIGURE 13 illustrates an example of a 1300 computing device architecture that can be employed to perform various steps, methods, and techniques disclosed in this document. Specifically, the computing device architecture can be integrated with the electromagnetic imaging tools described in this document. Furthermore, the computing device can be configured to implement the borehole image combination control techniques via machine learning described in this document.

[0113] As noted above, FIGURE 13 illustrates an example of a computing device architecture 1300 of a computing device that can implement the various technologies and techniques described in this document. The components of the computing device architecture 1300 are shown communicating electrically with each other using a connection 1305, such as a bus. The example computing device architecture 1300 includes a processing unit (CPU or processor) 1310 and a computing device connection 1305 that couples various computing device components, including computing device memory 1315, such as read-only memory (ROM) 1320 and random-access memory (RAM) 1325, to the processor 1310. Petition 870260040778, dated 04 / 30 / 2026, page 45 / 119 38 / 49

[0114] The computing device architecture 1300 may include a high-speed memory cache directly connected to, in immediate proximity to, or integrated as part of the processor 1310. The computing device architecture 1300 may copy data from memory 1315 and / or storage device 1330 to the cache 1312 for fast access by the processor 1310. In this way, the cache may provide a performance boost that avoids delays in the processor 1310 while waiting for data. These and other modules may control or be configured to control the processor 1310 to perform various actions. Other memories of the computing device 1315 may also be available for use. The memory 1315 may include several different types of memory with different performance characteristics.The 1310 processor can include any general-purpose processor and a hardware or software service, such as service 1 1332, service 2 1334, and service 3 1336 stored in storage device 1330, configured to control the 1310 processor, as well as a special-purpose processor where software instructions are incorporated into the processor design. The 1310 processor can be a standalone system containing multiple cores or processors, a bus, memory controller, cache, etc. A multi-core processor can be symmetric or asymmetric.

[0115] To enable user interaction with the computing device architecture 1300, an input device 1345 may represent any number of input mechanisms, such as a microphone for speech, a touch screen for gesture or graphic input, keyboard, mouse, motion input, speech, and so forth. An output device 1335 may also be one or more of the various output mechanisms known to those skilled in the art, such as a monitor, projector, television, speaker device, etc. In some cases, multimodal computing devices may allow a user to provide multiple types of input to communicate with the computing device architecture 1300. The communications interface 1340 may, in general, control and manage user input and computing device output. There are no restrictions on operation in a given hardware arrangement and therefore, Petition 870260040778, dated 04 / 30 / 2026, page 46 / 119 39 / 49 The basic features presented here can be easily replaced by improved hardware or firmware arrangements as they are developed.

[0116] The storage device 1330 is non-volatile memory and may be a hard disk or other types of computer-readable media that can store data accessible by a computer, such as magnetic cassettes, flash memory cards, solid-state memory devices, digital versatile disks, cartridges, random-access memories (RAMs) 1325, read-only memory (ROM) 1320, and hybrids thereof. The storage device 1330 may include services 1332, 1334, 1336 for controlling the processor 1310. Other hardware or software modules may be contemplated. The storage device 1330 may be connected to the computing device connection 1305.In one aspect, a hardware module that performs a specific function may include the software component stored on a computer-readable medium in connection with the necessary hardware components, such as the 1310 processor, the 1305 connector, the 1335 output device, and so on, to perform the function.

[0117] For ease of explanation, in some cases, the present technology may be presented as including individual functional blocks, including functional blocks comprising devices, device components, steps or routines in a method embedded in software or combinations of hardware and software.

[0118] In some embodiments, computer-readable storage devices, media and memories may include a cable or wireless signal containing a bit stream and the like. However, when mentioned, computer-readable non-transient storage media expressly exclude media such as energy, carrier signals, electromagnetic waves and signals per se.

[0119] The methods according to the examples described above can be implemented using computer-executable instructions, stored or otherwise available from computer-readable media. Such instructions may include, for example, instructions and data, which cause or otherwise configure a general-purpose computer, special-purpose computer or Petition 870260040778, dated 04 / 30 / 2026, page 47 / 119 40 / 49 a processing device to perform a specific function or group of functions. Portions of the computer resources used can be accessed on a network. Computer-executable instructions can be, for example, binary, instructions in intermediate formats such as assembly language, firmware, source code, etc. Examples of computer-readable media that can be used to store instructions, information used, and / or information created during the methods described include magnetic or optical disks, flash memory, USB devices with non-volatile memory, network storage devices, and so on.

