Data-driven optimization for rock physics modeling assisted by machine learning

Abstract

The disclosed methods include: generating a geological model; sampling captured geological data to generate sampled data; evaluating, using an objective function, the sampled data to determine a parameter range for the geological model; deploying, based on the parameter range, a machine learning unsupervised clustering of datapoints comprised in the sampled data to generate seeds data; and ranking, based on the seeds data, two or more rock physics parameters of the geological model. The method further comprises: stochastically optimizing the geological model based on the seeds data and the determined parameter range to generate model performance data for the geological model; calibrating, based on the model performance data, the two or more parameters of the geological model to generate a calibrated geological model; and generating, based on the calibrated geological model, a multi-dimensional report indicating elastic property predictions for each lithology comprised in a reservoir associated with the resource site.

Description

DATA-DRIVEN OPTIMIZATION FOR ROCK PHYSICS MODELING ASSISTEDBY MACHINE LEARNINGCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of Malaysian Patent Application No.PI2024001424 entitled “Data-Driven Optimization for Rock Physics Modeling Assisted by Machine Learning,” filed March 6, 2024, the disclosure of which is incorporated herein by reference in its entirety.INTRODUCTION

[0002] This disclosure is directed to a technique for calibrating and / or using rock physics models.BACKGROUND

[0003] In order to substantially and accurately characterize reservoirs for development operations at a resource site, it is vital to analyze geological structures using, for example, rock physics. Rock physics is a field of study directed to understanding the physical properties of rocks including elastic rock properties. Elastic rock properties may be a function of pore space data, fluid data, mineral grains data, texture data, and microstructure data associated with rocks at a given resource site. Since rock physics is a multidisciplinary field that integrates geology, petrophysics, geophysics, and geological engineering, rock physics may provide valuable cross- disciplinary insights for geological analysis.SUMMARY

[0004] Disclosed are methods, systems, and computer program products that generate rock physics data for a resource site. According to an embodiment, a method for generating rock physics data comprises: generating a geological model comprising two or more rock physics parameters; sampling captured geological data associated with the resource site to generate sampled data; evaluating, using at least one objective function, the sampled data to determine a parameter range associated with the two or more rock physics parameters; deploying, based on the parameter range, a machine learning unsupervised clustering of datapoints comprised in the sampled data to generate seeds data for the geological model; and ranking, based on the seeds data, the two or more rock physics parameters to prioritize a firstparameter comprised in the two or more rock physics parameters over a second parameter comprised in the two or more rock physics parameters and thereby generate a ranked parameter list for the geological model. In response to applying the seeds data to the two or more rock physics parameters based on the ranked parameter list for the geological model, the method further comprises: stochastically optimizing the geological model based on the seeds data and the determined parameter range to generate model performance data for the geological model; calibrating, based on the model performance data, the two or more parameters of the geological model to generate a calibrated geological model; and generating, based on the calibrated geological model, a multi-dimensional report indicating at least elastic property predictions for each lithology comprised in a reservoir associated with the resource site.

[0005] In other embodiments, a system and a computer program can include or execute the method described above. These and other implementations may each optionally include one or more of the following features.

[0006] The two or more parameters can comprise at least two of: a bounding average method parameter; a Constant Cement parameter; a Differential Effective Medium parameter; and one or more statistical parameters indicating metric determinations derived from the two or more rock physics parameters excluding the one or more statistical parameters.

[0007] In some embodiments, the statistical parameters comprise at least one of: average data indicating R2coefficient determinations associated with Bulk or Shear moduli for measured data versus model performance data; and residual data comprising mean or standard deviation indicators associated with the sampled data.

[0008] Furthermore, the sampling comprises executing numerical computations on the captured geological data to extract the sampled data.

[0009] In addition, the resource site can comprise one or more well locations or one or more reservoir locations.

[0010] According to some embodiments, the geological model is a rock physics model.

[0011] Moreover, sampling the captured geological data associated with the resource site can comprise applying uncertainty sampling to the captured geological data using a quasirandom process with low-discrepancy sequence values or low-discrepancy sequence values scaled to real values.

[0012] In some cases, evaluating, using the at least one objective function, the sampled data can comprise eliminating parameter sets comprised in the captured geological data or comprised in the sampled data that yield an increase in data points outside of Hashin-Shtrikman bounds.

[0013] Furthermore, the captured geological data can comprises one or more of: density data associated with a geological structure at the resource site; porosity data associated with the geological structure at the resource site; pressure data associated with the geological structure at the resource site; water saturation data associated with the geological structure at the resource site; hydrocarbon saturation data associated with the geological structure at the resource site; and lithology data associated with the geological structure at the resource site.

[0014] In some implementations, the captured geological data comprises one or more of well log data or core data captured by a logging tool at the resource site.

[0015] According to some embodiments, the elastic property predictions comprise data relationships between: depth values associated with the reservoir; and elastic property values associated with the reservoir.

[0016] Furthermore, the report may be generated on a graphical user interface by an application (e. ., a web application).

[0017] In some cases, the report is applied in at least one of: seismic wave inversion operations for / at the resource site; or reservoir characterizations for / at the resource site.

[0018] In some embodiments, the report is used for at least one of: well placement operations at the resource site; equipment placement operations at the resource site; and surgically locating a subsurface resource at the resource site.

[0019] In addition, the objective function can relate one or more of Bulk or Shear moduli data for the captured geological data to one or more geological properties associated with subsurface structures associated with the resource site.

[0020] In some implementations, a weight variable (m) controls a dependence of the at least one objective function on one or more of: a Bulk modulus characterization of a subterranean structure at the resource site; or a Shear modulus characterization of the subterranean structure at the resource site.BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The disclosure is illustrated by way of example, and not by way of limitation in the figures of the accompanying drawings in which like reference numerals are used to refer to similar elements. It is emphasized that various features may not be drawn to scale and the dimensions of various features may be arbitrarily increased or reduced for clarity of discussion.

[0022] FIGURE 1A shows an exemplary workflow for rock physics modeling at a resource site.

[0023] FIGURE IB shows an exemplary state space workflow for a stochastic hill climbing process.

[0024] FIGURE 2 depicts a cross-sectional view of a resource site for which the process of FIGURE 4 may be executed.

[0025] FIGURE 3 depicts a networked system illustrating a communicative coupling of devices or systems associated with the resource site of FIGURE 2.

[0026] FIGURE 4A shows an exemplary workflow for a data-driven optimization process associated with rock physics modeling.

[0027] FIGURE 4B provides an exemplary detailed workflow for methods, systems, and computer programs that generate rock physics data for a resource site.

[0028] FIGURES 5A and 5B show visualizations indicating plots associated with Bulk and Shear moduli associated with a resource site.

