Hydraulic Fracturing in a Subsurface Formation

Description

TECHNICAL FIELD

This disclosure relates to hydraulic fracturing in a subsurface formation.

BACKGROUND

Hydraulic fracturing is a process of injecting pressurized fluids (e.g., water, chemicals) with or without solids (e.g., sand, proppant) into a well in a subsurface formation to cause fractures in the rock of the formation. The fractures provide pathways for hydrocarbons contained within the subsurface formation to flow to the well for extraction. Hydraulic fracturing can be used in unconventional reservoirs (e.g., reservoirs with low porosity and/or permeability) to increase the ability to produce hydrocarbons from the reservoir.

SUMMARY

Unconventional reservoirs, such as tight reservoirs, can be primary candidates for current and future hydrocarbon production as hydrocarbons in conventional reservoirs are depleted. To profitably develop tight reservoirs, horizontal wells can be used to increase the reservoir contact. Multi-stage hydraulic fracturing techniques can be applied to the wells to increase reservoir conductivity to the wellbores by creating flow channels in the tight reservoirs. Multi-stage hydraulic fracturing includes performing fracturing operations on individually isolated portions (stages) of a well.

This disclosure provides an approach for multi-stage hydraulic fracturing in a subsurface formation. Multi-stage hydraulic fracture models can be generated from a geo-mechanics simulation and hydraulic fracture simulation. The fracture models can be propagated to additional stages in the same well or different wells using artificial intelligence techniques. The fracture models can be integrated into a reservoir model using, for example, a local grid refinement (LGR) method, multiple-continuum models, or using embedded discrete fracture models (EDFM). Reservoir simulations can be performed to determine well spacing, cluster spacing, and/or hydraulic fracture designs.

Implementations of the systems and methods of this disclosure can provide various technical benefits. Production in unconventional reservoirs can be modelled using data-driven methods using artificial intelligence (AI). Various machine-learning techniques such as support vector regression (SVR), multiple linear regression (MLR), and backpropagation (BP) neural networks trained using numerical simulation data can be utilized to forecast the production performance of unconventional resources before drilling or fracturing wells in the reservoir. The reusability of machine learning techniques can reduce computational cost; however, the complex transport mechanisms of shale reservoirs may not be readily accounted for. Numerical simulations that account for various complex mechanisms such as phase transition, nonlinear flow behavior, and non-Darcy flow, can achieve the most accurate predictions without production data. Numerical simulations typically involve both geo-mechanics simulation and reservoir simulation. Numerical simulations can be more computationally expensive than data driven or analytical techniques. Training machine learning models using numerical simulation data to forecast future production performance enables these methods to be utilized in well fracturing design and production planning schemes like analytical methods (e.g., material balance equations (MBE), decline curve analysis (DCA), and rate transient analysis (RTA)) or machine learning models that rely on previous production data from the unconventional resource.

Using data-driven, artificial intelligence techniques to propagate hydraulic fracture models in a reservoir model can reduce computational cost and computation time by decreasing the amount of computation to generate representations of the hydraulic fractures in the reservoir model as compared with generating representations of the hydraulic fractures using geomechanical simulations. The reduced computations result in the ability to perform multiple reservoir simulations with varying parameters to optimize well spacing and/or cluster spacing in the reservoir. Training the artificial intelligence techniques using simulated data enables forecasting hydrocarbon production performance before a well is drilled or fractured to enable alterations to the well placement or hydraulic fracture design to improve hydrocarbon production after completion of the well. The prediction results generated by this approach can have high accuracy (e.g., similar to accuracy of full numerical simulations) while being generated with reduced computational cost compared with numerical simulations.

The details of one or more implementations of these systems and methods are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of these systems and methods will be apparent from the description and drawings, and from the claims.

DESCRIPTION OF DRAWINGS

FIG. 1 is a schematic illustration of a hydraulic fracturing operation.

FIG. 2 is a block diagram of a system for modelling multi-stage hydraulic fractures.

FIG. 3 is a flow chart for a method for modelling hydraulic fractures in a subsurface formation.

FIG. 4 is an illustration of an artificial neural network for modelling hydraulic fractures.

FIGS. 5A-5C are views of hydraulic fractures in a well in a reservoir model.

FIGS. 6A-6B are views of multiple wells in a reservoir model with integrated hydraulic fractures.

FIG. 7 illustrates hydrocarbon production operations that include field operations and computational operations, according to some implementations.

FIG. 8 is a block diagram illustrating an example computer system used to provide computational functionalities associated with described algorithms, methods, functions, processes, flows, and procedures according to some implementations of the present disclosure.

Like reference symbols in the various drawings indicate like elements.

DETAILED DESCRIPTION

Unconventional reservoirs, such as tight reservoirs, can be primary candidates for current and future hydrocarbon production as hydrocarbons in conventional reservoirs are depleted. To profitably develop tight reservoirs, horizontal wells can be used to increase the reservoir contact. Multi-stage hydraulic fracturing techniques can be applied to the wells to increase reservoir conductivity to the wellbores by creating flow channels in the tight reservoirs. Multi-stage hydraulic fracturing includes performing fracturing operations on individually isolated portions (stages) of a well.

This disclosure provides an approach for multi-stage hydraulic fracturing in a subsurface formation. Multi-stage hydraulic fracture models can be generated from a geo-mechanics simulation and hydraulic fracture simulation. The fracture models can be propagated to additional stages in the same well or different wells using artificial intelligence techniques. The fracture models can be integrated into a reservoir model using, for example, a local grid refinement (LGR) method, multiple-continuum models, or using embedded discrete fracture models (EDFM). Reservoir simulations can be performed to determine well spacing, cluster spacing, and/or hydraulic fracture designs.

