CHARACTERIZING GEOLOGICAL FACIES ASSOCIATIONS IN A SUBSURFACE FORMATION

Description

TECHNICAL FIELD

The present disclosure relates to methods and systems for predicting geological facies associations in a subsurface formation to enable hydrocarbon extraction from the subsurface formation.

BACKGROUND

In geology, sedimentary facies are bodies of sediment that are recognizably distinct from adjacent sediments that resulted from different depositional environments. Generally, geologists distinguish facies by aspects of the rock or sediment being studied. Depositional facies associations refer, for example, to groups of sedimentary facies that occur together and can be interpreted to represent a particular depositional environment or a series of related environments. Depositional facies associations can provide a broad context of the deposition processes and environments including spatial and temporal relationships between different facies. In the oil and gas industry, depositional facies associations can be useful for building geological models and identifying portions of a subsurface formation containing hydrocarbons that can be produced to the surface.

SUMMARY

Facies prediction can be used in the geological and geophysical domains to determine distributions and characteristics of geological facies in subsurface formations. Facies associations can be predicted in subsurface formations including, for example, subsurface formations that include fluvial and tidal components in the depositional system that can cause irregular or unusual log responses in open hole well logs due to high gamma ray readings from radioactive sandy facies. Features can be extracted from well logs that distinguish sand and mud facies in the subsurface formation. The extracted features can include, for example, differences between various types of porosity logs and features representing depositional settings of the subsurface formation. Facies associations for the subsurface formation can be predicted by executing a series of machine learning models that receive the extracted features as input. Using the predicted facies associations along with the already existing facies associations from cored wells, locations to place new wells in the subsurface formation can be determined.

This disclosure describes systems and processes for characterizing geological facies in a subsurface formation. The described systems and processes can utilize a data processing system (e.g., a computer or control system). The data processing system can access, e.g., from a hardware storage device, porosity well logs from one or more wells in a subsurface formation. The data processing system can generate a first set of input features derived from the porosity well logs. The input features can include relative differences between the porosity well logs. The data processing system can identify sand and mud facies along a depth of the one or more wells by executing a first machine learning model that receives as input the porosity well logs. The data processing system can process the sand and mud facies to generate a second set of input features indicating depositional settings of the sand facies. The data processing system can predict facies associations for the one or more wells by executing a second machine learning model that receives the first set and the second set of input features as input. The data processing system can identify one or more locations to place one or more new wells in the subsurface formation based on the predicted facies associations. The facies associations can indicate, for example, regions in the subsurface formation with a higher hydrocarbon potential than other regions in the subsurface formation.

Implementations of the systems and processes of this disclosure can provide various technical benefits. The described systems and processes can differentiate facies that have similar log responses resulting in more accurate characterization of subsurface formations. For example, radioactive sand faces can generate gamma ray log responses similar to mud facies and formations including fluvial and tidal components can produce similar log responses. The described systems and processes can accurately predict the facies associations by accounting for the geological sequence of the subsurface formation along the depth of a well. The described systems and processes can predict facies associations for wells without core samples or borehole images by training the machine learning models using well logs labeled with core sample and/or borehole image data from wells with core samples or borehole images. These systems and processes can predict facies associations to fill in gaps in geological models between cored intervals of cored wells. The predicted facies associations can be used in blind test runs to quality check the consistencies of wireline log signatures in different cored wells in the subsurface formation.

The details of one or more embodiments 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.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic illustrating an example wireline operation in a subsurface formation.

FIG. 2 is a block diagram of an example system for characterizing facies associations in a subsurface formation.

FIG. 3 is a flowchart of an example process for characterizing facies associations in a subsurface formation.

FIG. 4 is a flowchart of another example method for characterizing facies associations in a subsurface formation.

FIG. 5 illustrates hydrocarbon production operations that include field operations and computational operations, according to some implementations.

FIG. 6 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

This disclosure describes systems and processes for characterizing geological facies associations in a subsurface formation. Geological facies associations can be useful for understanding vertical and lateral changes in the geological and geophysical composition of the subsurface formation. In the oil and gas industry, facies associations can be used to build geological models of the subsurface formation and identify regions of the subsurface formation containing hydrocarbons. Based on these identified locations, one or more new wells can be drilled in the subsurface formation to access the hydrocarbons and produce the hydrocarbons to the surface in hydrocarbon production operations.