[0029] FIGURE 6 shows a visual analysis of the behavior of multiple objective functions for varying parameter values to provide indications of conflicting and nonconflicting objectives.DETAILED DESCRIPTION

[0030] Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings and figures. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the disclosed subject-matter. However, it will be apparent to one of ordinary skill in the art that the solutions disclosed may be practiced without these specific details. In other instances, well- known methods, procedures, components, circuits, and networks have not been described in detail so as not to unnecessarily obscure aspects of the embodiments.

[0031] The disclosed systems and methods may be accomplished using interconnected devices and systems that obtain a plurality of data associated with various parameters of interest at a resource site. The workfl ows / flowcharts described in this disclosure, according to some embodiments, implicate a new processing approach (e.g., hardware, special purpose processors, and specially programmed general-purpose processors) because such analyses are too complex and cannot be done by a person in the time available or at all. Thus, the described systems and methods are directed to tangible implementations or solutions to specific technological problems in developing natural resources such as oil, gas, water well industries, and other mineral exploration operations. More specifically, the systems and methods presently disclosed may be applicable to operations associated with stratigraphic analysis associated with a resource site.

[0032] Attention is now directed to methods, techniques, infrastructure, and workflows for operations that may be carried out at a resource site. Some operations in the processing procedures, methods, techniques, and workflows disclosed herein may be combined while the order of some operations may be changed. Some embodiments include an iterative refinement of one or more data models associated with the resource site via feedback loops executed by one or more computing device processors and / or through other control devices / mechanisms that make determinations regarding whether a given action, template, or resource data, etc., is sufficiently accurate.Overview

[0033] FIGURE 1A shows an exemplary workflow for rock physics modeling at a resource site. In particular, this figure depicts the use of conditioned well logs 102 from which is extracted rock matrix data 104 and fluid data 106 which may be subsequently combined to generate outputs from which can be determined dry rock and brine data 108. The rock and brine data 108 can also facilitate generation of saturated rock data 110 as well as lithology data 112a and / or bounding data 112b. In one embodiment, the lithology data may be used to generate Bulk and Shear moduli information 114 as further discussed below.

[0034] It is appreciated that rock physics modeling at a resource site (e.g., well locations, reservoir locations), requires input from conditioned or unconditioned well logs including gamma ray (GR) data, density data, sonic data, neutron porosity data, and resistivity logs data.One of the assumptions applied to rock physics modeling is that the modeling is computed at 100% brine saturation, so that fluid substitution using, for example, Gassmann techniques, may be performed before calibrating a rock physics model. Calibration of rock physics models may be done on a lithology basis and / or by applying similar or different depositional environmental structures that have their own corresponding models. In particular, each model for similar or different depositional environmental structures can have its own set of input parameters which may each be associated with as bulk modulus (K) data, shear modulus (p) data, critical porosity data, pore share data, and angularity data.

[0035] Furthermore, one of the relevant objectives of accurately calibrating and / or configuring models associated with geological structures is to find an optimal combination of model parameters that enhance robust estimation of elastic rock property data including rock rigidity data, rock incompressibility data, rock density data, rock compressional data, and shear wave velocity data associated with propagated waves through a subsurface rock structure.

[0036] The disclosed approach automatically provides a diverse yet reliable set of calibrated rock physics models for a resource site to improve reservoir modeling and / or streamline the decision-making process associated with energy development. According to one embodiment, the disclosed workflows can evaluate candidate models by using a statistical and / or a physics-based validation technique. For example, the statistical technique can involve: thoroughly sampling one or more scenarios across a defined parameter space; conducting value estimations on the sampled one or more scenarios to generate a qualitative or quantitative value set; optimizing the qualitative or quantitative value set using one or more objective functions that applying averaging (e.g., weighted averaging) computations on the qualitative or quantitative value set based on determined coefficient data (e.g., R2data) associated with one or more calculated moduli. In addition, the physics-based validation techniques may be implemented by constraining generated models to be within, for example, a defined bound (e.g. , Hashin-Shtrikman bounds) that limit the range of possible elastic properties of rock based on mineral and / or fluid components.

[0037] FIGURE IB shows an exemplary state space workflow for a stochastic hill climbing process which may be applied to model optimizations, according to some embodiments. At block 120, a determined solution (e.g., input datasets) may be selected following which said solution is evaluated at block 122. Moving on to block 124, a first newsolution (e.g., new input datasets) close to a data neighborhood of the selected solution is selected and evaluated or otherwise tested on a geological model at block 126 and if (see decision block 128) the first new solution provides optimal results relative to the determined solution from block 120, the first new solution is feedback at block 130 to block 124 where the first new solution is further tested or validated. However, if the first new solution does not provide optimal results relative to the determined solution from block 120, a second new solution within the neighborhood of the determined solution may be selected for further evaluation or testing on the geological model. This process beneficially features in the disclosed optimizations as further discussed below.Resource Site

[0038] FIGURE 2 shows a cross-sectional view of a resource site 200 for which the process of FIGURE 1 may be executed. While the illustrated resource site 200 represents a subterranean formation, the resource site, according to some embodiments, may be below water bodies such as oceans, seas, lakes, ponds, wetlands, rivers, etc.

[0039] According to one embodiment, various measurement tools capable of sensing one or more resource site data such as seismic two-way travel time, density, resistivity, production rate, etc., of a subterranean formation and / or geological formations may be provided at the resource site. As an example, wireline tools may be used to obtain measurement information related to geological attributes (c'.g, geological attributes of a wellbore and / or reservoir) including geophysical and / or chemical information. For example, the chemical information may include chemical information associated with the subsurface and / or chemical information associated with the surface / above ground areas of the resource site 200.

[0040] In some embodiments, various sensors may be located at various locations around the resource site 200 to monitor and collect data for executing the process of FIGURES 4A and 4B. In other embodiments, the techniques disclosed herein may be applied to surface seismic monitoring applications, surface gravity applications, surface electromagnetic applications, surface ground heave applications, and surface measurement of induced seismicity applications. According to some implementations, the disclosed techniques may be applied to remote sensing applications, subsea applications associated with permanent sensors, temporary sensor applications, applications associated with remotely operated vehicles, andapplications associated with aerial -based measurements (e.g., performed from planes, helicopters, and / or drones). Such measurements may include Synthetic Aperture Radar data, atmospheric concentration data associated with molecules such as CO2, CH4, and / or gas concentration data associated with gases within the seabed.

[0041] Part, or all, of the resource site 200 may be on land, on water, or below water. In addition, while a resource site 200 is depicted, the technology described herein may be used with any combination of one or more resource sites (e.g. , multiple oil fields or multiple wellsites, one or more saline aquifers, one or more depleted oil / gas fields, etc.), one or more processing facilities, etc. As can be seen in FIGURE 2, the resource site 200 may have data acquisition tools 202a, 202b, 202c, and 202d positioned at various locations within the resource site 200. The subterranean structure 204 may have a plurality of geological formations 206a-206d. As shown, this structure may have several formations or layers, including a shale layer 206a, a carbonate layer 206b, a shale layer 206c, and a sand layer 206d. A fault 207 may extend through the shale layer 206a and the carbonate layer 206b. The data acquisition tools, for example, may be adapted to take measurements and detect geophysical and / or chemical characteristics of the various formations shown.

