GEOSTEERING USING RECONCILED SUBSURFACE PHYSICAL PARAMETERS

Abstract

Systems and methods for geosteering using reconciled subsurface physical parameters are disclosed. The methods include obtaining reconciled physical parameters at each of a plurality of locations within a subsurface; training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters; classifying the reconciled physical parameters into the rock type with the at least one machine learning network; and interpreting the rock type to form a subsurface geology model and inform a geosteering decision.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application is related to co-pending application Ser. No. ______, titled “METHODS AND SYSTEMS FOR PREDICTING CONDITIONS AHEAD OF A DRILL BIT” (attorney docket number 18733-1066001) filed on the same date as the present application and co-pending application Ser. No. ______, titled “GEOSTEERING USING IMPROVED DATA CONDITIONING” (attorney docket number 18733-1065001) filed on the same date as the present application. These co-pending patent applications are hereby incorporated by reference herein in their entirety.

BACKGROUND

Information about the subsurface may be derived from a variety of sources, including seismic and electromagnetic (EM) surveys obtained from the surface, seismic and EM data obtained by sensors near the drill bit during drilling, as well as from logging while drilling (LWD). The quality of the estimates of the physical parameters obtained from these data is proportional to the quality of the data, which may vary according to the data source. Therefore, LWD, EM, and seismic data must be reconciled with each other, for example through machine learning methods, with higher quality data providing more information to the reconciled result. Reconciliation of estimated parameters enables easier interpretation of features in the data, as well more accurate estimation of other subsurface properties.

One important subsurface property to know when planning the path of a well is the rock type of subsurface formations ahead of the drill bit. Certain rock types are easier to drill through. Others are more likely to contain hydrocarbons. Accordingly, there exists a need for a fast and accurate method to classify reconciled estimates of subsurface parameters into rock type.

SUMMARY

This summary is provided to introduce a selection of concepts that are further described below in the detailed description. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used as an aid in limiting the scope of the claimed subject matter.

In general, in one aspect, embodiments are disclosed related to systems and methods for geosteering using reconciled subsurface physical parameters. The methods include obtaining reconciled physical parameters at each of a plurality of locations within a subsurface; training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters; classifying the reconciled physical parameters into the rock type with the at least one machine learning network; and interpreting the rock type to form a subsurface geology model and inform a geosteering decision.

In general, in one aspect, embodiments are disclosed related to a non-transitory computer-readable memory comprising computer-executable instructions stored thereon that, when executed on a processor, cause the processor to perform the steps of geosteering using reconciled subsurface physical parameters. The steps include obtaining reconciled physical parameters at each of a plurality of locations within a subsurface; training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters; classifying the reconciled physical parameters into the rock type with the at least one machine learning network; and interpreting the rock type to form a subsurface geology model and inform a geosteering decision.

In general, in one aspect, embodiments are disclosed related to systems configured for geosteering using reconciled subsurface physical parameters. The systems include a geosteering system configured to guide a drill bit in a well and a computer system configured to obtain reconciled physical parameters at each of a plurality of locations within a subsurface; train at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters; classify the reconciled physical parameters into the rock type with the at least one machine learning network; and interpret the rock type to form a subsurface geology model and inform a geosteering decision.

Other aspects and advantages of the claimed subject matter will be apparent from the following description and the appended claims.

BRIEF DESCRIPTION OF DRAWINGS

Specific embodiments of the disclosed technology will now be described in detail with reference to the accompanying figures. Like elements in the various figures are denoted by like reference numerals for consistency.

FIG. 1 shows a drilling system in accordance with one or more embodiments.

FIG. 2A shows a neural network in accordance with one or more embodiments.

FIG. 2B shows a restricted Boltzmann machine, according to one or more embodiments.

FIG. 2C shows a deep belief network, according to one or more embodiments.

FIG. 3 shows a flowchart according to one or more embodiments.

FIG. 4 shows a computer system in accordance with one or more embodiments.

DETAILED DESCRIPTION

In the following detailed description of embodiments of the disclosure, numerous specific details are set forth in order to provide a more thorough understanding of the disclosure. However, it will be apparent to one of ordinary skill in the art that the disclosure may be practiced without these specific details. In other instances, well-known features have not been described in detail to avoid unnecessarily complicating the description.