[0120] Devices implementing methods according to these disclosures may include hardware, firmware, and / or software, and may assume various form factors. Typical examples of such form factors include laptops, smartphones, small form factor personal computers, personal digital assistants, rack-mount devices, standalone devices, and so forth. The functionality described herein may also be incorporated into peripherals or add-on boards. This functionality may also be implemented on a circuit board between different chips or different processes running on a single device, by way of further example.

[0121] The instructions, the means for transmitting such instructions, the computing resources for executing them, and other structures for supporting those computing resources are examples of means for providing the functions described in the disclosure.

[0122] In the preceding description, aspects of the application are described with reference to specific embodiments thereof, but those skilled in the art will recognize that the application is not limited to them. Thus, although illustrative embodiments of the application have been described in detail herein, it should be understood that the concepts disclosed may be incorporated and employed in various ways and that the appended claims should be interpreted to include such variations, except where limited by the state of the art. Several features and aspects of the subject described above may be used individually or in combination. Furthermore, the embodiments may be used in any number of environments and applications beyond those described herein. Petition 870260040778, dated 04 / 30 / 2026, page 48 / 119 41 / 49 document, without departing from the broader spirit and scope of the descriptive report. The descriptive report and figures should therefore be considered illustrative and not restrictive. For illustrative purposes, the methods have been described in a specific order. It should be considered that, in other embodiments, the methods may be performed in a different order than that described.

[0123] When components are described as configured to perform certain operations, this configuration can be achieved, for example, by designing electronic circuits or other hardware to perform the operation, by programming programmable electronic circuits (e.g., microprocessors or other suitable electronic circuits) to perform the operation, or any combination thereof.

[0124] The various illustrative logic blocks, modules, circuits, and algorithm steps described in connection with the examples disclosed in this document may be implemented as electronic hardware, computer software, firmware, or combinations thereof. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above in general terms of their functionality. Whether this functionality is implemented as hardware or software depends on the particular application and the design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as a departure from the scope of this application.

[0125] The techniques described in this document can also be implemented in electronic hardware, computer software, firmware, or any combination thereof. Such techniques can be implemented in any of a variety of devices, such as general-purpose computers, wireless communication devices, or multi-purpose integrated circuit devices, including applications in wireless communication devices and other devices. Any features described as modules or components can be implemented together in an integrated logic device or separately as discrete, but interoperable, logic devices. If Petition 870260040778, dated 04 / 30 / 2026, page 49 / 119 42 / 49 implemented in software, the techniques can be performed, at least in part, by a computer-readable data storage medium comprising program code that includes instructions which, when executed, perform one or more of the methods, algorithms and / or operations described above. The computer-readable data storage medium may be part of a computer program product, which may include packaging materials.

[0126] Computer-readable media may include memory or data storage media such as random access memory (RAM), such as synchronous dynamic random access memory (SDRAM), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), FLASH memory, magnetic or optical data storage media and the like. In addition, or alternatively, the techniques may be implemented, at least in part, by a computer-readable communication medium that carries or communicates the program code in the form of instructions or data structures and that can be accessed, read and / or executed by a computer as propagated signals or waves.

[0127] Other forms of dissemination can be practiced in networked computing environments with many types of computer system configurations, including personal computers, portable devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, and the like. These forms can also be practiced in distributed computing environments, where tasks are performed by local and remote processing devices that are connected (by wired links, wireless links, or a combination thereof) through a communications network. In a distributed computing environment, program modules can be located on both local and remote memory storage devices.

[0128] In the description above, terms such as top, up, bottom, down, above, below, bottom of well, well-above, longitudinal, lateral, and the like, as used herein, shall mean in relation to the bottom or the furthest extent of the wellbore. Petition 870260040778, dated 04 / 30 / 2026, page 50 / 119 43 / 49 surrounding, even if the wellbore or portions thereof may be offset or horizontal. Similarly, the transverse, axial, lateral, longitudinal, radial, etc. orientations should mean orientations relative to the orientation of the wellbore or tool. Furthermore, the illustrated embodiments are represented such that the orientation is such that the right side is at the bottom of the well compared to the left side.

[0129] The term coupled is defined as connected, either directly or indirectly, through intervening components, and is not necessarily limited to physical connections. The connection may be made in such a way that the objects are permanently connected or loosely connected. The term outside refers to a region that is beyond the outermost limits of a physical object. The term inside indicates that at least a portion of a region is partially contained within a boundary formed by the object. The term substantially is defined as essentially conforming to the dimension, shape, or other specific word that substantially modifies, so that the component need not be exact. For example, substantially cylindrical means that the object resembles a cylinder, but may have one or more deviations from a true cylinder.