[0042] While a specific subterranean formation with specific geological structures is depicted, it is appreciated that the resource site 200 may contain a variety of geological structures and / or formations, sometimes having extreme complexity. In some locations of a given geological structure, for example below a water line (e.g., aquifer) relative to the given geological structure, fluid may occupy pore spaces of the formations. Each of the measurement devices may be used to measure properties of the formations and / or other geological features. While each data acquisition tool is shown as being in specific locations in FIGURE 2, it is appreciated that one or more types of measurement may be taken at one or more locations across one or more sources of the resource site 200 or other locations for comparison and / or analysis.

[0043] The data collected from various sources at the resource site 200 may be processed and / or evaluated and / or used as training data, and or used to generate high resolution result sets for characterizing a resource at the resource site, and / or used for generating resource models, etc. In one embodiment, the data collected by a set of sensors at the resource site may include data associated with the number of wells of a first reservoir or second reservoir at the resource site, data associated with the number of grid cells of the first or second reservoir, dataassociated with the average permeability of the first or second reservoir, data associated with the production duration history (e.g., number of years of production) of the first reservoir or second, etc.

[0044] Data acquisition tool 202a is illustrated as a measurement truck, which may comprise devices or sensors that take measurements of the subsurface through sound vibrations such as, but not limited to, seismic measurements. Drilling tool 202b may include a downhole sensor adapted to perform logging while drilling (LWD) data collection. The wireline tool 202c may include a downhole sensor deployed in a wellbore or borehole. Production tool 202d may be deployed from a production unit or Christmas tree into a completed wellbore. Examples of resource site data that may be measured include weight on bit, torque on bit, subterranean pressures (e.g., underground fluid pressure), temperatures, flow rates, compositions, rotary speed, particle count, voltages, currents, and / or other parameters of operations as further discussed below.

[0045] Sensors may be positioned about the resource site to collect data relating to various resource site operations, such as sensors deployed by the data acquisition tools 202. The sensor may include any type of sensor such as a metrology sensor (e.g., temperature, humidity), an automation enabling sensor, an operational sensor (e.g., pressure sensor, EES sensor, thermometer, depth, tension), evaluation sensors, that can be used for acquiring data regarding the formation, wellbore, formation fluid / gas, wellbore fluid, gas / oil / water comprised in the formation / wellbore fluid, or any other suitable sensor. For example, the sensors may include accelerometers, flow rate sensors, pressure transducers, electromagnetic sensors, acoustic sensors, temperature sensors, chemical agent detection sensors, nuclear sensor, and / or any additional suitable sensors.

[0046] In one embodiment, the data captured by the one or sensors may be used to characterize, or otherwise generate one or more parameter values for a high-resolution result set used to, for example, label or configure a machine learning (ML) engine, a resource model as the case may require. In other embodiments, test data or synthetic data may also be used in developing the ML engine or resource model via one or more parameterization / labeling operations such as those discussed in association with the workflows presented herein.

[0047] Evaluation sensors may be featured in downhole tools such as tools 202b-202d and may include for instance electromagnetic, acoustic, nuclear, and optic sensors. Examplesof tools including evaluation sensors that can be used in the framework of the current method include electromagnetic tools including imaging sensors such as FMI™ or QuantaGeo™ (mark of SLB, Houston, TX); induction sensors such as Rt Scanner™ (mark of SLB, Houston, TX), multifrequency dielectric dispersion sensor such as Dielectric Scanner™ (mark of SLB, Houston, TX); acoustic tools including sonic sensors, such as Sonic Scanner™ (mark of SLB, Houston, TX) or ultrasonic sensors, such as pulse-echo sensor as in UBI™ or PowerEcho™ (marks of SLB, Houston, TX) or flexural sensors PowerFlex™ (mark of SLB, Houston, TX); nuclear sensors such as Litho Scanner™ (mark of SLB, Houston, TX) or nuclear magnetic resonance sensors; fluid sampling tools including fluid analysis sensors such as InSitu Fluid Analyzer ™ (mark of SLB, Houston, TX); distributed sensors including fiber optic. Such evaluation sensors may be used in particular for evaluating the formation in which the well is formed (z.e., determining petrophysical or geological properties of the formation), for verifying the integrity of the well (such as casing or cement properties) and / or analyzing the produced fluid (flow, type of fluid, etc.).

[0048] As shown, data acquisition tools 202a-202d may generate data plots or measurements 208a-208d, respectively. These data plots are depicted within the resource site 200 to demonstrate that data generated by some of the operations executed at the resource site 200.

[0049] Data plots 208a-208c are examples of static data plots that may be generated by data acquisition tools 202a-202c, respectively. However, it is herein contemplated that data plots 208a-208c may also be data plots that may be generated and updated in real time. These measurements may be analyzed to better define properties of the formation(s) and / or determine the accuracy of the measurements and / or check for and compensate for measurement errors. The plots of each of the respective measurements may be aligned and / or scaled for comparison and verification purposes. In some embodiments, base data associated with the plots may be incorporated into site planning, modeling a test at the resource site 200. The respective measurements that can be taken may be any of the above.

[0050] Other data may also be collected, such as historical data of the resource site 200 and / or sites similar to the resource site 200, user inputs, information (e.g. , economic information) associated with the resource site 200 and / or sites similar to the resource site 200, and / or othermeasurement data and other parameters of interest. Similar measurements may also be used to measure changes in formation aspects over time.

[0051] Computer facilities such as those discussed in association with FIGURE 3 may be positioned at various locations about the resource site 200 (e.g., a surface unit) and / or at remote locations. A surface unit (e.g., one or more terminals 320) may be used to communicate with the onsite tools and / or offsite operations, as well as with other surface or downhole sensors. The surface unit may be capable of sending commands to the oil field equipment / systems, and receiving data therefrom. The surface unit may also collect data generated during production operations and can produce output data, which may be stored or transmitted for further processing.