Throughout the application, ordinal numbers (e.g., first, second, third, etc.) may be used as an adjective for an element (i.e., any noun in the application). The use of ordinal numbers is not to imply or create any particular ordering of the elements nor to limit any element to being only a single element unless expressly disclosed, such as using the terms “before”, “after”, “single”, and other such terminology. Rather, the use of ordinal numbers is to distinguish between the elements. By way of an example, a first element is distinct from a second element, and the first element may encompass more than one element and succeed (or precede) the second element in an ordering of elements.

It is to be understood that the singular forms “a”, “an,” and “the” include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to “a system” includes reference to one or more of such systems.

Terms such as “approximately,” “substantially,” etc., mean that the recited characteristic, parameter, or value need not be achieved exactly, but that deviations or variations, including for example, tolerances, measurement error, measurement accuracy limitations and other factors known to those of skill in the art, may occur in amounts that do not preclude the effect the characteristic was intended to provide.

It is to be understood that one or more of the steps shown in a flowchart may be omitted, repeated, and/or performed in a different order than the order shown. Accordingly, the scope disclosed herein should not be considered limited to the specific arrangement of steps shown in the flowchart.

Although multiple dependent claims are not introduced, it would be apparent to one of ordinary skill that the subject matter of the dependent claims of one or more embodiments may be combined with other dependent claims.

In the following description of FIGS. 1-4, any component described regarding a figure, in various embodiments disclosed herein, may be equivalent to one or more like-named components described regarding any other figure. For brevity, descriptions of these components will not be repeated regarding each figure. Thus, each and every embodiment of the components of each figure is incorporated by reference and assumed to be optionally present within every other figure having one or more like-named components. Additionally, in accordance with various embodiments disclosed herein, any description of the components of a figure is to be interpreted as an optional embodiment which may be implemented in addition to, in conjunction with, or in place of the embodiments described regarding a corresponding like-named component in any other figure.

In one aspect, embodiments disclosed herein relate to using reconciled physical parameters estimated from LWD, EM, and/or seismic data, including data obtained from near the drill bit and from deep remote sensing surveys obtained prior to drilling, to create a deep learning method for classification of rock type. The reconciliation of physical parameters implies that they are consistent with each other, thus removing any interpretation conflicts and improving quality of the subsequent classification. The classified parameters may enhance the interpretation of a subsurface geology model and the prediction of other related physical variables ahead of a drill bit for geosteering purposes.

LWD data may includes, without limitation, neutron porosity data, borehole caliber data, nuclear magnetic resonance data, gamma ray data, weight on bit data, rate of penetration data, inclination data, measured depth data, true vertical depth data, bearing data, temperature data, and pressure data.

EM methods measure electric or magnetic fields at the Earth's surface or in boreholes in order to determine electrical properties (i.e., electrical resistivity, electrical permeability or electrical permittivity) in the subsurface. Electromagnetic or electrical logging is the main technique used in oil exploration to measure the amount of hydrocarbons in the pores of underground reservoirs. Inductive EM methods include a variety of techniques that deploy wire coils at or near the surface and transmit low frequency (a few Hz to several kHz) waves into the subsurface. Other EM modalities include direct current (electrical or resistivity methods), induced polarization (IP), microwave frequencies (i.e., ground-penetrating radar), and methods that use natural electromagnetic fields (i.e., magnetotelluric methods). Ground-penetrating radar (GPR) uses antennae as sources to send time varying signals into the surface which reflect off subsurface structures. Whereas induction, induced polarization, magnetotelluric, and direct current methods provide lower resolution information, the higher frequency GPR methods may delineate smaller subsurface features. However, GPR methods are limited to penetrating only a few hundred feet into the subsurface.

Seismic methods send seismic waves (analogous to the electromagnetic waves used in GPR) into the subsurface which reflect off of structures and are recorded by sensors in boreholes or on the surface. For exploration purposes, seismic methods allow practical exploration tens of thousands of feet into the subsurface.