FIG. 1 is a schematic illustration of an example implementation of a hydraulic fracturing system 100. Generally, system 100 may be operated to apply a fracture treatment to a subsurface formation 106 (e.g., rock formation, geologic formation) from a wellbore 104 that extends from a surface 102 to the subsurface formation 106. Fracture treatments can be used, for example, to form or propagate fractures in a rock layer of the subsurface formation 106 by injecting pressurized fluid. The fracture treatment can enhance or otherwise influence production of petroleum, natural gas, coal seam gas, or other types of reservoir resources.

The wellbore 104 shown in FIG. 1 includes vertical and horizontal sections, as well as a curved section that connects the vertical and horizontal portions. Generally, and in alternative implementations, the wellbore 104 can include horizontal, vertical (e.g., only vertical), slant, curved, and other types of wellbore geometries and orientations, and the fracture treatment can generally be applied to any portion of a subsurface formation 106. The wellbore 104, in this example, includes a casing 110 that is cemented or otherwise secured to the wellbore wall to define a borehole 108 in the inner volume of the casing 110. In alternative implementations, the wellbore 104 can be uncased or include uncased sections. Perforations (not specifically labeled) can be formed in the casing 110 to allow fracturing fluids and/or other materials to flow into the borehole 108 and to the terranean surface 102. Perforations can be formed using shape charges, a perforating gun, and/or other tools. Although illustrated as generally vertical portions and generally horizontal portions, such parts of the wellbore 104 may deviate from exactly vertical and exactly horizontal (e.g., relative to the surface 102) depending on the formation techniques of the wellbore 104, type of rock formation in the subsurface formation 106, and other factors.

The surface 102 can be any appropriate surface from which drilling and completion equipment may be staged to recover hydrocarbons from a subsurface zone. For example, in some aspects, the surface 102 may represent a body of water, such as a sea, gulf, ocean, lake, or otherwise. In some aspects, all or part of a drilling and completion system, including hydraulic fracturing system 100, may be staged on the body of water or on a floor of the body of water (e.g., ocean or gulf floor). Thus, references to surface 102 includes reference to bodies of water, terranean surfaces under bodies of water, as well as land locations.

Subsurface formation 106 includes one or more rock or geologic formations that bear hydrocarbons (e.g., oil, gas) or other fluids (e.g., water) to be produced to the surface 102. For example, the rock or geologic formations can be shale, sandstone, or other type of rock, typically, that may be hydraulically fractured to initiate, increase, or enhance the production of such hydrocarbons.

The example hydraulic fracturing system 100 includes a hydraulic fracturing liquid circulation system 112 that is fluidly coupled to the borehole 108 through conduit 120 and also fluidly coupled to a first hydraulic fracturing liquid 114 and a second hydraulic fracturing liquid 116. In some aspects, there may be multiple first hydraulic fracturing liquids 114 and/or multiple second hydraulic fracturing liquids 116 (e.g., each liquid stored separately). In some aspects, each of the multiple liquids (whether 114 or 116) may be the same composition (e.g., each first hydraulic fracturing liquid 114 is the same or each second hydraulic fracturing liquid 116 is the same).

In some aspects, as shown, the hydraulic fracturing liquid circulation system 112 is fluidly coupled to the subsurface formation 106 (which could include a single formation, multiple formations or portions of a formation) through a working string 130 (e.g., a tubular string that may be lowered and raised through the borehole 109). Generally, the hydraulic fracturing liquid circulation system 112 can be deployed, for example, via skid equipment, a marine vessel, sub-sea deployed equipment, or other types of equipment and include hoses, tubes, fluid tanks or reservoirs, pumps, valves, and/or other suitable structures and equipment arranged to circulate a hydraulic fracturing liquid 128 through the working string 130 and into the subsurface formation 106. The working string 130 is positioned to communicate the hydraulic fracturing liquid 128 into the wellbore 104 and can include coiled tubing, sectioned pipe, and/or other structures that communicate fluid through the wellbore 104. The working string 130 can also include flow control devices, bypass valves, ports, and or other tools or well devices that control the flow of fracturing fluid from the interior of the working string 130 into the subsurface formation 106.

In this example, a control system 118 is communicably coupled to the hydraulic fracturing liquid circulation system 112 (and may also be communicably coupled to one or more other components in the hydraulic fracturing system 100, such as flow control devices in the conduit 120, the working string 130, or other components). Generally, the control system 118, which may be electronic, electric, electro-mechanical, mechanical, pneumatic, or a combination thereof, may control (e.g., automatically without real-time human intervention, by a human operator, or a combination thereof) the hydraulic fracturing liquid circulation system 112 to deliver the hydraulic fracturing liquid 128 at specified flowrates, pressures, and time durations to the working string 130 and to the subsurface formation 106 to hydraulically fracture a geologic or rock formation. Control of the hydraulic fracturing liquid circulation system 112 may include, for example, opening, closing, and modulating one or more valves that fluidly couple the circulation system 112 to the first and second hydraulic fracturing liquid sources 114 and 116, as well as the conduit 120 and the working string 130. Control of the hydraulic fracturing liquid circulation system 112 may also include, for example, controlling one or more pump motor controllers (e.g., variable frequency drives) to circulate one or both of the first and second hydraulic fracturing liquid sources 114 and 116 into the working string 130 and to the subsurface formation 106.

Generally, the first hydraulic fracturing liquid 114 includes a pad or pre-pad liquid that does not include proppant. For example, in some examples, the first hydraulic fracturing liquid 114 (which may be mixed, generated, and stored at the wellsite or delivered to the wellsite) may include a slickwater liquid. For instance, the slickwater hydraulic fracturing liquid may consist of water mixed with a low concentration of a friction reducer to reduce a friction pressure in the working string 130 as the first hydraulic fracturing liquid 114 is circulated to the subsurface formation 106 by the hydraulic fracturing liquid circulation system 112. The friction reducer may be based on acrylamide polymers or copolymers. In some specific examples, the first hydraulic fracturing liquid 114 may include a water or brine-based Acrylamido Methyl Propane Sulfonate (AMPS)-polyacrylamide slickwater.