[0130] The term radially means substantially in a direction along a radius of the object, or with a directional component in a direction along a radius of the object, even if the object is not exactly circular or cylindrical. The term axially means substantially along a direction from the axis of the object. If not specified, the term axially refers to the longest axis of the object.

[0131] Although a variety of information has been used to explain aspects within the scope of the appended claims, no limitation of the claims should be implied based on specific features or arrangements, since a person skilled in the art would be able to derive a wide variety of implementations. Furthermore, although some matters may have been described in language specific to structural features and / or method steps, it should be understood that the subject matter defined in the appended claims is not necessarily limited to those described features or acts. Such functionality Petition 870260040778, dated 04 / 30 / 2026, page 51 / 119 44 / 49 may be distributed differently or implemented in components other than those identified in this document. The resources and steps described are disclosed as possible components of systems and methods within the scope of the appended claims.

[0132] Furthermore, claim language that states at least one of a set indicates that one member of the set or several members of the set satisfy the claim. For example, claim language that states at least one of A and B means A, B or A and B.

[0133] The methods of dissemination include:

[0134] Modality 1. Method comprising the generation of a synthetic formation based on one or more image generation properties; the simulation of a response from an image generation tool operating according to one or more operational parameters to generate images of the synthetic formation and generate a response from the synthetic tool; the identification of a change in at least one of the one or more image generation properties and one or more operational parameters; simulating the response of the image generation tool operating according to the change in at least one of the one or more image generation properties and one or more operational parameters to generate a modified synthetic tool response;and reproduce a representation of the response of the modified synthetic tool to show an effect of the change in at least one or more image generation properties and one or more operational parameters on the response of the image generation tool.

[0135] Modality 2. Method, according to embodiment 1, wherein the image generation tool is an oil-based electromagnetic mud image generation tool, a water-based electromagnetic mud image generation tool, an acoustic image generation tool or a density image generation tool.

[0136] Modality 3. Method, according to either of modalities 1 and 2, in which the synthetic formation is generated by a formation model generator that is a random or pseudorandom generator that generates random or pseudorandom variations in one or more generation properties. Petition 870260040778, dated 04 / 30 / 2026, p. 52 / 119 45 / 49 of images and one or more image generation properties comprise formation properties of at least one complex formation resistivity and relative formation permittivity.

[0137] Mode 4. Method, according to any of modes 1 to 3, in which the synthetic formation is generated based on reference log data.

[0138] Mode 5. Method, according to any of modes 1 to 4, in which the synthetic formation is generated based on user input.

[0139] Modality 6. Method, according to any of the modalities 1 to 5, in which the response of the image generation tool is simulated by an advanced model that is executed on demand using a simulation code.

[0140] Modality 7. Method, according to any of the modalities 1 to 6, in which the response of the image generation tool is simulated by an advanced model applied based on previous simulation results for the image generation tool.

[0141] Modality 8. Method, according to any of modalities 1 to 7, in which the response of the image generation tool is simulated by an advanced model applied based on the measured responses for the image generation tool in varying image generation properties and at a variable offset.

[0142] Modality 9. Method, according to any of the modalities from 1 to 8, in which the response of the image generation tool is simulated by an advanced model and the simulation of the tool response to generate the synthetic tool response or the modified synthetic tool response during a simulation additionally includes: identifying a previous simulation result or a measured response of the image generation tool associated with the simulation based on the corresponding image generation properties and the operational parameters used in the simulation generation; and generating the simulation based on the previous simulation result or the measured response of the image generation tool associated with the simulation. Petition 870260040778, dated 04 / 30 / 2026, page 53 / 119 46 / 49

[0143] Modality 10. Method, according to any of the modalities from 1 to 9, in which the response of the image generation tool is simulated by an advanced model and the simulation of the tool response for the synthetic formation or for the modified synthetic formation during a simulation additionally includes the application of multidimensional interpolation to the tool responses from known image generation properties to find the corresponding tool responses in the image generation properties used to generate the synthetic formation for the simulation.

[0144] Modality 11. Method, according to any of modalities 1 to 10, including additionally: identifying one or more additional image generation properties; and simulating the response of the image generation tool based on one or more additional image generation properties to generate the response of the modified synthetic tool.