“Rock type” refers to a categorization or division of rocks making up a formation based on their chemistry, physical structure, and origin. For example, rocks composed primarily of quartz grains may be called “sandstone,” while those composed primarily of calcium carbonate may be called a “carbonate.” The latter group may be further divided into a “limestones” or “dolomite” depending on the crystallographic form of the grains, while rocks with high fractions of kerogen may be called “shale.”

An example of a rock type defined by its origin is an aeolian sandstone, a sedimentary rock that may have been deposited in a desert, i.e., a primordial sand dune. A marine sandstone may have originated as a beach composed of quartz sand. Similarly, a limestone may be further subdivided into, for example a “reef-limestone,” a “forereef limestone”, or an “oolitic limestone” depending on how and where it was deposited.

Further subdivisions are used. For example, marine sandstones may be subdivided into coarse, intermediate, and fine-grained sandstones, or well-sorted (i.e., composed of very similar sized grains), and poorly-sorted sandstones.

Different rock types may exhibit different physical characteristics. For example, well-sorted coarse grained sandstones may typically exhibit high porosity and high permeability, while shales may typically exhibit low porosity and low permeability. Consequently, measured physical characteristics may often be used to infer the rock type at the location of the measurement. However, as used herein the term rock type does not include the physical characteristics.

The terms “rock type” and “lithology” are sometimes used interchangeably as having the same meaning. However, in other cases, lithology includes but goes beyond rock type to include the age, a visual and physical description of the rock, e.g., “a soft, red, highly permeable, Permian, aeolian sandstone.” Herein, we use this latter meaning.

FIG. 1 illustrates systems in accordance with one or more embodiments. Specifically, FIG. 1 shows a well (102) that may be drilled by a drill bit (104) attached by a drillstring (106) to a drill rig (100) located on the surface of the earth (116). The borehole (118) corresponds to the uncased portion of the well (102). The borehole (118) of the well (102) may traverse a plurality of overburden layers (110) and one or more cap-rock layers (112) to a hydrocarbon reservoir (114). As the well (102) is being drilled, tools located near the drill bit (104) may perform physical measurements resulting in different data sets (LWD, seismic while drilling, EM while drilling). The various data sets are related to different physical parameters of the rock formations through which the drill bit (104) is passing. For instance, seismic data gives information on acoustic impedance, and EM data provides information on the resistivity of the rocks, LWD data may include neutron porosity data, borehole caliber data, nuclear magnetic resonance data, gamma ray data, weight on bit data, rate of penetration data, inclination data, measured depth data, true vertical depth data, bearing data, temperature data, pressure data, sonic, deep azimuthal resistivity, and density logs. Surface seismic and surface EM data may also be obtained from larger-scale, deep remote sensing surveys of the subsurface conducted prior to drilling. The estimated physical parameters may be reconciled with each other before further processing. The reconciliation process removes noise from the estimated physical parameters and ensures that they are more consistent with each other.

The geosteering system may include functionality for monitoring various sensor signatures (e.g., an acoustic signature from acoustic sensors) that gradually or suddenly change as a well path traverses overburden layers (110), cap-rock layers (112), or enters a hydrocarbon reservoir (114) due to sudden changes in the lithology between these regions. For example, a sensor signature of the hydrocarbon reservoir (114) may be different from the sensor signature of the cap-rock layer (112). When the drill bit (104) drills out of the hydrocarbon reservoir (114) and into the cap-rock layer (112), a detected amplitude spectrum of a particular sensor type may change suddenly between the two distinct sensor signatures. In contrast, when drilling from the hydrocarbon reservoir (114) downward into the bed rock (117), the detected amplitude spectrum may gradually change.