[0052] The data collected by sensors may be used alone or in combination with other data. The data may be collected in one or more databases and / or transmitted on or offsite. The data may be historical data, real-time data, or combinations thereof. The real-time data may be used in real time, or stored for later use. The data may also be combined with historical data or other inputs for further analysis or for modeling purposes to optimize production processes at the resource site 200. In one embodiment, the data is stored in separate databases, or combined into a single database.High-Level Networked System

[0053] FIGURE 3 shows a high-level networked system diagram illustrating a communicative coupling of devices or systems associated with the resource site 200 as described in FIGURE 2. The system shown in the figure may include a set of processors 302a, 302b, and 302c for executing one or more processes discussed herein. The set of processors 302 may be electrically coupled to one or more servers (e.g., computing systems) including memory 306a, 306b, and 306c that may store for example, program data, databases, and other forms of data. Each server of the one or more servers may also include one or more communication devices 308a, 308b, and 308c. The set of servers may provide a cloudcomputing platform 310. In one embodiment, the set of servers includes different computing devices that are situated in different locations and may be scalable based on the needs and workflows associated with the resource site 200. The communication devices of each server may enable the servers to communicate with each other through a local or global network suchas an Internet network. In some embodiments, the servers may be arranged as a town 312, which may provide a private or local cloud service for users. A town may be advantageous in remote locations with poor connectivity. Additionally, a town may be beneficial in scenarios with large networks where security may be of concern. A town in such large network embodiments can facilitate implementation of a private network within such large networks. The town may interface with other towns or a larger cloud network, which may also communicate over public communication links. Note that cloud-computing platform 310 may include a private network and / or portions of public networks. In some cases, a cloud-computing platform 310 may include remote storage and / or other application processing capabilities.

[0054] The system of FIGURE 3 may also include one or more user terminals 314a and 314b each including at least a processor to execute programs, a memory (e.g., 316a and 316b) for storing data, a communication device and one or more user interfaces and devices that enable the user to receive, view, and transmit information. In one embodiment, the user terminals 314a and 314b is a computing system having interfaces and devices including keyboards, touchscreens, display screens, speakers, microphones, a mouse, styluses, etc. The user terminals 314 may be communicatively coupled to the one or more servers of the cloudcomputing platform 310. The user terminals 314 may be client terminals or expert terminals, enabling collaboration between clients and experts through the system of FIGURE 3.

[0055] The system of FIGURE 3 may also include at least one or more resource sites200 having, for example, a set of terminals 320, each including at least a processor, a memory, and a communication device for communicating with other devices communicatively coupled to the cloud-computing platform 310. The resource site 200 may also have a set of sensors (e.g., one or more sensors described in association with FIGURE 2) or sensor interfaces 322a and 322b communicatively coupled to the set of terminals 320 and / or directly coupled to the cloudcomputing platform 310. In some embodiments, data collected by the set of sensors / sensor interfaces 322a and 322b may be processed to generate a one or more resource models (e.g., reservoir models) or one or more resolved data sets used to generate the resource model which may be displayed on a user interface associated with the set of terminals 320, and / or displayed on user interfaces associated with the set of servers of the cloud computing platform 310, and / or displayed on user interfaces of the user terminals 314. Furthermore, various equipment / devices discussed in association with the resource site 200 may also be communicatively coupled to theset of terminals 320 and or communicatively coupled directly to the cloud-computing platform 310. The equipment and sensors may also include one or more communication device(s) that may communicate with the set of terminals 320 to receive orders / instructions locally and / or remotely from the resource site 200 and also send statuses / updates to other terminals such as the user terminals 314.

[0056] The system of FIGURE 3 may also include one or more client servers 324 including a processor, memory, and communication device. For communication purposes, the client servers 324 may be communicatively coupled to the cloud-computing platform 310, and / or to the user terminals 314a and 314b, and / or to the set of terminals 320 at the resource site 200 and / or to sensors at the oil field, and / or to other equipment at the resource site 200.

[0057] A processor, as discussed with reference to the system of FIGURE 3, may include a microprocessor, a graphical processing unit (GPU), a microcontroller, a processor module or subsystem, a programmable integrated circuit, a programmable gate array, or another control or computing device.

[0058] The memory / storage media discussed above in association with FIGURE 3 can be implemented as one or more computer-readable or machine-readable storage media that are non-transitory. In some embodiments, storage media may be distributed within and / or across multiple internal and / or external enclosures of a computing system and / or additional computing systems. Storage media may include one or more different forms of memory including semiconductor memory devices such as dynamic or static random access memories (DRAMs or SRAMs), erasable and programmable read-only memories (EPROMs), electrically erasable and programmable read-only memories (EEPROMs) and flash memories; magnetic disks such as fixed, floppy and removable disks; other magnetic media including tape; optical media such as compact disks (CDs) or digital video disks (DVDs), BluRays or any other type of optical media; or other types of storage devices. “Non-transitory” computer readable medium refers to the medium itself (i.e., tangible, not a signal) and not data storage persistency (e.g, RAM vs. ROM).

[0059] Note that instructions can be provided on one computer-readable or machine- readable storage medium, or alternatively, can be provided on multiple computer-readable or machine-readable storage media distributed in a large system having possibly plural nodes and / or non-transitory storage means. Such computer-readable or machine-readable storagemedium or media is (are) considered to be part of an article (or article of manufacture). The storage medium or media can be located either in a computer system running the machine- readable instructions, or located at a remote site from which machine-readable instructions can be downloaded over a network for execution.

[0060] It is appreciated that the described system of FIGURE 3 is an example that may have more or fewer components than shown, may combine additional components, and / or may have a different configuration or arrangement of the components. The various components shown may be implemented in hardware, software, or a combination of both, hardware, and software, including one or more data processing and / or application specific integrated circuits.

[0061] Further, the steps in the flowcharts described below may be implemented by running one or more functional modules in an information processing apparatus such as general-purpose processors or application specific chips, such as ASICs, FPGAs, PLDs, GPUs or other appropriate devices associated with the system of FIGURE 3. For example, the flowchart of FIGURE 1 as well as the flowcharts below may be executed using a data engine / a data processing module (e.g., computing module) stored in memory 306a, 306b, or 306c such that the data engine / data processing module includes instructions that are executed by the one or more processors such as processors 302a, 302b, or 302c as the case may be. The various modules of FIGURE 3, combinations of these modules, and / or their combination with general hardware are included within the scope of protection of the disclosure. While one or more computing processors (e.g., processors 302a, 302b, or 302c) may be described as executing steps associated with one or more of the flowcharts described in this disclosure, the one or more computing device processors may be associated with the cloud-based computing platform 310 and may be located at one location or distributed across multiple locations. In one embodiment, the one or more computing device processors may also be associated with other systems of FIGURE 3 other than the cloud-computing platform 310.

[0062] In some embodiments, a computing system is provided that includes at least one processor, at least one memory, and one or more programs stored in the at least one memory, such that the programs comprise instructions, which when executed by the at least one processor, are configured to perform any method disclosed herein.

[0063] In some embodiments, a computer readable storage medium is provided, which has stored therein one or more programs, the one or more programs including instructions,which when executed by a processor, cause the processor to perform any method disclosed herein. In some embodiments, a computing system is provided that includes at least one processor, at least one memory, and one or more programs stored in the at least one memory for performing any method disclosed herein. In some embodiments, an information processing apparatus for use in a computing system is provided for performing any method disclosed herein.Embodiments

[0064] The disclosed solution applies a data-driven optimization workflow assisted by machine learning to facilitate robust and efficient rock physics modeling of a subsurface associated with a resource site. Integration of sensitivity analysis (e.g., low-discrepancy sequence sampling, parameter influence ranking, etc.), and machine learning techniques (e.g., unsupervised K means clustering, etc.), and derivative-free local optimizations (e.g., Nelder Mead (NM) optimization techniques, Stochastic Hill Climbing (SHC) optimization techniques) to model, configure, or characterize input parameters (e.g. geological model parameters or physics-based parameters) of a geological model (e.g., rock physics model). By leveraging prior information from for example, data from a resource site (e.g., well log data), optimal results with better confidence interval data and faster model convergence data (e.g., data generated by a geological model arriving at a steady state based on simulations or testing) may be generated.