The second hydraulic fracturing liquid 116 includes a liquid that does include proppant (e.g., plastic-based or coated with resin or polymer or other softer materials to mitigate embedment issues). For example, in some examples, the second hydraulic fracturing liquid 116 (which may be mixed, generated, and stored at the wellsite or delivered to the wellsite) may also include a slickwater liquid, such as a slickwater that is seawater- or brine-based and includes proppant. Moreover, in some aspects, the second hydraulic fracturing liquid 116 may include two separate hydraulic fracturing liquids. For example, one of the second hydraulic fracturing liquid 116 may be a slickwater hydraulic fracturing liquid, while another of the second hydraulic fracturing liquid 116 may be a linear or crosslinked hydraulic fracturing liquid that also includes proppant. Thus, for the present disclosure, the difference between the one or more first hydraulic fracturing liquids 114 (e.g., pad and pre-pad liquids) and the one or more second hydraulic fracturing liquids 116 is that the one or more first hydraulic fracturing liquids 114 does not include proppant and the one or more second hydraulic fracturing liquids 116 does include proppant. Both, however, may be circulated by the hydraulic fracturing liquid circulation system 112 into the working string 130 as the hydraulic fracturing liquid 128 (e.g., based on a particular step being implemented in the hydraulic fracture job or operation).

As shown in FIG. 1, there may be multiple fracture zones (or stages) 122, 124, and 126 within the subsurface formation 106. In some aspects, the first and second hydraulic fracturing liquids 114 and 116 may be circulated in a specified order, and at specified times within a hydraulic fracturing job (e.g., multi-stage) to fractures in the zones 122, 124, and 126. Although three fracture zones or stages are shown, more or fewer fracture zones or stages can be used. In some aspects, each zone 122, 124, and 126 may be fluidly isolated, e.g., with packers 132 or other zonal isolation devices or techniques. Such isolation may be implemented within the hydraulic fracturing process, e.g., after or prior to certain circulations of the first or second hydraulic fracturing liquids 114 or 116.

The design of a multi-stage fracturing operation can depend on the geomechanics of the subsurface formation 106. The design of the fracturing operation can change from stage to stage when geomechanical, geological, and/or petrophysical properties of the subsurface formation 106 change along the length of the well bore 104. For example, the fracturing pressure, the amount of proppant, size of proppant, duration of the fracturing operation, etc. can be modified depending on the properties of the subsurface formation 106 at a particular fracture zone. Modelling of the subsurface formation can be used to design multi-stage hydraulic fractures that maximize production from the subsurface formation, reduce costs, and reduce overlap between adjacent wells.

FIG. 2 is a block diagram of an example system 200 for modelling hydraulic fractures in a subsurface formation. The system 200 includes several modules that generate, store, and/or transform data and make the data available to one or more other modules. The system 200 can be implemented on one or more data processing systems (e.g., computer systems or control systems).

Geo-mechanics modelling module 202 generates a model of a hydraulic fracture for one or more stages in a well in a subsurface formation. The subsurface formation can include an unconventional reservoir (e.g., a tight reservoir). The geo-mechanics modelling module 202 performs a numerical simulation (e.g., a finite-element simulation) based on geomechanical properties of the subsurface formation (e.g., Young's modulus, Poisson's ratio, permeability, etc.) to generate a model of the hydraulic fracture. The numerical simulation can also include parameters for the hydraulic fracturing including, for example, fracture spacing, injection rate, a time series of pumping schedules, proppant concentration, well static pressure, well bottom hole pressure, fracture pressure, etc. The geophysical, geo-mechanical and hydraulic fracturing properties can enable the geo-mechanics modelling module 202 to model stress and strain for considering stress shadowing effects on complex fracture geometry, which can cause differences in fracture geometry for each stage of the well. The output of the geomechanics modelling module 202 can be, for example, a rectangle shape of a hydraulic fracture centralized in a well perforation location or the width and half-length of a fracture generated from the inputs. The output can also include discrete values of fracture conductivities (millidarcy feet (md*ft), millidarcy meter (md*m), m³) mapped to fracture geometry. The output (e.g., the hydraulic fracture) can be stored in the hydraulic fracture database 204.

Hydraulic fracture database 204 stores hydraulic fractures generated by the geo-mechanics module 202. The hydraulic fractures stored in hydraulic fracture database 204 can be used to correlate input parameters (e.g., geomechanical properties, hydraulic fracture parameters) with resulting hydraulic fractures. For example, a regression method can be used to correlate the input parameters with the hydraulic fractures. The hydraulic fracture database 204 can also be used to form training and validation datasets for machine learning models.

The AI module 206 can generate AI models that link the geo-mechanical, geological, and hydraulic fracture inputs to the resulting hydraulic fracture outputs based on the data generated by the geo-mechanics module 202 and/or the data stored in the hydraulic fractures database 204. The AI module 206 can incorporate data-driven methods such as machine learning models and deep learning models. The AI module 206 can also use statistical techniques (e.g., linear and non-linear regression) or geometric techniques (e.g., affine transformations) to establish correlations between inputs and outputs. The AI module 206 takes inputs 205 (e.g., reservoir properties, geo-mechanics properties, hydraulic fracturing properties, microseismic data) and produces outputs 207 (e.g., hydraulic fracture geometry). The AI models generated by AI module 206 can reduce computation time for simulating hydrocarbon production for a hydraulically fractured well by reducing the computational time and complexity to generate hydraulic fractures in a reservoir model for each stage in a multi-stage well.