Openhole well logs, such as gamma-ray, resistivity, thermal neutron porosity, density, and acoustic logs, can provide valuable subsurface data to describe rock properties. Facies distributions and lithological variations within a reservoir or formation can be determined based on the well logs. Additionally, machine learning techniques can be used to distribute or populate the facies information in geological models in specified regions of the model corresponding to target areas of the subsurface formation.

Advanced machine learning models, for example, artificial neural networks (ANN) and random forest models, can be used to predict facies associations from well logs. The machine learning models can be trained to recognize patterns and relationships from training data including, for example, well logs labeled using facies associations determined from core samples and/or borehole images. Machine learning models can enable prediction of facies associations in regions of the subsurface formation where core descriptions or borehole images are unavailable. In some examples, considerable challenges can arise when predicting facies associations due to unusual log responses or similarity between responses in different logs. For example, high gamma-ray sands can generate log responses that can indicate mud facies rather than sandy facies.

To overcome these challenges, the systems and processes described herein use features engineered to consider the attributes of the stratigraphic sequence of the subsurface formation as a whole. Porosity-logs-driven features can be used in the machine learning model to differentiate between, for example, mud-composed facies associations and facies associations often accompanied with high gamma ray radioactive sands. Furthermore, the feature engineering process can derive additional features by executing a machine learning model to derive features that describe the sequence attributes of facies associations, e.g., whether the facies associations occur in bulky or laminated depositional trends. Other features can be used to describe the fraction of associated mud facies for a given sand facie in a given interval. The inclusion of the engineered features improves the accuracy of predicted facies associations as compared with predictions generated without using these features.

FIG. 1 illustrates a wireline operation 100 (e.g., a well logging operation) in which a wellbore 110 extends downhole from a wellhead 112. The wireline operation 100 can be performed to measure properties of a subsurface formation 124. Example properties include porosity, density, and sound velocity.

The wellbore 110 is a vertical wellbore but wireline operations can also be performed in other wellbores, for example, slanted or horizontal wellbores. In the wireline operation 100, the wellbore 110 penetrates through five layers 114, 116, 118, 120, 122 of the subsurface formation 124. A control truck 128 lowers a logging tool 132 (e.g., a porosity logging tool) down the wellbore 110 on a wireline 136.

The logging tool 132 is a string of one or more instruments with sensors operable to measure petrophysical properties of the subsurface formation 124. For example, logging tools can include resistivity logs, borehole image logs, porosity logs, density logs, or sonic logs. Resistivity logs measure the subsurface electrical resistivity, which is the ability to impede the flow of electric current. These logs can help differentiate between formations filled with salty waters (good conductors of electricity) and those filled with hydrocarbons (poor conductors of electricity). Porosity logs measure the fraction or percentage of pore volume in a volume of rock using acoustic or nuclear technology. Acoustic logs measure characteristics of sound waves propagated through the well-bore environment. Nuclear logs utilize nuclear reactions that take place in the downhole logging instrument or in the formation. Density logs measure the bulk density of a formation by bombarding it with a radioactive source and measuring the resulting gamma ray count after the effects of Compton scattering and photoelectric absorption. Sonic logs provide a formation interval transit time, which is typically a function of lithology and rock texture but particularly porosity. The logging tool includes a piezoelectric transmitter and receiver and the time taken for the sound wave to travel the fixed distance between the two is recorded as an interval transit time.

As the logging tool 132 travels downhole, measurements of formation properties are recorded to generate a well log. In the illustrated operation, the data are recorded at the control truck 128 in real-time. Real-time data are recorded directly against measured cable depth. In some well-logging operations, the data is recorded at the logging tool 132 and downloaded later. In this approach, the downhole data and depth data are both recorded against time. The two data sets are then merged using the common time base to create an instrument response versus depth log.

In the wireline operation 100, the well logging is performed on a wellbore 110 that has already been drilled. In some operations, well logging is performed in the form of logging while drilling techniques. In these techniques, the sensors are integrated into the drill string and the measurements are made in real-time, during drilling rather than using sensors lowered into a well after drilling.