[0065] According to one embodiment, the disclosed approach addresses subsurface modeling issues by:• Optimizing one or more workflows that combines machine learning with physics-based processes to develop a robust and efficient rock physics modeling (e.g., rock physics model calibration) solution based on a set of scenarios or cases or a combination of scenarios and cases with diverse model parameters to developed rock physics models; and• generating a user-centric application or data processing engine or data processing logic deployed within a geological modeling tool (e.g., rock physics model calibration tool) that provides comprehensive multi-dimensional visualizations that trace every step of the automated workflow and / or machine learning workflow and thereby enabling accurate insight data associated with a subsurface of a resource site.

[0066] The disclosed technique automates rock physics modeling by executing:• global sensitivity analysis operations to identify areas of interest in a multi-dimensional parameter space associated with one or more geological models with a set of initial value datapoints; and• follow-up focused optimization operations to further improve the offered objective function.

[0067] According to one embodiment, each geological model (e.g. , rock physics model) has a plurality of parameters (e.g., at least 5 parameters or at least 8 parameters or at least 10 parameters) such that each of the plurality of parameters have data values corresponding to actual sensor values that are realizable at the resource site. Furthermore, one of the objectives of the disclosed techniques is to determine data values for the plurality of parameters of the geological model within specific value ranges that are representative of resource site data and thereby minimize data mismatches between the geological model data and the resource site data. As such, the disclosed processes test various combinations of the plurality of geological parameters thereby making each test instance a search space comprised in the multidimensional space representative of all the various test combinations.

[0068] In some embodiments, the global sensitivity analysis operations comprise executing an uncertainty sampling process to capture geological data using a quasi-random process with low-discrepancy sequences (e.g., a Sobol sequence with base 2) and thereby generate sampled data associated with uncertainty datapoints corresponding to one or more rock physics model parameters. Following this the sampled data is scaled with values from the Real number space to generate scaled sampled data associated with the parameters of the geological model. The scaled sampled data is subjected to, or otherwise undergo processing by one or more objective functions (e.g., an average of R2for bulk and shear moduli objective function, an R2of Bulk modulus objective function, R2of Shear modulus objective function) to determine optimal parameter ranges for the parameters associated with the geological model. According to some embodiments, this is achieved by filtering out parts of the parameter space that yield results below a specified threshold value (e.g., an R2= 0). For example, the parameters may be ranked to generate a parameter list comprising a ranking of the parameters of the geological model as further discussed below in association with FIGURES 4A and 4B. In particular, a parameter ranking process, also known as factor prioritization, may be performed to prioritize parameters (e.g., input parameters) of the geological model (e.g., rock physics model) based on parameter influence on the objective function to enhance model tuning. It is appreciated thatthe use of dedicated sampling during the disclosed process beneficially facilitates the generation of stable and / or accurate rock physics models according to some embodiments.

[0069] Once the data sampling and / or data pre-conditioning with R2and / or imposing, for example, bounding constraints (e. ., Hashin-Shtrikman bounds) on the sampled data, a machine learning unsupervised clustering operation, with for example, at least 2 data clusters comprised in the sampled data, or at least 3 data clusters comprised in the sampled data, or at least 4 data clusters comprised in the sampled data, or at least 5 data clusters comprised in the sampled data, to select data starting points or "seeds data," which serve as model starting points or initial model values to guide the disclosed optimization process. In one embodiment, optimal seeds data and defined constraints for local optimization ensure that the disclosed process can escape or otherwise cross a local optima value. In particular, testing the geological model (e.g., rock physics model) via, for example, one or more simulations generates model response data or model performance data that may have a plurality of peak values or maximum values such that a peak value for a given value neighborhood comprised in the response data is designated as the local optima value. According to one embodiment, the selected local optima is distinct from a global optima value which may be reached during globally testing the geological model. In some cases, optimal seeds data and defined constraints for global optimization of the geological model can ensure that the disclosed process can escape or cross the global maxima value. Thus, the disclosed solution introduces an innovative way to automate starting point or seed data selection and range definition for model parameters by leveraging global sensitivity analysis techniques and machine learning clustering methods.

[0070] In some embodiments, the disclosed workflow comprises applying optimization routines to fine-tune parameter combinations generated by the sensitivity analysis techniques. At this stage outlier data (e.g., data points out of established bounds such as the Hashin- Shtrikman bounds) may be removed during the model parameter calibration with an R2cost function associated with an L2 norm that is sensitive to outlier data. In one embodiment, the cost function is used to mitigate (e.g., minimize) against data mismatches associated with one or more parameters of the geological model (e.g., rock physics model). For example, the cost function comprises a weighted average of R-square (e.g., coefficients of determination) for bulk and shear moduli. Following this a stochastic approach to local optimization based on the Stochastic Hill Climbing process (see FIGURE IB) may be used to improve the parameterizedmodel using random perturbations of the seed data or starting point values associated with the parameterized models under consideration.

[0071] According to some embodiments, the seeds data forms the basis values for initializing the parameterized model. Following configuring the parameterized model based on the seeds data, new data points are generated within a step size derived from scaled parameter values of the parameter bounds defined from the sensitivity analysis. In some embodiments, the new data points are evaluated to determine performance data for each previous parameter data point and if the new data points indicate better performance relative to the previous parameter data points, the new data points are used to configure the parameter values of the geological model. These aspects are further indicated in FIGURE IB.

[0072] The generation of new data points, according to some embodiments, rely on random data generated using a Stochastic Hill Climbing process, with the aim of skipping over bumpy datapoints, or noisy datapoints, or discontinuous datapoints, or deceptive datapoints associated with geological regions of a response surface comprised in captured sensor data at the resource site. In some cases, the disclosed process is iterated for about 500 times or 800 times or at least 1000 times for other seed data points selected from the unsupervised clustering operation. According to some embodiments, the multi-iterations process is used to improve the seed data and thereby help mitigate against the risk of getting stuck at a local optima, which can be a challenge for geological optimizer tools.

[0073] During the disclosed optimization process, computation effectiveness may be improved by imposing a heuristic early stopping criteria on the data being processed by a specified time duration (e.g., about 10%, about 20%, or about 30%, or about 40%, or about at least 50% of the number of iterations) that describes the number of epochs or periods indicating improvement of model performance and thereby reduce unnecessary computations. In some embodiments, the seed data is constrained to perturbed starting points by ensuring that the seed data are within physical boundaries corresponding to geological structures (e.g., rock physics bounds) with a positive R2score. This ensures the physical integrity of optimal solutions associated with model parameter value initialization while making use of randomness as part of the search process for non-linear response surfaces associated with the subsurface of the resource site.