During the lateral drilling of the borehole (118), preliminary upper and lower boundaries of a formation layer's thickness may be derived from a deep remote sensing survey and/or an offset well obtained before drilling the borehole (118). If a vertical section of the well (102) is drilled, the actual upper and lower boundaries of a formation layer may be determined. Based on well data, an operator may steer the drill bit (104) through a lateral section of the borehole (118) in real time. In particular, a logging tool may monitor a detected sensor signature proximate the drill bit (104), where the detected sensor signature may continuously be compared against prior sensor signatures, e.g., of signatures detected in the cap-rock layer (112), hydrocarbon reservoir (114), and bed rock (117). As such, if the detected sensor signature of drilled rock is the same or similar to the sensor signature of the hydrocarbon reservoir (114), the drill bit (104) may still be drilling in the hydrocarbon reservoir (114). In this scenario, the drill bit (104) may be operated to continue drilling along its current path and at a predetermined distance from a boundary of the hydrocarbon reservoir. If the detected sensor signature is same as or similar to the prior sensor signatures of the cap-rock layer (112) or the bed rock (117), respectively, then the geosteering system may determine that the drill bit (104) is drilling out of the hydrocarbon reservoir (114) and into the upper or lower boundary of the hydrocarbon reservoir (114), respectively. At this point, the vertical position of the drill bit (104) at this lateral position below the surface may be determined and the upper and lower boundaries of the hydrocarbon reservoir (114) may be updated.

In the embodiment of the invention presented here, the reconciled physical parameters are related to rock type, which may be a categorical variable. The classified rock type of subsurface formations allow a geologist to interpret the geologic setting; this, in turn, allows for better decisions in the well-drilling process (e.g., geosteering), and better planning of field development.

It is assumed that there exists information from nearby wells (102) or other fields that may be used as training data for a machine learning method. This information takes the form of training data where the input/output pairs are reconciled physical parameters (the input) and an interpreted and classified rock types (output). The reconciled physical parameters were obtained from estimated physical parameters which, in turn, were obtained from remote sensing data (including seismic, EM, and LWD data). It is assumed that information as to the rock type was obtained at the same location as the remote sensing data.

It is possible that each rock type has values of other physical variables associated with it. That is, by classifying a point in the subsurface as being of a certain rock type, one may know from nearby well data that this rock type usually has fixed values for certain physical properties, e.g., porosity and permeability. The rock type classification may be done according to petrophysical properties such as, e.g., hardness categories. An ordinal variable like hardness could show what locations in the subsurface will cause slower drilling, and thus a geosteering program may preferentially avoid these areas.

Linking the reconciled physical parameters (e.g., acoustic impedance and resistivity) to another a categorical variable (e.g., rock type) requires constructing a mathematical function that takes as input the reconciled physical properties and produces as an output the categorical variable. Machine learning (ML) methods are general purpose functions that can accomplish this task.

FIG. 2A shows a neural network (200), a common ML architecture for prediction/inference. At a high level, a neural network (200) may be graphically depicted as comprising nodes (202), shown here as circles, and edges (204), shown here as directed lines connecting the circles. The nodes (202) may be grouped to form layers, such as the four layers (208, 210, 212, 214) of nodes (202). The nodes (202) are grouped into columns for visualization of their organization. However, the grouping need not be as shown in FIG. 2A. The edges (204) connect the nodes (202). Edges (204) may connect, or not connect, to any node(s) (202) regardless of which layer (205) the node(s) (202) is in. That is, the nodes (202) may be fully or sparsely connected. A neural network (200) will have at least two layers with the first layer (208) considered as the “input layer” and the last layer (214) as the “output layer”. Any intermediate layer, such as layers (210) and (212) is usually described as a “hidden layer”. A neural network (200) may have zero or more hidden layers e.g., hidden layers (210) and (212). However, a neural network (200) with at least one hidden layer (210, 212) may be described as a “deep” neural network forming the basis of a “deep learning method”. In general, a neural network (200) may have more than one node (202) in the output layer (214). In this case the neural network (200) may be referred to as a “multi-target” or “multi-output” network.

Nodes (202) and edges (204) carry additional associations. Namely, every edge is associated with a numerical value. The numerical value of an edge, or even the edge (204) itself, is often referred to as a “weight” or a “parameter”. While training a neural network (200), numerical values are assigned to each edge (204). Additionally, every node (202) is associated with a numerical variable and an activation function. Activation functions are not limited to any functional class, but traditionally follow the form:

$\begin{array}{cc}A=f\left({\sum }_{i\in \left(i\mathrm{ncoming}\right)}\left[{\left(\mathrm{node}\mathrm{value}\right)}_i{\left(\mathrm{edge}\mathrm{value}\right)}_i\right]\right),& \left(1\right)\end{array}$

where i is an index that spans the set of “incoming” nodes (202) and edges (204) and f is a user-defined function. Incoming nodes (202) are those that, when viewed as a graph (as in FIG. 2A), have directed arrows that point to the node (202) where the numerical value is being computed. Functional forms of ƒ may include the linear function ƒ(x)=x, sigmoid function

$f\left(x\right)=\frac{1}{1+e^{-x}},$

and rectified linear unit function ƒ(x)=max(0,x), however, many additional functions are commonly employed. Each node (202) in a neural network (200) may have a different associated activation function. Often, as a shorthand, activation functions are described by the function ƒ by which it is composed. That is, an activation function composed of a linear function ƒ may simply be referred to as a linear activation function without undue ambiguity.