Using a wireline coring tool, core samples can be obtained in addition to obtaining well logs. A core sample is a usually cylindrical piece of the subsurface formation that is removed by a special drill and brought to the surface. Core samples can be used to measure petrophysical properties of the subsurface formation such as grain size, porosity, permeability, and unconformity. Core samples can be taken from the sidewalls of a drilled well. When sidewall core samples are repeated along the length of the well, the properties measured from the core samples can be compared and correlated with well logging measurements.

FIG. 2 is a block diagram of an example system 200 for characterizing facies associations in a subsurface formation. System 200 includes a computer system 206 that includes a memory 208, processing device 210, bus system 212, and interface 214. The memory 208 includes a feature extraction engine 230, a sand analysis engine 232, a prediction engine 234, and a geological model 236. The computer system 206 can connect to a remote device 220 (e.g., to transmit or receive data) through a network 216. The network 216 can be a wired or wireless network. The computer system 206 is also communicatively coupled to a database 222. The database 222 can include data such as well log data 224, core sample data 226, and borehole image data 228.

The feature extraction engine 230 receives well log data 224 from the database 222. The well log data 224 can include, for example, gamma ray logs, density logs, thermal neutron porosity logs, sonic logs, thorium logs, potassium logs, and uranium logs. The feature extraction engine 230 extracts a first set of features based on the well log data 224. One example feature, delta-porosity (DPOR), that can be included in the first set of features includes a difference between measured thermal neutron porosity and computed density porosity. The computed density porosity is determined based on the density log. The computed density can be based on the density log assuming known fluid and grain densities. For example, assuming a clastic-dominated environment, the feature extraction engine can use a grain density of 2.65 g/cc and a fluid density of 1 g/cc (e.g., fresh water) to determine the computed density porosity. Another example feature, delta-porosity-sonic (DPORS), that can be included in the first set of features includes a difference between computed sonic porosity and computed density porosity. The computed sonic porosity is determined based on the sonic logs. The sonic porosity can be determined from the compressional slowness log, assuming, for example, a grain slowness of 52 μs/ft for a clastic-dominated environment, and a fluid slowness of 189 μs/ft (e.g., fresh water). The presence of muds in the subsurface formation can result in overestimating the sonic and thermal neutron porosities and underestimating the density porosity. Gamma ray based logs can be unreliable in differentiating mud and sand facies due to unusually high radioactivity of sand facies in some formations. The features included in the first set of features (e.g., DPOR and DPORS) can enable machine learning models to better separate sandy and muddy facies as compared with using solely gamma ray based logs or features.

The feature extraction engine 230 can also generate a second set of input features that describe the depositional settings of sand facies (e.g., whether the sand facies are bulky or laminated) and the fraction of mud facies associating the sand facies. The feature extraction engine 230 includes a machine learning model (e.g., a random forest model) to predict the presence of sand or mud facies along a given depth interval in the subsurface formation. The machine learning model receives as input well log data 224 and generates sand or mud facies classifications associated with the depths in the well log data 224. The sand or mud facies classification can be a binary classification of either sand or mud facie. The feature extraction engine 230 can send the generated sand or mud facies to the sand analysis engine 232 to generate the features for the second set of input features.

The machine learning model in the feature extraction engine 230 can be trained using the well log data labeled with the respective sand or mud facies as determined from the core sample data 226 or the borehole image data 228. The machine learning model in the feature extraction engine 230 can be trained in a similar manner as described below in reference to the prediction engine 234.

The sand analysis engine 232 receives the sand or mud facies classifications along depth intervals and determines the continuity of sand facies in the depth interval, the level of bulkiness or lamination of the sand facies, and the fraction of associating mud facies. The features generated by the sand analysis engine 232 consider the geological sequence of the subsurface formation. The sand analysis engine 232 can determine the mud fraction by, for example, determining the ratio of the total mud sample points to the total number of samples. A threshold value can be used to determine if a zone is muddy or not. For example, if the mud fraction is above the threshold value, then the zone is muddy. Alternatively, if the mud fraction is below the threshold value, then the zone is not muddy. The sand analysis engine 232 can determine the sand lamination by determining the length of sand facies before being cut by mud facies (e.g., sand continuity). The sand analysis engine 232 determines that regions where sand facies extend for a specified interval before being cut by mud are bulky sand facies, whereas regions where sand facies do not extend for the specified interval before being cut by mud are laminated sand facies. Categorical features (e.g., sand bulkiness/lamination) can be encoded to be processed by a machine learning model along with non-categorical features.