[0145] Modality 12. Method, according to any of the modalities 1 to 11, in which one or more operational parameters comprise one of the operating frequencies, profiling speed, base pressure, curvature mismatch between the base and the borehole and measurement noise.

[0146] Modality 13. Method, according to any of the modalities 1 to 12, wherein one or more image generation properties comprise formation and borehole properties, wherein the formation properties comprise at least one of the variations of formation resistivity and formation permittivity, the borehole properties comprise mud properties and spacing, and the mud properties further comprise at least one of the variations of mud permittivity, mud resistivity and mud oil-to-water ratio.

[0147] Modality 14. Method, according to any of the modalities 1 to 13, additionally including the provision of functionalities Petition 870260040778, dated 04 / 30 / 2026, p. 54 / 119 47 / 49 to perform image enhancement in one or both the synthetic tool response and the modified synthetic tool response.

[0148] Modality 15. Method, according to any of the modalities 1 to 14, additionally including the provision of functionalities for carrying out quantitative estimates in one or both the synthetic tool response and the modified synthetic tool response.

[0149] Modality 16. Method, according to modality 15, in which quantitative estimation is performed by means of an inversion approach, a machine learning approach or a hybrid machine learning and inversion approach.

[0150] Modality 17. Method, according to modality 15, additionally comprising the comparison of the results of one or more image generation properties obtained from the quantitative estimation with one or more image generation properties used in the generation of one or both the response of the synthetic tool and the response of the synthetic tool modified to quantify an expected performance for one or both the change in one or more image generation parameters and the change in one or more operational parameters.

[0151] Modality 18. Method, according to modality 17, which additionally includes the generation of a quality indicator of one or both the synthetic tool response and the modified synthetic tool response based on a difference between the results of one or more image generation properties obtained from the quantitative estimate with one or more image generation properties of the formation used in the generation of one or both the synthetic tool response and the modified synthetic tool response due to one or both the change in one or more image generation properties and the change in one or more operational parameters.

[0152] Modality 19. Method, according to modality 15, which additionally includes comparing the results of one or more image generation properties obtained from the quantitative estimate with one or more image generation properties used in generating one or both of the synthetic tool response and the modified synthetic tool response, for Petition 870260040778, dated 04 / 30 / 2026, p. 55 / 119 48 / 49 quantify expected performance for a given measurement noise level.

[0153] Modality 20. System comprising: one or more processors; and at least one computer-readable storage medium with instructions stored thereon that, when executed by one or more processors, cause one or more processors to: generate a synthetic formation based on one or more image generation properties; simulate a tool response of an image generation tool operating according to one or more operational parameters to generate images of the synthetic formation and generate a synthetic tool response; identify a change in at least one of one or more image generation properties; simulate the tool response of the image generation tool operating according to the change in at least one of one or more image generation properties to generate a modified synthetic tool response; access actual measurements made by the image generation tool on an actual formation;and compare the actual measurements with simulated measurements included in one or both the synthetic tool response and the modified synthetic tool response to aid in the interpretation of the tool response.

[0154] Modality 21. System comprising: one or more processors; and at least one computer-readable storage medium with instructions stored thereon that, when executed by one or more processors, cause one or more processors to: generate a synthetic formation based on one or more image generation properties; simulate a response of an image generation tool operating according to one or more operational parameters to generate images of the synthetic formation in order to generate a response of the synthetic tool; identify a change in at least one of one or more image generation properties and one or more operational parameters; simulate the response of the image generation tool operating according to the change in at least one of one or more image generation properties and one or more operational parameters to generate a modified synthetic tool response;and reproduce a representation of the response from the modified synthetic tool; Petition 870260040778, dated 04 / 30 / 2026, page 56 / 119 49 / 49 show an effect of changing at least one or more image generation properties and one or more operational parameters on the response of the image generation tool.

[0155] Modality 22. System comprising means to execute a method, as defined in any of the modalities 1 to 19. Petition 870260040778, dated 04 / 30 / 2026, page 57 / 119

Claims

1 / 5 Claims 1. A method, characterized by comprising: generating a synthetic formation based on one or more image generation properties; simulating a tool response of an image generation tool operating according to one or more operational parameters to generate images of the synthetic formation and generating a synthetic tool response; identifying a change in at least one of the one or more image generation properties and one or more operational parameters; simulating the tool response of the image generation tool operating according to the change in at least one of the one or more image generation properties and one or more operational parameters to generate a modified synthetic tool response;and reproduce a representation of the response of the modified synthetic tool to show an effect of the change in at least one or more image generation properties and one or more operational parameters on the response of the image generation tool.