When the neural network (200) receives an input, the input is propagated through the network according to the activation functions and incoming node (202) values and edge (204) values to compute a value for each node (202). That is, the numerical value for each node (202) may change for each received input. Occasionally, nodes (202) are assigned fixed numerical values, such as the value of 1, that are not affected by the input or altered according to edge (204) values and activation functions. Fixed nodes (202) are often referred to as “biases” or “bias nodes” (206), and are depicted in FIG. 2A with a dashed circle.

In some implementations, the neural network (200) may contain specialized layers (205), such as a normalization layer, or additional connection procedures, like concatenation. One skilled in the art will appreciate that these alterations do not exceed the scope of this disclosure.

As noted, the training procedure for the neural network (200) comprises assigning values to the edges (204). To begin training, the edges (204) are assigned initial values. These values may be assigned randomly, assigned according to a prescribed distribution, assigned manually, or by some other assignment mechanism. Once edge (204) values have been initialized, the neural network (200) may act as a function, such that it may receive inputs and produce an output. As such, at least one input is propagated through the neural network (200) to produce an output. Recall that a given data set will be composed of inputs and associated target(s), where the target(s) represent the “ground truth”, or the otherwise desired output. The neural network (200) output is compared to the associated input data target(s). The comparison of the neural network (200) output to the target(s) is typically performed by a so-called “loss function”; although other names for this comparison function such as “error function” and “cost function” are commonly employed. Many types of loss functions are available, such as the mean-squared-error function. However, the general characteristic of a loss function is that it provides a numerical evaluation of the similarity between the neural network (200) output and the associated target(s). The loss function may also be constructed to impose additional constraints on the values assumed by the edges (204), for example, by adding a penalty term, which may be physics-based, or a regularization term. Generally, the goal of a training procedure is to alter the edge (204) values to promote similarity between the neural network (200) output and associated target(s) over the data set. Thus, the loss function is used to guide changes made to the edge (204) values, typically through a process called “backpropagation”.

The particular kind of a neural network (200) used in the method presented in this invention is a deep belief network. A deep belief network is composed of another kind of neural network known as a restricted Boltzmann machine (RBM), a two-layer neural network where the first layer corresponds to visible variables and the second layer corresponds to hidden variables. FIG. 2B shows an example of an RBM. The first layer of the RBM contains the visible nodes (220), corresponding to observed data. The second layer of the RBM contains hidden nodes (222). A required characteristic of RBMs, and hence of deep belief networks (228), is that the conditional probability of a particular visible node (220) only depends on the hidden nodes (222) to which it is connected by an edge (204). Similarly, the conditional probability of a particular hidden node (222) only depends on the visible node (220) to which it is connected by an edge (204). This is known as the bipartite structure. RBMs are typically defined such that the nodes (202) are binary valued. This, however, is not a limitation of the structure. It is easy extended to real valued variables, although training a real-valued RBM or deep belief network requires more computation.

The goal of an RBM is to capture the probabilistic structure of the data. A probability distribution is defined over the visible nodes (220) and hidden nodes (222) such that input vectors that look similar to the data used to train the RBM are assigned higher probability values. By assigning a cut-off probability value, one may allow the RBM to discriminate whether new input data belongs to the same group of data as the training data. This allow for feature detection/classification. Assuming the training data correspond to a rock type, the RBM may classify whether the new reconciled physical parameters sent into the RBM are of the same rock type.

By linking RMBs together end-to-end, the ability to classify is increased, and a deep belief network (228) is constructed, as shown in FIG. 2C. Furthermore, several deep belief networks may be constructed in this fashion, each one corresponding to a different rock type. Once learned, each deep belief network (228) may be used determine the probability that a new set of reconciled physical parameters input into the deep belief network (228) belong to that particular rock type. In this way, multiple classifications for different rock types may be conducted.