For example, for a simple case (e.g., homogeneous reservoir and neglecting mechanisms affecting fracture stress geometry), the AI module 206 can replicate the geometry of a hydraulic fracture (e.g., produced by the geo-mechanics modelling module 202 or from the hydraulic fractures database 204), by performing a three-dimensional (3D) mapping using an affine transformation including scaling, reflection, translation, and rotation. An affine transformation can be an input matrix multiplied by a weight matrix in terms. The weight matrix can be determined using a machine learning model based on the input parameters. In a more complex case, the AI module 206 can use, for example, a deep learning framework that is trained based on the hydraulic fractures stored in the hydraulic fracture database 204. After training, the deep learning framework (e.g., a neural network) can be used to generate hydraulic fractures for one or more additional well stages. The deep learning framework can also be continually updated based on newly acquired or newly simulated data.

The outputs 207 of the AI module 206 are stored in hydraulic fracture module 208. The hydraulic fracture module 208 can store the hydraulic fractures for each stage in a multi-stage well and/or hydraulic fractures in multiple multi-stage wells with a subsurface formation.

Geological model module 210 generates a reservoir model 212 incorporating geological, geomechanical, and/or petrophysical properties. One or more wells can be represented in the reservoir model 212, and execution of the reservoir model 212 can simulate hydrocarbon production of the one or more wells.

The system 200 can integrate 216 the hydraulic fractures 208 with the reservoir model 212 to perform a numerical simulation 214 of the hydrocarbon production from one or more fractured wells in the reservoir model 212. Hydraulic fractures can be integrated 216 into the reservoir model 212 using, for example, local grid refinement (LGR), an unstructured grid, a multiple continuum model, discrete fracture models (DFM), and/or embedded discrete fracture models (EDFM).

The numerical simulation 214 using hydraulic fractures 208 and reservoir models 212 can predict the production performance of multi-stage fractured horizontal wells in unconventional reservoir. The numerical simulation 214 can incorporate complex mechanism such as compaction and adsorption, nonlinear flow behavior, non-Darcy flow, etc. in unconventional reservoirs. The numerical simulation 214 can be used in simulation studies to optimize construction design and maximize production benefits, by predicting the production performance before drilling and hydraulic fracturing begin.

The system 200 can be used to efficiently conduct well spacing and cluster spacing sensitivity studies. Well spacing can include, for example, the spacing between vertical or horizontal wells in the subsurface formation. Optimizing the well spacing can be important since large well spacing may lead to unrecovered oil/gas between wells, and small well spacing can make hydraulic fracture from one well overlaps in the other, wells may interfere with each other in production. Small well spacing results in drilling more wells, and thus increases the cost. An optimal well spacing can maximize the hydrocarbon recovery and minimize the cost. Determining an optimal well spacing can require many simulation runs of the reservoir model with the integrated hydraulic fractures. Cluster spacing can include the number of fractures in a stage and/or the number of stages within a well in the subsurface formation. Capturing the architecture of hydraulic fractures in a simulator offers an opportunity to understand the impacts of the hydraulic fractures on production before drilling wells in the subsurface formation and/or before performing a hydraulic fracturing operation. In some implementations, the system 200 can be used for history matching and production forecasts.

FIG. 3 is a flow chart of an example method 300 for hydraulic fracturing a subsurface formation. The method 300 can be implemented on a data processing system (e.g., the computer system of FIG. 8).

The data processing system obtains a reservoir model representing a subsurface formation (step 302). For example, the data processing system may access the reservoir model from a data store, or the data processing system may generate the reservoir model.

The data processing system obtains a baseline hydraulic fracture model for one or more stages of a well in the subsurface formation based on the reservoir model (step 304). For example, the data processing system obtains the hydraulic fracture model by generating a hydraulic fracture model by performing a geomechanics simulation of the subsurface formation based on geomechanical and geophysical properties of the subsurface formation. In some implementations, the data processing system obtains the baseline hydraulic fracture model by accessing a data store storing one or more hydraulic fracture models.

The data processing system generates additional hydraulic fracture models for one or more additional stages in one or more wells in the subsurface formation using a machine learning model trained based on the baseline hydraulic fracture model (step 306). The machine learning model can include an affine transformation or an artificial neural network. Inputs to the machine learning model can include one or more of geomechanical properties, geophysical properties, and time-series data for a hydraulic fracturing operation. Geomechanical properties can include Young's modulus, Poisson's ratio, permeability, etc. The machine learning model can include hydraulic fracturing parameters including, for example, fracture spacing, injection rate, a time series of pumping schedules, proppant concentration, well static pressure, well bottom hole pressure, fracture pressure, etc.

The data processing system can train the machine learning model. The training data to train the machine learning model can include input features such as geomechanical and geophysical properties of the subsurface formation and labeled output including the obtained hydraulic fracture model. The data processing system can obtain the input and output data for the training data from a data store (e.g., a hydraulic fracture database), or from a geomechanics simulation, or both.

The data processing system integrates the additional hydraulic fracture models into the reservoir model (step 308). For example, the data processing system can integrate the additional hydraulic fracture models into the reservoir model by using local grid refinement, an unstructured grid, or embedded discrete fracture models to represent the fractures in the reservoir model.

The data processing system simulates hydrocarbon production from the subsurface formation using the reservoir model with the integrated additional hydraulic fracture models (step 310). For example, the data processing system executes a massively parallel simulation (e.g., hundreds to thousands of processes) of the reservoir model to simulate hydrocarbon production from the subsurface formation by solving coupled flow equations in parallel.

The data processing system determines a well spacing for the one or more wells or a cluster spacing for hydraulic fractures in the one or more wells based on the simulated hydrocarbon production (step 312). For example, the data processing system can perform a sensitivity analysis by iteratively simulating hydrocarbon production from the subsurface formation while altering spacing parameters of wells or clusters in the reservoir model.