[0074] Thus, the combination of the disclosed workflows enables a unified approach, sensitivity analysis-guided optimization, to detect multiple realizable models with performant statistical metrics for every lithology type provided for a given resource site.

[0075] It is appreciated that the disclosed techniques beneficially include interfaces(e.g., graphical user interfaces or web application interfaces) that are generated in association with one or more disclosed workflows such that the interfaces can effectively present comprehensive multi-dimensional (e.g., 2-dimensional, 2.5 dimensional, or 3 -dimensional) including image and / or textual visualizations to facilitate rock physics operations for a given resource site. Furthermore, the disclosed solution beneficially allows interactively reviewing computational model results by a plurality of energy or geological domains including a lithology domain, rock physics domain, etc. In addition, the disclosed methods and systems reduce model generation times and / or model utilization times to beneficially generate geological models (e.g., rock physics model) with attendant values required for timely execution of energy development and / or other development operations associated with a resource site.

[0076] According to some embodiments, the disclosed methods, systems, and computer program products are applied to non-pressure-dependent clastic depositional environments. Furthermore, the disclosed approach may be seamlessly extended to other depositional environments, such as carbonate reservoirs, and pressure-dependent clastic reservoirs. The flexibility of the disclosed solution also enables integration with a plurality of geological modeling tools.

[0077] In addition, insights from the auto-narrow search range, data-driven starting point definition, and parameter ranking not only provide additional insights to a user, but also give better control and understanding before proceeding to model optimization. In particular, the disclosed approach automatically screens various geological models (e.g., rock physics models) with different values of model parameters for the provided data set (e.g., sensor data from a resource site). While a set of suggested scenarios with defined values of rock physics models may be provided in some embodiments, such provisioned data may be used to guide or otherwise facilitate the training of the geological model.

[0078] Furthermore, the disclosed technology can be extended to single-objective optimization (SOO) tools from multi -objective analysis (MOA) to full-fledged multi-objectiveoptimizations (MOO) by splitting objective functions of bulk and shear moduli. According to some embodiments, a first objective function comprising an average of R2(e.g, R2= coefficient of determination) for Bulk and Shear moduli is applied during the disclosed optimization process. In some embodiments, the disclosed solution is configured to adapt weights within the objective function (OF) based on pure Bulk modulus relative to pure Shear modulus represented using the following objective function (OF) relationship:OF = a) x R2(Bulk) + (1 — m) x R2Shear), where a> E[0, 1]

[0079] It is appreciated that m represents a weight (e.g, a weight of the Bulk modulus in the overall objective function) and can take any value between 0 and 1 inclusive. With m = 0, OF = R2(Shear) indicating that the objective function in this case, would be based on just the Shear modulus. In instances where to = 0.8, OF = 0.8 x R2(Bulk) + 0.2 x R2(Shear) thereby incorporating both the Bulk and Shear moduli correlations into the objective function with the Bulk modulus component being weightier than the Shear modulus component.

[0080] According to some embodiments, the Bulk modulus characterizes the ability of a subterranean structure (e.g, a reservoir, a well) to withstand volumetric stress (measured in GPa) and is inverse to compressibility data associated with the subterranean structure. In addition, the shear modulus characterizes the rigidity of a subsurface material, and / or the resistance of said material to shear strain (e.g., measured in GPa) and / or angular distortions associated with said material in the subsurface. It is appreciated that the shear modulus is zero for fluids in the subsurface. It is further appreciated that rock physics model calibration and / or model optimization defines model parameters (e.g, rock physics model parameters) to maximize the fit between a quantity / property measured by, for example, well logs and the quantity / property computed from a calibrated rock physics model. Moreover, Bulk and Shear moduli data can be used to determine the quality of the geological model (e.g, rock physics model) by comparing observed Bulk and Shear moduli using, for example, measured well logs comprising Vp data, Vs data, density data, etc., along a given well with Bulk and Shear values calculated using the rock physics model. In some embodiments, determined elastic properties based on acoustic impedance (Al) data values, Vp / Vs values, Young modulus values, etc. may be related and or compared to the captured or measured well log values.

[0081] In some embodiments, one parameter associated with the geological model (e.g. , rock physics model) is determined e.g., calculated) based on another parameter such that any 2 parameters (e.g., Bulk and Shear moduli properties associated with parameters) associated with the geological model can be used to define or otherwise characterize the remaining parameters associated with the geological model.Flowcharts / Workflows

[0082] FIGURE 4A shows an exemplary workflow for a data-driven optimization process associated with rock physics modeling assisted by machine learning. Sensitivity analysis combined machine learning clustering operations are used to extract local optimization data 404a and 404b from sampled data plotted in the graph 402. The optimization data 404a and 404b may then be used to generate lithology data 406 as further discussed below in association with FIGURE 4B.

[0083] FIGURE 4B illustrates an exemplary detailed workflow 410 for methods, systems, and computer programs that generate rock physics data for a resource site. It is appreciated that a data engine stored in a memory device may cause a computer processor to execute the various processing stages of the workflow 410. For example, the disclosed techniques may be implemented as a data engine within a geological software tool such that the data engine enables the modeling of geological structures (e.g., wells, reservoirs, etc.) in the subsurface of a resource site based on the processes outlined herein.

[0084] At block 412, the data engine may facilitate generating a geological model comprising two or more rock physics parameters. The data engine may be further used to sample, at block 414, captured geological data associated with the resource site to generate sampled data. At block 416, the data engine evaluates, based on at least one objective function, the sampled data to determine a parameter range associated with the two or more rock physics parameters following which the data engine deploys, at block 418, based on the parameter range, a machine learning unsupervised clustering of datapoints comprised in the sampled data to generate seeds data for the geological model.

[0085] Turning to block 420, the data engine ranks, based on all the captured geological data samples or based on a fraction of the captured geological samples or based on the seeds data, the two or more rock physics parameters to prioritize a first parameter comprised in thetwo or more rock physics parameters over a second parameter comprised in the two or more rock physics parameters and thereby generate a ranked parameter list for the geological model. In response to applying the seeds data to the two or more rock physics parameters based on the ranked parameter list for the geological model, the data engine stochastically optimizes, by locating one or more new sets of parameter values and applying the new sets to evaluate one or more objective functions and thereby confirm performance of the model, the geological model based on the seeds data and the determined parameter range to generate model performance data for the geological model. In some embodiments, the data engine calibrates at block 424, based on the model performance data, the two or more parameters of the geological model to generate a calibrated geological model. The data engine may then generate, at block 426, based on the calibrated geological model, a multi-dimensional report indicating at least elastic property predictions for each lithology comprised in a reservoir associated with the resource site.