A training data set for the deep belief network (228) may come from offset wells or wells (102) from another reservoir where data was previously collected and the values of physical parameters were estimated and then reconciled, and where the rock type is known at the same locations.

Expert information may also be incorporated into each deep belief network (228) by manually modifying its weights. Such expert information may come from the interpretation of a geologist who knows that certain patterns or occurrences of rock types must occur, or cannot occur, at a particular location. Some pairs of training data may be reserved for testing and evaluation purposes. The deep belief networks (228) may be validated on this test data. The quality of the classification conducted by the deep belief networks (228) may be based on their training and testing accuracy score. An accuracy score above 80% on both training and a testing dataset are considered adequate. If the deep belief network (228) cannot reach this level of accuracy, it may be beneficial to find more training data, retrain, and then re-measure the accuracy score to ensure they have reached 80%.

An advantage of using a deep belief network (228) in the method is its adaptability to, and automatic classification of, various data sets. Furthermore, it allows expert information to be taken into account during the data reconciliation process via manually adjusting the weights in the deep belief networks (228). In this way, this method enables the automatic and data-driven classification of looking ahead of the bit measurement data, for consistent interpretation and estimation geologic properties.

Feature importance quantification techniques (LIME and Shapley values) may be used in conjunction with training to determine which reconciled physical parameter has the most effect on the output classification of the deep belief networks (228). Shapley values are determined after a neural network is trained by modifying the input and observing changes to the output. The Shapley values enable an expert such as geologist to modify the deep belief networks (228), e.g., remove nodes (202), that do not affect the resulting classification, thus improving efficiency.

FIG. 3 shows a workflow in accordance with one or more embodiments. In Step 302, any outliers or erroneous data may be removed from the reconciled physical parameters as a preprocessing step by any method or methods known in the art, without departing from the scope of the invention. Next, in Step 304, the deep belief network (228) is trained using data from offset wells to convert each reconciled physical parameter into rock type. In Step 306, Shapley values are determined for the deep belief network (228) to determine which inputs have the most effect on the output of the network. In optional Step 307, an expert may use the information provided by the Shapley values to manually set the values of certain nodes (202) in the deep belief networks (228), and remove other edges/nodes (202, 204) to increase efficiency. The reweighted deep belief networks (228) may be retrained again, repeating Step 304 and Step 306. This loop may be repeated until an optimal deep belief network (228) is constructed. Next, in Step 308, the modified deep belief network (228) classifies the reconciled physical parameters into rock types. This may be performed at any location where reconciled parameters have been obtained. In Step 310, if classification is performed at a new drilling location ahead of the drill bit (104), the results may be used by a geologist, well manager, or data interpreter, to interpret the subsurface environment and assist in geosteering and planning of the path of the well (102).

The system for predicting conditions ahead of the drill bit (104) may include a computing system such as that shown in FIG. 4. The computing system may be a control system. The computing system, in one or more embodiments, performs a method for predicting the rock type ahead of the drill bit (104) by classifying reconciled physical parameters. The system for predicting conditions ahead of the drill bit (104) may include other components, in addition to the computing system. For example, the system for predicting conditions ahead of the drill bit (104) may include data sources other than those previously described.

FIG. 4 depicts a block diagram of a computer system (402) used to provide computational functionalities associated with described algorithms, methods, functions, processes, flows, and procedures as described in this disclosure, according to one or more embodiments. The illustrated computer (402) is intended to encompass any computing device such as a server, desktop computer, laptop/notebook computer, wireless data port, smart phone, personal data assistant (PDA), tablet computing device, one or more processors within these devices, or any other suitable processing device, including both physical or virtual instances (or both) of the computing device. Additionally, the computer (402) may include a computer that includes an input device, such as a keypad, keyboard, touch screen, or other device that can accept user information, and an output device that conveys information associated with the operation of the computer (402), including digital data, visual, or audio information (or a combination of information), or a GUI.