In some implementations, the data processing system causes the drilling of one or more wells in the subsurface formation based on the determined well spacing (step 314). For example, the data processing system generates control commands to control drilling equipment to drill wells in the subsurface formation based on the well spacing. In some implementations, the data processing system causes performance of a hydraulic fracturing operation on the one or more wells based on the determined cluster spacing (step 316). For example, the data processing system can generate control commands to control hydraulic fracturing equipment in a hydraulic fracturing operation (e.g., hydraulic fracturing operation 100) based on the determined cluster spacing.

FIG. 4 is a schematic of an example artificial neural network 400 that can be used to generate hydraulic fracture models. Artificial neural network 400 includes four layers, an input layer 402, two hidden layers 404, 406, and an output layer 408. Artificial neural network 400 is a fully connected neural network (e.g., each node in a first layer is connected to each node in the next consecutive layer). The input layer 400, as shown, includes three input nodes 402a-c. The node 402a represents Poisson's ratio, the node 402b represents Young's modulus, and the node 402c represents permeability, fracture spacing, or injection rate. In some implementations, more input nodes can be used representing additional geomechanical and hydraulic fracture parameters. The output layer 408 includes a node representing a hydraulic fracture 408a. The hydraulic fracture 408a can represent, for example, the shape, fracture half length, or fracture height of the hydraulic fracture.

FIGS. 5A-5B illustrate example hydraulic fractures 500, 502 integrated into a reservoir simulation. The hydraulic fractures 500, 502 can be generated using, for example, a geomechanical simulation. FIG. 5C illustrates a well 510 with hydraulic fractures 512 replicated in many stages of along the length of the well 510. For example, the hydraulic fractures 512 are replicated in each stage of the well 510 using a machine learning model.

FIGS. 6A-6B illustrate hydraulic fractures replicated in multiple wells in a reservoir model of a subsurface formation. FIG. 6A shows a side view of three wells 602, 604, 606 each with hydraulic fractures replicated along the length of the wells. FIG. 6B shows a perspective view of many wells in a subsurface formation 610 with hydraulic fractures generated based on the methods and systems herein.

FIG. 7 illustrates hydrocarbon production operations 700 that include both one or more field operations 710 and one or more computational operations 712, which exchange information and control exploration for the production of hydrocarbons. In some implementations, outputs of techniques of the present disclosure (e.g., the method 500) can be performed before, during, or in combination with the hydrocarbon production operations 700, specifically, for example, either as field operations 710 or computational operations 712, or both.

Examples of field operations 710 include forming/drilling a wellbore, hydraulic fracturing, producing through the wellbore, injecting fluids (such as water) through the wellbore, to name a few. In some implementations, methods of the present disclosure can trigger or control the field operations 710. For example, the methods of the present disclosure can generate data from hardware/software including sensors and physical data gathering equipment (e.g., seismic sensors, well logging tools, flow meters, and temperature and pressure sensors). The methods of the present disclosure can include transmitting the data from the hardware/software to the field operations 710 and responsively triggering the field operations 710 including, for example, generating plans and signals that provide feedback to and control physical components of the field operations 710. Alternatively, or in addition, the field operations 710 can trigger the methods of the present disclosure. For example, implementing physical components (including, for example, hardware, such as sensors) deployed in the field operations 710 can generate plans and signals that can be provided as input or feedback (or both) to the methods of the present disclosure.

Examples of computational operations 712 include one or more computer systems 720 that include one or more processors and computer-readable media (e.g., non-transitory computer-readable media) operatively coupled to the one or more processors to execute computer operations to perform the methods of the present disclosure. The computational operations 712 can be implemented using one or more databases 718, which store data received from the field operations 710 and/or generated internally within the computational operations 712 (e.g., by implementing the methods of the present disclosure) or both. For example, the one or more computer systems 720 process inputs from the field operations 710 to assess conditions in the physical world, the outputs of which are stored in the databases 718. For example, seismic sensors of the field operations 710 can be used to perform a seismic survey to map subsurface features, such as facies and faults. In performing a seismic survey, seismic sources (e.g., seismic vibrators or explosions) generate seismic waves that propagate in the earth and seismic receivers (e.g., geophones) measure reflections generated as the seismic waves interact with boundaries between layers of a subsurface formation. The source and received signals are provided to the computational operations 712 where they are stored in the databases 718 and analyzed by the one or more computer systems 720.

In some implementations, one or more outputs 722 generated by the one or more computer systems 720 can be provided as feedback/input to the field operations 710 (either as direct input or stored in the databases 718). The field operations 710 can use the feedback/input to control physical components used to perform the field operations 710 in the real world.

For example, the computational operations 712 can process the seismic data to generate three-dimensional (3D) maps of the subsurface formation. The computational operations 712 can use these 3D maps to provide plans for locating and drilling exploratory wells. In some operations, the exploratory wells are drilled using logging-while-drilling (LWD) techniques which incorporate logging tools into the drill string. LWD techniques can enable the computational operations 712 to process new information about the formation and control the drilling to adjust to the observed conditions in real-time.

The one or more computer systems 720 can update the 3D maps of the subsurface formation as information from one exploration well is received and the computational operations 712 can adjust the location of the next exploration well based on the updated 3D maps. Similarly, the data received from production operations can be used by the computational operations 712 to control components of the production operations. For example, production well and pipeline data can be analyzed to predict slugging in pipelines leading to a refinery and the computational operations 712 can control machine operated valves upstream of the refinery to reduce the likelihood of plant disruptions that run the risk of taking the plant offline.

In some implementations of the computational operations 712, customized user interfaces can present intermediate or final results of the above-described processes to a user. Information can be presented in one or more textual, tabular, or graphical formats, such as through a dashboard. The information can be presented at one or more on-site locations (such as at an oil well or other facility), on the Internet (such as on a webpage), on a mobile application (or app), or at a central processing facility.