[0086] These and other implementations may each optionally include one or more of the following features.

[0087] The two or more parameters can comprise at least two of a bounding average method parameter; a Constant Cement Differential Effective Medium parameter; and one or more statistical parameters indicating metric determinations derived from the two or more rock physics parameters excluding the one or more statistical parameters. According to one embodiment, each parameter of the at least two parameters can have at least one of the following properties: a Bulk modulus phase 1 property; a Bulk modulus phase 2 property; a Shear modulus phase 1 property; a Shear modulus phase 2 property.

[0088] In some embodiments, the statistical parameters comprise at least one of: average data indicating R2coefficient determinations associated with Bulk or Shear moduli for measured data versus model performance data; and residual data comprising mean or standard deviation indicators associated with the sampled data.

[0089] Furthermore, the sampling comprises executing numerical computations on the captured geological data to extract the sampled data.

[0090] In addition, the resource site can comprise one or more well locations or one or more reservoir locations.

[0091] According to some embodiments, the geological model is a rock physics model.

[0092] Moreover, sampling the captured geological data associated with the resource site can comprise applying uncertainty sampling to the captured geological data using a quasirandom process with low-discrepancy sequence values or low-discrepancy sequence values scaled to real values.

[0093] In some cases, evaluating, using the at least one objective function, the sampled data can comprise eliminating parameter sets comprised in the sampled data that yield an increase in data points outside of Hashin- Shtrikman bounds.

[0094] Furthermore, the captured geological data can comprise one or more of: density data associated with a geological structure at the resource site; porosity data associated with the geological structure at the resource site; pressure data associated with the geological structure at the resource site; water saturation data associated with the geological structure at the resource site; hydrocarbon saturation data associated with the geological structure at the resource site; and lithology data associated with the geological structure at the resource site.

[0095] In some implementations, the captured geological data comprises one or more of well log data or core data captured by a logging tool at the resource site.

[0096] According to some embodiments, the elastic property predictions comprise data relationships between depth values associated with the reservoir and elastic property values associated with the reservoir.

[0097] Furthermore, the report may be generated on a graphical user interface by an application (e.g., a web application).

[0098] In some cases, the report is applied in at least one of: seismic wave inversion operations for / at the resource site or reservoir characterizations for / at the resource site.

[0099] In some embodiments, the report is used for at least one of: well placement operations at the resource site; equipment placement operations at the resource site and surgically locating a subsurface resource at the resource site.

[0100] In addition, the objective function can relate and / or map and / or correlate one or more of Bulk or Shear moduli data for the captured geological data to one or more geological properties associated with subsurface structures associated with the resource site.

[0101] In some implementations, a weight variable (m) controls a dependence of the at least one objective function on one or more of: a Bulk modulus characterization of asubterranean structure at the resource site or a Shear modulus characterization of the subterranean structure at the resource site.

[0102] According to one embodiment, the quality of the geological model may be assessed based on FIGURES 5A and 5B which are plots 502 and 504, respectively, derived from a generated report based on the disclosed workflows. Specifically, these figures show exemplary rock physics plots of moduli versus total porosities with Hashin-Shtrikman bounds displayed on user interfaces that allow users to compare multiple geological models (e. ., rock physics models). In particular, this figure shows a visualization indicating a plot of the Bulk and Shear moduli versus total porosity (e.g., represented in the figure as a cloud of points indicating captured / measured well data while the lines represent performance data of rock physics models). If a representative line is generated by, for example, configuring the geological model based on Bulk and / or Shear moduli, it will mean that complexity data (e.g., geological data) associated with a geological environment (e.g., subterranean structures such as reservoirs, etc.) can be represented by the geological model which in turn can be subsequently used for future analysis of the same or different geological structures.

[0103] In some cases, the disclosed solution supports visual analysis of dual objectives(e.g., Bulk modulus relative to Shear modulus objectives or objective functions) to determine data dependencies associated with the dual objectives and / or determine distinctions or conflicts between the dual objectives. In some instances, the disclosed technology beneficially enables automatically locating tradeoffs between conflicting objective functions.

[0104] This addresses concerns associated with SOO tools with attendant probability of obtaining resultant model parameter combinations that impact generated results. Moreover, the disclosed approach enables MOA for users by displaying the R2score of bulk and shear moduli in a scatter plot, as depicted in FIGURE 6, for improved decision-making. Specifically, FIGURE 6 shows a visual analysis visualization 600 of the behavior of multiple objective functions for varying parameter values to provide indications of conflicting and nonconflicting objectives. In particular, each data point indicated in this figure represents a scenario (e.g., a set of parameters) for a selected geological model (e.g., rock physics model) based on a lithology class (e.g., a bounding average method (BAM) for shale or constant cement for sand).

[0105] According to one embodiment, the horizontal axis of FIGURE 6 corresponds to the objective function with weights being comprised in the domain of [1,0]. In this example,there is a Bulk modulus mismatch based on an R2objective function for bulk modulus calculated well logs relative to modeled data associated with a rock physics model. Furthermore, the vertical axis of FIGURE 6 corresponds to a range of values associated with the objective function having weights comprised in [0,1] that indicate a Shear modulus mismatch. The z-axis of FIGURE 6 (e.g., indicated with various shades of grayscale) highlights values associated with selected model parameters for specific scenarios (e.g., critical porosity scenario).

[0106] In some embodiments, the disclosed approach focuses on dependent or independent R2Bulk and Shear moduli data indicated in the top right corner of FIGURE 6. Due to interdependencies between the Bulk and Shear moduli, a trade-off between 2 objectives (e.g., reference Pareto efficient frontier objectives). To support this process, the disclosed approach filters model parameters (e.g., critical porosity scenario parameters, etc.) as needed to optimize a given geological model.

[0107] The foregoing description, for purpose of explanation, has been described with reference to specific embodiments. However, the illustrative discussions above are not intended to be exhaustive or to limit the invention to the precise forms disclosed. Many modifications and variations are possible in view of the above teachings. The embodiments were chosen and described in order to explain the principles of the invention and its practical applications, to thereby enable others skilled in the art to use the invention and various embodiments with various modifications as are suited to the particular use contemplated. It is appreciated that the term optimize / optimal and its variants (e.g., efficient or optimally) may simply indicate improving, rather than the ultimate form of 'perfection' or the like.

[0108] It will also be understood that, although the terms first, second, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used to distinguish one element from another. For example, a first object or step could be termed a second object or step, and, similarly, a second object or step could be termed a first object or step, without departing from the scope of the invention. The first object or step, and the second object or step, are both objects or steps, respectively, but they are not to be considered the same object or step.

[0109] The terminology used in the description herein is for the purpose of describing particular embodiments and is not intended to be limiting. As used in the description of theinvention and the appended claims, the singular forms “a,” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or” as used herein refers to and encompasses any possible combination of one or more of the associated listed items. It will be further understood that the terms “includes,” “including,” “comprises” and / or “comprising,” when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0110] As used herein, the term “if’ may be construed to mean “when” or “upon” or“in response to determining” or “in response to detecting,” depending on the context.