2. Method according to claim 1, characterized in that the imaging tool is an oil-based electromagnetic sludge imaging tool, a water-based electromagnetic sludge imaging tool, an acoustic imaging tool, or a density imaging tool.

3. Method, according to claim 1, characterized in that the synthetic formation is generated by a formation model generator that is a random or pseudorandom generator that generates random or pseudorandom variations in one or more image generation properties and in one or more image generation properties comprising at least one of the formation properties of formation resistivity and complex formation relative permittivity.

4. Method, according to claim 1, characterized by the synthetic formation being generated based on reference log data.

5. Method, according to claim 1, characterized in that the synthetic formation is generated based on user input.

6. A method according to claim 1, characterized in that the response of the image generation tool is simulated by an advanced model that is executed on demand using a simulation code.

7. A method according to claim 1, characterized in that the response of the image generation tool is simulated by an advanced model applied based on previous simulation results for the image generation tool.

8. Method, according to claim 1, characterized in that the response of the image generation tool is simulated by an advanced model applied based on measured responses to the image generation tool at variable formation properties and at a variable offset.

9. A method according to claim 1, characterized in that the response of the image generation tool is simulated by an advanced model and the simulation of the tool response to generate the synthetic tool response or the modified synthetic tool response during a simulation further includes: identifying a previous simulation result or a measured response of the image generation tool associated with the simulation based on the corresponding image generation properties and operational parameters used in the simulation generation; and generating the simulation based on the previous simulation result or the measured response of the image generation tool associated with the simulation.

10. Method, according to claim 1, characterized in that the response of the image generation tool is simulated by an advanced model and the simulation of the tool response for the synthetic formation or for the modified synthetic formation during a simulation further comprises applying multidimensional interpolation to the tool responses from known image generation properties to find corresponding tool responses in image generation properties used to generate the synthetic formation for the simulation.

11. A method according to claim 1, characterized by further comprising: identifying one or more additional image generation properties; and simulating the response of the image generation tool based on one or more additional image generation properties to generate the response of the modified synthetic tool.

12. Method, according to claim 1, characterized by further comprising providing functionalities to perform image generation enhancement on one or both the synthetic tool response and the modified synthetic tool response, providing functionalities to perform quantitative estimates on one or both the synthetic tool response and the modified synthetic tool response, or a combination thereof.

13. Method according to claim 12, characterized by further comprising: comparing the results of one or more image generation properties obtained from quantitative estimation with one or more image generation properties used in the generation of one or both of the synthetic tool response and the modified synthetic tool response to quantify expected performance for one or both of the image generation parameters; and the change in one or more operational parameters.

14. System, characterized by comprising: one or more processors; and at least one computer-readable storage medium with instructions stored thereon that, when executed by one or more processors, cause the one or more processors to: Petition 870260040778, dated 04 / 30 / 2026, p.60 / 119 4 / 5 generate a synthetic formation based on one or more image generation properties; simulate a tool response of an image generation tool operating according to one or more operational parameters to generate images of the synthetic formation and generate a synthetic tool response; identify a change in at least one of one or more image generation properties; simulate the tool response of the image generation tool operating according to the change in at least one of one or more image generation properties to generate a modified synthetic tool response; access actual measurements made by the image generation tool in the image generation of a real formation; and compare the actual measurements with the simulated measurements included in one or both of the synthetic tool response or the modified synthetic tool response to aid in the interpretation of the tool response.

15. System, characterized by comprising: one or more processors; and at least one computer-readable storage medium with instructions stored thereon that, when executed by one or more processors, cause the one or more processors to: generate a synthetic formation based on one or more image generation properties; simulate a response from an image generation tool operating according to one or more operational parameters to generate images of the synthetic formation and generate a response from the synthetic tool; identify a change in at least one of the one or more image generation properties and one or more operational parameters; simulate the response from the image generation tool operating according to the change in at least one of the one or more operational parameters. Petition 870260040778, dated 04 / 30 / 2026, page 1.61 / 119 5 / 5 more image generation properties and one or more operational parameters to generate a response from the modified synthetic tool; and reproduce a representation of the response from the modified synthetic tool to show an effect of the change in at least one of the image generation properties and one or more operational parameters on the response of the image generation tool. Petition 870260040778, dated 04 / 30 / 2026, p. 62 / 119.

Images