The presented information can include feedback, such as changes in parameters or processing inputs, that the user can select to improve a production environment, such as in the exploration, production, and/or testing of petrochemical processes or facilities. For example, the feedback can include parameters that, when selected by the user, can cause a change to, or an improvement in, drilling parameters (including drill bit speed and direction) or overall production of a gas or oil well. The feedback, when implemented by the user, can improve the speed and accuracy of calculations, streamline processes, improve models, and solve problems related to efficiency, performance, safety, reliability, costs, downtime, and the need for human interaction.

In some implementations, the feedback can be implemented in real-time, such as to provide an immediate or near-immediate change in operations or in a model. The term real-time (or similar terms as understood by one of ordinary skill in the art) means that an action and a response are temporally proximate such that an individual perceives the action and the response occurring substantially simultaneously. For example, the time difference for a response to display (or for an initiation of a display) of data following the individual's action to access the data can be less than 1 millisecond (ms), less than 1 second(s), or less than 5 s. While the requested data need not be displayed (or initiated for display) instantaneously, it is displayed (or initiated for display) without any intentional delay, taking into account processing limitations of a described computing system and time required to, for example, gather, accurately measure, analyze, process, store, or transmit the data.

Events can include readings or measurements captured by downhole equipment such as sensors, pumps, bottom hole assemblies, or other equipment. The readings or measurements can be analyzed at the surface, such as by using applications that can include modelling applications and machine learning. The analysis can be used to generate changes to settings of downhole equipment, such as drilling equipment. In some implementations, values of parameters or other variables that are determined can be used automatically (such as through using rules) to implement changes in oil or gas well exploration, production/drilling, or testing. For example, outputs of the present disclosure can be used as inputs to other equipment and/or systems at a facility. This can be especially useful for systems or various pieces of equipment that are located several meters or several miles apart or are located in different countries or other jurisdictions.

FIG. 8 is a block diagram of an example computer system 800 used to provide computational functionalities associated with described algorithms, methods, functions, processes, flows, and procedures described in the present disclosure, according to some implementations of the present disclosure. The illustrated computer 802 is intended to encompass any computing device such as a server, a desktop computer, a laptop/notebook computer, a wireless data port, a smart phone, a personal data assistant (PDA), a tablet computing device, or one or more processors within these devices, including physical instances, virtual instances, or both. The computer 802 can include input devices such as keypads, keyboards, and touch screens that can accept user information. Also, the computer 802 can include output devices that can convey information associated with the operation of the computer 802. The information can include digital data, visual data, audio information, or a combination of information. The information can be presented in a graphical user interface (UI) (or GUI).

The computer 802 can serve in a role as a client, a network component, a server, a database, a persistency, or components of a computer system for performing the subject matter described in the present disclosure. The illustrated computer 802 is communicably coupled with a network 830. In some implementations, one or more components of the computer 802 can be configured to operate within different environments, including cloud-computing-based environments, local environments, global environments, and combinations of environments.

At a high level, the computer 802 is an electronic computing device operable to receive, transmit, process, store, and manage data and information associated with the described subject matter. According to some implementations, the computer 802 can also include, or be communicably coupled with, an application server, an email server, a web server, a caching server, a streaming data server, or a combination of servers.

The computer 802 can receive requests over network 830 from a client application (for example, executing on another computer 802). The computer 802 can respond to the received requests by processing the received requests using software applications. Requests can also be sent to the computer 802 from internal users (for example, from a command console), external (or third) parties, automated applications, entities, individuals, systems, and computers.

Each of the components of the computer 802 can communicate using a system bus 803. In some implementations, any or all of the components of the computer 802, including hardware or software components, can interface with each other or the interface 804 (or a combination of both), over the system bus 803. Interfaces can use an application programming interface (API) 812, a service layer 813, or a combination of the API 812 and service layer 813. The API 812 can include specifications for routines, data structures, and object classes. The API 812 can be either computer-language independent or dependent. The API 812 can refer to a complete interface, a single function, or a set of APIs.

The service layer 813 can provide software services to the computer 802 and other components (whether illustrated or not) that are communicably coupled to the computer 802. The functionality of the computer 802 can be accessible for all service consumers using this service layer. Software services, such as those provided by the service layer 813, can provide reusable, defined functionalities through a defined interface. For example, the interface can be software written in JAVA, C++, or a language providing data in extensible markup language (XML) format. While illustrated as an integrated component of the computer 802, in alternative implementations, the API 812 or the service layer 813 can be stand-alone components in relation to other components of the computer 802 and other components communicably coupled to the computer 802. Moreover, any or all parts of the API 812 or the service layer 813 can be implemented as child or sub-modules of another software module, enterprise application, or hardware module without departing from the scope of the present disclosure.

The computer 802 includes an interface 804. Although illustrated as a single interface 804 in FIG. 8, two or more interfaces 804 can be used according to particular needs, desires, or particular implementations of the computer 802 and the described functionality. The interface 804 can be used by the computer 802 for communicating with other systems that are connected to the network 830 (whether illustrated or not) in a distributed environment. Generally, the interface 804 can include, or be implemented using, logic encoded in software or hardware (or a combination of software and hardware) operable to communicate with the network 830. More specifically, the interface 804 can include software supporting one or more communication protocols associated with communications. As such, the network 830 or the interface's hardware can be operable to communicate physical signals within and outside of the illustrated computer 802.

The computer 802 includes a processor 805. Although illustrated as a single processor 805 in FIG. 8, two or more processors 805 can be used according to particular needs, desires, or particular implementations of the computer 802 and the described functionality. Generally, the processor 805 can execute instructions and can manipulate data to perform the operations of the computer 802, including operations using algorithms, methods, functions, processes, flows, and procedures as described in the present disclosure.