The computer (402) can serve in a role as a client, network component, a server, a database or other persistency, or any other component (or a combination of roles) of a computer system for performing the subject matter described in the instant disclosure. The illustrated computer (402) is communicably coupled with a network (430). In some implementations, one or more components of the computer (402) may be configured to operate within environments, including cloud-computing-based, local, global, or other environment (or a combination of environments).

At a high level, the computer (402) is an electronic computing device operable to receive, transmit, process, store, or manage data and information associated with the described subject matter. According to some implementations, the computer (402) may also include or be communicably coupled with an application server, e-mail server, web server, caching server, streaming data server, business intelligence (BI) server, or other server (or a combination of servers).

The computer (402) can receive requests over network (430) from a client application (for example, executing on another computer (402) and responding to the received requests by processing the said requests in an appropriate software application. In addition, requests may also be sent to the computer (402) from internal users (for example, from a command console or by other appropriate access method), external or third-parties, other automated applications, as well as any other appropriate entities, individuals, systems, or computers.

Each of the components of the computer (402) can communicate using a system bus (403). In some implementations, any or all of the components of the computer (402), both hardware or software (or a combination of hardware and software), may interface with each other or the interface (404) (or a combination of both) over the system bus (403) using an application programming interface (API) (412) or a service layer (413) (or a combination of the API (412) and service layer (413). The API (412) may include specifications for routines, data structures, and object classes. The API (412) may be either computer-language independent or dependent and refer to a complete interface, a single function, or even a set of APIs. The service layer (413) provides software services to the computer (402) or other components (whether or not illustrated) that are communicably coupled to the computer (402). The functionality of the computer (402) may be accessible for all service consumers using this service layer. Software services, such as those provided by the service layer (413), provide reusable, defined business functionalities through a defined interface. For example, the interface may be software written in JAVA, C++, or other suitable language providing data in extensible markup language (XML) format or another suitable format. While illustrated as an integrated component of the computer (402), alternative implementations may illustrate the API (412) or the service layer (413) as stand-alone components in relation to other components of the computer (402) or other components (whether or not illustrated) that are communicably coupled to the computer (402). Moreover, any or all parts of the API (412) or the service layer (413) may be implemented as child or sub-modules of another software module, enterprise application, or hardware module without departing from the scope of this disclosure.

The computer (402) includes an interface (404). Although illustrated as a single interface (404) in FIG. 4, two or more interfaces (404) may be used according to particular needs, desires, or particular implementations of the computer (402). The interface (404) is used by the computer (402) for communicating with other systems in a distributed environment that are connected to the network (430). Generally, the interface (404) includes logic encoded in software or hardware (or a combination of software and hardware) and operable to communicate with the network (430). More specifically, the interface (404) may include software supporting one or more communication protocols associated with communications such that the network (430) or interface's hardware is operable to communicate physical signals within and outside of the illustrated computer (402).

The computer (402) includes at least one computer processor (405). Although illustrated as a single computer processor (405) in FIG. 4, two or more processors may be used according to particular needs, desires, or particular implementations of the computer (402). Generally, the computer processor (405) executes instructions and manipulates data to perform the operations of the computer (402) and any algorithms, methods, functions, processes, flows, and procedures as described in the instant disclosure.

The computer (402) also includes a memory (406) that holds data for the computer (402) or other components (or a combination of both) that can be connected to the network (430). For example, memory (406) can be a database storing data consistent with this disclosure. Although illustrated as a single memory (406) in FIG. 4, two or more memories may be used according to particular needs, desires, or particular implementations of the computer (402) and the described functionality. While memory (406) is illustrated as an integral component of the computer (402), in alternative implementations, memory (406) can be external to the computer (402).

The application (407) is an algorithmic software engine providing functionality according to particular needs, desires, or particular implementations of the computer (402), particularly with respect to functionality described in this disclosure. For example, application (407) can serve as one or more components, modules, applications, etc. Further, although illustrated as a single application (407), the application (407) may be implemented as multiple applications (407) on the computer (402). In addition, although illustrated as integral to the computer (402), in alternative implementations, the application (407) can be external to the computer (402).

There may be any number of computers (402) associated with, or external to, a computer system containing computer (402), wherein each computer (402) communicates over network (430). Further, the term “client,” “user,” and other appropriate terminology may be used interchangeably as appropriate without departing from the scope of this disclosure. Moreover, this disclosure contemplates that many users may use one computer (402), or that one user may use multiple computers (402).