[0111] Those with skill in the art will appreciate that while some terms in this disclosure may refer to absolutes, e.g., all source receiver traces, each of a plurality of objects, etc., the methods and techniques disclosed herein may also be performed on fewer than all of a given thing, e.g., performed on one or more components and / or performed on one or more source receiver traces. Accordingly, in instances in the disclosure where an absolute is used, the disclosure may also be interpreted to be referring to a subset.

Claims

What is claimed is:

1. A method for generating rock physics data for a resource site, the method comprising: generating a geological model including two or more rock physics parameters; sampling captured geological data associated with the resource site to generate sampled data; evaluating, using at least one objective function, the sampled data to determine a parameter range associated with the two or more rock physics parameters; deploying, based on the parameter range, a machine learning unsupervised clustering of datapoints included in the sampled data to generate seeds data for the geological model; ranking, based on the seeds data, the two or more rock physics parameters to prioritize a first parameter included in the two or more rock physics parameters over a second parameter included in the two or more rock physics parameters and thereby generate a ranked parameter list for the geological model; in response to applying the seeds data to the two or more rock physics parameters based on the ranked parameter list for the geological model, stochastically optimizing the geological model based on the seeds data and the determined parameter range to generate model performance data for the geological model; calibrating, based on the model performance data, the two or more parameters of the geological model to generate a calibrated geological model; and generating, based on the calibrated geological model, a multi-dimensional report indicating at least elastic property predictions for each lithology included in a reservoir associated with the resource site.

2. The method of claim 1, wherein the two or more parameters include at least two of: a bounding average method parameter; a Constant Cement parameter; a Differential Effective Medium parameter; and one or more statistical parameters indicating metric determinations derived from the two or more rock physics parameters excluding the one or more statistical parameters.

3. The method of claim 2, wherein the statistical parameters include at least one of average data indicating R2coefficient determinations associated with Bulk or Shear moduli for measured data versus model performance data; and residual data including mean or standard deviation indicators associated with the sampled data.

4. The method of claim 1, wherein the sampling includes executing numerical computations on the captured geological data to extract the sampled data.

5. The method of claim 1, wherein the resource site includes one or more well locations or one or more reservoir locations.

6. The method of claim 1, wherein the geological model is a rock physics model.

7. The method of claim 1, wherein sampling the captured geological data associated with the resource site includes applying uncertainty sampling to the captured geological data using a quasi-random process with low-discrepancy sequence values or low-discrepancy sequence values scaled to real values.

8. The method of claim 1, wherein evaluating, using the at least one objective function, the sampled data includes eliminating parameter sets included in the sampled data that yield an increase in data points outside of Hashin-Shtrikman bounds.

9. The method of claim 1, wherein the captured geological data includes one or more of density data associated with a geological structure at the resource site; porosity data associated with the geological structure at the resource site; pressure data associated with the geological structure at the resource site; water saturation data associated with the geological structure at the resource site; hydrocarbon saturation data associated with the geological structure at the resource site; and lithology data associated with the geological structure at the resource site.

10. The method of claim 1, wherein the captured geological data includes one or more of well log data or core data captured by a logging tool at the resource site.

11. The method of claim 1, wherein the elastic property predictions include data relationships between: depth values associated with the reservoir; and elastic property values associated with the reservoir.

12. The method of claim 1, wherein the report is generated on graphical user interface by an application.

13. The method of claim 1, wherein the report is applied in at least one of: seismic wave inversion operations for the resource site; or reservoir characterizations for the resource site.

14. The method of claim 1, wherein the report is used for at least one of: well placement operations at the resource site; equipment placement operations at the resource site; and surgically locating a subsurface resource at the resource site.

15. The method of claim 1, wherein the objective function relates one or more of Bulk or Shear moduli data for the captured geological data to one or more geological properties associated with subsurface structures associated with the resource site.

16. A system for generating rock physics data for a resource site, the system comprising: a computer processor, and a memory storing a data processing engine that includes instructions which are executable by the computer processor to: generate a geological model including two or more rock physics parameters;sample captured geological data associated with the resource site to generate sampled data; evaluate, based on at least one objective function, the sampled data to determine a parameter range associated with the two or more rock physics parameters; deploy, based on the parameter range, a machine learning unsupervised clustering of datapoints included in the sampled data to generate seeds data for the geological model; rank, based on the sampled data, the two or more rock physics parameters to prioritize a first parameter included in the two or more rock physics parameters over a second parameter included in the two or more rock physics parameters and thereby generate a ranked parameter list for the geological model; in response to applying the seeds data to the two or more rock physics parameters based on the ranked parameter list for the geological model, stochastically optimize the geological model based on the seeds data and the determined parameter range to generate model performance data for the geological model; calibrate, based on the model performance data, the two or more parameters of the geological model to generate a calibrated geological model; and generate, based on the calibrated geological model, a multi-dimensional report indicating at least elastic property predictions for each lithology included in a reservoir associated with the resource site.

17. The system of claim 16, wherein the two or more parameters include at least two of: a bounding average method parameter; a Constant Cement parameter; a Differential Effective Medium parameter; and one or more statistical parameters indicating metric determinations derived from the two or more rock physics parameters excluding the one or more statistical parameters.

18. A computer program for generating rock physics data for a resource site, the computer program including a non-transitory computer-readable medium comprising code configured to: generate a geological model including two or more rock physics parameters;sample captured geological data associated with the resource site to generate sampled data; evaluate, based on at least one objective function, the sampled data to determine a parameter range associated with the two or more rock physics parameters; deploy, based on the parameter range, a machine learning unsupervised clustering of datapoints included in the sampled data to generate seeds data for the geological model; rank, based on the seeds data, the two or more rock physics parameters to prioritize a first parameter included in the two or more rock physics parameters over a second parameter included in the two or more rock physics parameters and thereby generate a ranked parameter list for the geological model; in response to applying the seeds data to the two or more rock physics parameters based on the ranked parameter list for the geological model, stochastically optimize the geological model based on the seeds data and the determined parameter range to generate model performance data for the geological model; calibrate, based on the model performance data, the two or more parameters of the geological model to generate a calibrated geological model; and generate, based on the calibrated geological model, a multi-dimensional report indicating at least elastic property predictions for each lithology included in a reservoir associated with the resource site.

19. The computer program of claim 18, wherein the two or more parameters include at least two of: a bounding average method parameter; a Constant Cement parameter; a Differential Effective Medium parameter; and one or more statistical parameters indicating metric determinations derived from the two or more rock physics parameters excluding the one or more statistical parameters.

20. The computer program of claim 18, wherein a weight variable ( m ) controls a dependence of the at least one objective function on one or more of: a Bulk modulus characterization of a subterranean structure at the resource site; or a Shear modulus characterization of the subterranean structure at the resource site.

Images