The computer 802 also includes a database 806 that can hold data for the computer 802 and other components connected to the network 830 (whether illustrated or not). For example, database 806 can hold data 816 (e.g., resistivity data). For example, database 806 can be an in-memory, conventional, or a database storing data consistent with the present disclosure. In some implementations, database 806 can be a combination of two or more different database types (for example, hybrid in-memory and conventional databases) according to particular needs, desires, or particular implementations of the computer 802 and the described functionality. Although illustrated as a single database 806 in FIG. 8, two or more databases (of the same, different, or combination of types) can be used according to particular needs, desires, or particular implementations of the computer 802 and the described functionality. While database 806 is illustrated as an internal component of the computer 802, in alternative implementations, database 806 can be external to the computer 802.

The computer 802 also includes a memory 807 that can hold data for the computer 802 or a combination of components connected to the network 830 (whether illustrated or not). Memory 807 can store any data consistent with the present disclosure. In some implementations, memory 807 can be a combination of two or more different types of memory (for example, a combination of semiconductor and magnetic storage) according to particular needs, desires, or particular implementations of the computer 802 and the described functionality. Although illustrated as a single memory 807 in FIG. 8, two or more memories 807 (of the same, different, or combination of types) can be used according to particular needs, desires, or particular implementations of the computer 802 and the described functionality. While memory 807 is illustrated as an internal component of the computer 802, in alternative implementations, memory 807 can be external to the computer 802.

The application 808 can be an algorithmic software engine providing functionality according to particular needs, desires, or particular implementations of the computer 802 and the described functionality. For example, application 808 can serve as one or more components, modules, or applications. Further, although illustrated as a single application 808, the application 808 can be implemented as multiple applications 808 on the computer 802. In addition, although illustrated as internal to the computer 802, in alternative implementations, the application 808 can be external to the computer 802.

The computer 802 can also include a power supply 814. The power supply 814 can include a rechargeable or non-rechargeable battery that can be configured to be either user- or non-user-replaceable. In some implementations, the power supply 814 can include power-conversion and management circuits, including recharging, standby, and power management functionalities. In some implementations, the power-supply 814 can include a power plug to allow the computer 802 to be plugged into a wall socket or a power source to, for example, power the computer 802 or recharge a rechargeable battery.

There can be any number of computers 802 associated with, or external to, a computer system containing computer 802, with each computer 802 communicating over network 830. Further, the terms “client,” “user,” and other appropriate terminology can be used interchangeably, as appropriate, without departing from the scope of the present disclosure. Moreover, the present disclosure contemplates that many users can use one computer 802 and one user can use multiple computers 802.

Implementations of the subject matter and the functional operations described in this specification can be implemented in digital electronic circuitry, in tangibly embodied computer software or firmware, in computer hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Software implementations of the described subject matter can be implemented as one or more computer programs. Each computer program can include one or more modules of computer program instructions encoded on a tangible, non transitory, computer-readable computer-storage medium for execution by, or to control the operation of, data processing apparatus. Alternatively, or additionally, the program instructions can be encoded in/on an artificially generated propagated signal. The example, the signal can be a machine-generated electrical, optical, or electromagnetic signal that is generated to encode information for transmission to suitable receiver apparatus for execution by a data processing apparatus. The computer-storage medium can be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of computer-storage mediums.

The terms “data processing apparatus,” “computer,” and “electronic computer device” (or equivalent as understood by one of ordinary skill in the art) refer to data processing hardware. For example, a data processing apparatus can encompass all kinds of apparatus, devices, and machines for processing data, including by way of example, a programmable processor, a computer, or multiple processors or computers. The apparatus can also include special purpose logic circuitry including, for example, a central processing unit (CPU), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC). In some implementations, the data processing apparatus or special purpose logic circuitry (or a combination of the data processing apparatus or special purpose logic circuitry) can be hardware- or software-based (or a combination of both hardware- and software-based). The apparatus can optionally include code that creates an execution environment for computer programs, for example, code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of execution environments. The present disclosure contemplates the use of data processing apparatuses with or without conventional operating systems, for example LINUX, UNIX, WINDOWS, MAC OS, ANDROID, or IOS.

The methods, processes, or logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform functions by operating on input data and generating output. The methods, processes, or logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, for example, a CPU, an FPGA, or an ASIC.

Computer readable media (transitory or non-transitory, as appropriate) suitable for storing computer program instructions and data can include all forms of permanent/non-permanent and volatile/non-volatile memory, media, and memory devices. Computer readable media can include, for example, semiconductor memory devices such as random access memory (RAM), read only memory (ROM), phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices. Computer readable media can also include, for example, magnetic devices such as tape, cartridges, cassettes, and internal/removable disks.

While this specification contains many specific implementation details, these should not be construed as limitations on the scope of what may be claimed, but rather as descriptions of features that may be specific to particular implementations. Certain features that are described in this specification in the context of separate implementations can also be implemented, in combination, in a single implementation. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple implementations, separately, or in any suitable sub-combination. Moreover, although previously described features may be described as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can, in some cases, be excised from the combination, and the claimed combination may be directed to a sub-combination or variation of a sub-combination.

Particular implementations of the subject matter have been described. Other implementations, alterations, and permutations of the described implementations are within the scope of the following claims as will be apparent to those skilled in the art. While operations are depicted in the drawings or claims in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed (some operations may be considered optional), to achieve desirable results. In certain circumstances, multitasking or parallel processing (or a combination of multitasking and parallel processing) may be advantageous and performed as deemed appropriate.

Moreover, the separation or integration of various system modules and components in the previously described implementations should not be understood as requiring such separation or integration in all implementations, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

Accordingly, the previously described example implementations do not define or constrain the present disclosure. Other changes, substitutions, and alterations are also possible without departing from the spirit and scope of the present disclosure.

Furthermore, any claimed implementation is considered to be applicable to at least a computer-implemented method; a non-transitory, computer-readable medium storing computer-readable instructions to perform the computer-implemented method; and a computer system comprising a computer memory interoperably coupled with a hardware processor configured to perform the computer-implemented method or the instructions stored on the non-transitory, computer-readable medium.