Although only a few example embodiments have been described in detail above, those skilled in the art will readily appreciate that many modifications are possible in the example embodiments without materially departing from this invention. Accordingly, all such modifications are intended to be included within the scope of this disclosure as defined in the following claims

Claims

1. A method, comprising:

obtaining reconciled physical parameters at each of a plurality of locations within a subsurface;

training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters;

classifying the reconciled physical parameters into the rock type with the at least one machine learning network; and

interpreting the rock type to form a subsurface geology model and inform a geosteering decision.

2. The method of claim 1, wherein obtaining reconciled physical parameters further comprises preprocessing the reconciled physical parameters to remove outliers.

3. The method of claim 1, wherein the at least one machine learning network comprises a deep belief network.

4. The method of claim 3, wherein the deep belief network comprises at least one restricted Boltzmann machine (RBM).

5. The method of claim 1, wherein the training further comprises incorporating expert information.

6. The method of claim 5, wherein incorporating the expert information comprises assigning values to nodes.

7. The method of claim 6, wherein the values assigned to the nodes are based on a determination of at least one Shapley value.

8. The method of claim 1, wherein the reconciled physical parameters are obtained from logging-while-drilling (LWD) data.

9. The method of claim 8, wherein the LWD data comprises at least one selected from the group consisting of: neutron porosity data, borehole caliber data, nuclear magnetic resonance data, gamma ray data, weight on bit data, rate of penetration data, inclination data, measured depth data, true vertical depth data, bearing data, temperature data, and pressure data.

10. A non-transitory computer-readable memory comprising computer-executable instructions stored thereon that, when executed on a processor, cause the processor to perform the steps of:

obtaining reconciled physical parameters at each of a plurality of locations within a subsurface;

training at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters;

classifying the reconciled physical parameters into the rock type with the at least one machine learning network; and

interpreting the rock type to form a subsurface geology model and inform a geosteering decision.

11. The non-transitory computer-readable memory comprising computer-executable instructions stored thereon of claim 10, wherein obtaining reconciled physical parameters further comprises preprocessing the reconciled physical parameters to remove outliers.

12. The non-transitory computer-readable memory comprising computer-executable instructions stored thereon of claim 10, wherein the at least one machine learning network comprises a deep belief network.

13. The non-transitory computer-readable memory comprising computer-executable instructions stored thereon of claim 12, wherein the deep belief network comprises at least one restricted Boltzmann machine (RBM).

14. The non-transitory computer-readable memory comprising computer-executable instructions stored thereon of claim 10, wherein the training further comprises incorporating expert information.

15. The non-transitory computer-readable memory comprising computer-executable instructions stored thereon of claim 14, wherein incorporating the expert information comprises assigning values to nodes.

16. The non-transitory computer-readable memory comprising computer-executable instructions stored thereon of claim 15, wherein the values assigned to the nodes are based on a determination of at least one Shapley value.

17. The non-transitory computer-readable memory comprising computer-executable instructions stored thereon of claim 10, wherein the reconciled physical parameters are determined from physical parameters that are estimated from at least one selected from the group consisting of: logging while drilling (LWD) data, seismic data, and electromagnetic data.

18. The non-transitory computer-readable memory comprising computer-executable instructions stored thereon of claim 17, wherein the LWD data comprises at least one selected from the group consisting of: neutron porosity data, borehole caliber data, nuclear magnetic resonance data, gamma ray data, weight on bit data, rate of penetration data, inclination data, measured depth data, true vertical depth data, bearing data, temperature data, and pressure data.

19. A system, comprising:

a computer, configured to:

obtain reconciled physical parameters at each of a plurality of locations within a subsurface,

train at least one machine learning network to classify the reconciled physical parameters into a rock type based, at least in part, on the reconciled physical parameters,

classify the reconciled physical parameters into the rock type with the at least one machine learning network, and

interpret the rock type to form a subsurface geology model; and

a geosteering system, configured to guide a drill bit through the subsurface.

20. The system of claim 19, wherein the drill bit is guided according to an interpreted rock type.