A number of implementations of these systems and methods have been described. Nevertheless, it will be understood that various modifications may be made without departing from the spirit and scope of this disclosure. Accordingly, other implementations are within the scope of the following claims.

Examples

In an example implementation, a method for hydraulic fracturing a subsurface formation includes obtaining a reservoir model representing a subsurface formation; obtaining a baseline hydraulic fracture model for one or more stages of a well in the subsurface formation based on the reservoir model; generating additional hydraulic fracture models for one or more additional stages in one or more wells in the subsurface formation using a machine learning model trained based on the baseline hydraulic fracture model; integrating the additional hydraulic fracture models into the reservoir model; simulating hydrocarbon production from the subsurface formation using the reservoir model with the integrated additional hydraulic fracture models; and determining a well spacing for the one or more wells or a cluster spacing for hydraulic fractures in the one or more wells based on the simulated hydrocarbon production.

An aspect combinable with the example implementation includes drilling one or more wells in the subsurface formation based on the determined well spacing.

Another aspect combinable with any of the previous aspects includes performing a hydraulic fracturing operation on the one or more wells based on the determined cluster spacing.

In another aspect combinable with any of the previous aspects, obtaining the baseline hydraulic fracture model includes generating the baseline hydraulic fracture model by performing a geomechanics simulation of the subsurface formation based on geomechanical and geophysical properties of the subsurface formation.

In another aspect combinable with any of the previous aspects, the machine learning model includes an affine transformation or an artificial neural network.

Another aspect combinable with any of the previous aspects includes training the machine learning model where training data to train the machine learning model includes input features including geomechanical and geophysical properties of the subsurface formation and labeled output including the obtained hydraulic fracture model.

In another aspect combinable with any of the previous aspects, inputs to the machine learning model include one or more of geomechanical properties, geophysical properties, and time-series data for a hydraulic fracturing operation.

In another aspect combinable with any of the previous aspects, integrating the additional hydraulic fracture models into the reservoir model includes using local grid refinement, an unstructured grid, or embedded discrete fracture models to represent the fractures in the reservoir model.

In another aspect combinable with any of the previous aspects, determining the well spacing or the cluster spacing includes performing a sensitivity analysis by iteratively simulating hydrocarbon production from the subsurface formation while altering spacing parameters of wells or clusters in the reservoir model.

In another example implementation, a system for hydraulic fracturing a subsurface formation includes at least one processor and a memory storing instructions that when executed by the at least one processor cause the at least one processor to perform operations including obtaining a reservoir model representing a subsurface formation; obtaining a baseline hydraulic fracture model for one or more stages of a well in the subsurface formation based on the reservoir model; generating additional hydraulic fracture models for one or more additional stages in one or more wells in the subsurface formation using a machine learning model trained based on the baseline hydraulic fracture model; integrating the additional hydraulic fracture models into the reservoir model; simulating hydrocarbon production from the subsurface formation using the reservoir model with the integrated additional hydraulic fracture models; and determining a well spacing for the one or more wells or a cluster spacing for hydraulic fractures in the one or more wells based on the simulated hydrocarbon production.

In an aspect combinable with the example implementation, the instructions include drilling one or more wells in the subsurface formation based on the determined well spacing or performing a hydraulic fracturing operation on the one or more wells based on the determined cluster spacing.

In another aspect combinable with any of the previous aspects, obtaining the baseline hydraulic fracture model includes generating the baseline hydraulic fracture model by performing a geomechanics simulation of the subsurface formation based on geomechanical and geophysical properties of the subsurface formation.

In another aspect combinable with any of the previous aspects, the instructions include training the machine learning model wherein training data to train the machine learning model includes input features including geomechanical and geophysical properties of the subsurface formation and labeled output including the obtained hydraulic fracture model.

In another aspect combinable with any of the previous aspects, the machine learning model includes an affine transformation or an artificial neural network.

In another aspect combinable with any of the previous aspects, integrating the additional hydraulic fracture models into the reservoir model includes using local grid refinement, an unstructured grid, or embedded discrete fracture models to represent the fractures in the reservoir model.

In another aspect combinable with any of the previous aspects, determining the well spacing or the cluster spacing includes performing a sensitivity analysis by iteratively simulating hydrocarbon production from the subsurface formation while altering spacing parameters of wells or clusters in the reservoir model.

In another example implementation, one or more non-transitory, machine-readable storage devices storing instructions for hydraulic fracturing a subsurface formation, the instructions being executable by one or more processors, to cause performance of operations including obtaining a reservoir model representing a subsurface formation; obtaining a baseline hydraulic fracture model for one or more stages of a well in the subsurface formation based on the reservoir model; generating additional hydraulic fracture models for one or more additional stages in one or more wells in the subsurface formation using a machine learning model trained based on the baseline hydraulic fracture model; integrating the additional hydraulic fracture models into the reservoir model; simulating hydrocarbon production from the subsurface formation using the reservoir model with the integrated additional hydraulic fracture models; and determining a well spacing for the one or more wells or a cluster spacing for hydraulic fractures in the one or more wells based on the simulated hydrocarbon production.

In an aspect combinable with any the example implementation, the instructions include drilling one or more wells in the subsurface formation based on the determined well spacing or performing a hydraulic fracturing operation on the one or more wells based on the determined cluster spacing.

In another aspect combinable with any of the previous aspects, obtaining the baseline hydraulic fracture model includes generating the baseline hydraulic fracture model by performing a geomechanics simulation of the subsurface formation based on geomechanical and geophysical properties of the subsurface formation.

In another aspect combinable with any of the previous aspects, the instructions include training the machine learning model wherein training data to train the machine learning model includes input features including geomechanical and geophysical properties of the subsurface formation and labeled output including the obtained hydraulic fracture model.