The prediction engine 234 receives input features from the feature extraction engine 230 and the sand analysis engine 232. The prediction engine 234 includes a machine learning model (e.g., a random forest model) to predict facies associations for the subsurface formation. Random forest models (classifiers) can robustly handle complex datasets producing accurate predictions. Random forest models use multiple decision trees, which helps avoid overfitting that can result from relying on single classifier approaches, such as decision tree or logistic regression. The classifications generated by random forest models can also be easily interpreted, which is advantageous in facies classification tasks where the resulting facies should follow solid geological and petrophysical sense. In some implementations, other machine learning architectures are used by the prediction engine 234, for example, ANNs, support vector machines, or decision tree models.

The prediction engine 234 can train the machine learning model using a training dataset. The training dataset includes the features derived from well logs for wells that have core sample data 226 (e.g., core descriptions) and/or borehole image data 228. The core sample data 226 and borehole image data 228 describe the lithofacies and composition of the subsurface formation. The features in the training dataset include the features output by the feature extraction engine 230 and the sand analysis engine 232. The features are labeled with the facies associations determined from the core sample data 226 or borehole image data 228. The training dataset can be split into a train set, a validation set, and a blind test set. For example, the training dataset can be split with 80% of the training data in the train set, 10% of the training data in the validation set, and 10% in the blind test set. In another example, 60% of the training data is in the train set, 20% in the validation set, and 20% in the blind test set. Other train, validation, test split ratios are also possible.

The prediction engine 234 can use, for example, a grid search method to tune the hyperparameters of the machine learning model to achieve a desired prediction performance. The prediction engine uses the train set and the validation set to tune the hyperparameters. The prediction performance can be measured using, for example, one or more scoring metrics such as the accuracy, recall and F1 scores. Once the desired prediction performance is achieved, the prediction engine 234 stops training the machine learning model. The final performance of the machine learning model can be determined using the blind test set.

The predicted facies associations generated by the prediction engine 234 are sent to the geological model 236. The geological model 236 includes a three-dimensional (3D) static model of the subsurface formation. The geological model 236 includes spatial distributions of the geological, geophysical, and/or petrophyscial properties in the subsurface formation. The predicted facies associations provide geological properties for regions in the subsurface formation to populate the geological model. The geological model 236 can be used to identify one or more locations in the subsurface formation that include hydrocarbons. One or more new wells can be drilled in the subsurface location at the one or more locations identified based on the geological model 236 and the predicted facies associations. Facies associations from cored wells, image logs and the prediction engine 234 can form a set of 1D building blocks for the 3D geological model. The predicted facies associations significantly reduce the uncertainty of the facies associations in the geological model 236 as compared to geological models based solely on a limited number of cored wells. The geological model 236 can use the set of 1D building blocks and 2D trends that are based on paleocurrent data and dominant sedimentary process to form the 3D geological model. The final product is a 3D geostatistical model where the facies can be populated using methods such as kriging or nearest neighbor.

A visualization of the predicted facies association and/or the geological model 236 can be rendered for display on display device 240. The visualization can include, for example, a 3D rendering of the subsurface formation with colors indicating the facies associations. The visualization can be used to validate the facies predictions (e.g., confirming that the facies associations make geological sense). The visualization can also aid in the placement and planning of wells in the subsurface.

FIG. 3 is a flowchart of an example process or method 300 for training a machine learning model to characterize geological facies in a subsurface formation. The method 300 can be implemented on a data processing system such as a computer or control system (e.g., computer system 206 or the computer system of FIG. 6).

The data processing system obtains openhole well logs 302 that undergo a feature engineering process 304 including two branches 306 and 308 prior to a machine learning training stage 310. The openhole well logs 302 include at least gamma ray logs, density logs, thermal neutron porosity logs, sonic logs, thorium logs, potassium logs, and uranium logs.

In the first branch 306 of the feature engineering process 304, the data processing system determines sonic porosity (SPHI) and density porosity (DPHI) (block 312). The SPHI and DPHI are based on the combinations and transformations of the openhole well logs 302. The data processing system uses the SPHI and DPHI logs to generate two features, DPOR and DPORS (block 314). The data processing system determines DPOR based on a difference between DPHI and a thermal neutron porosity log (NPHI). The data processing system determines DPORS based on a difference between SPHI and DPHI.

In the second branch 308 of the feature engineering process 304, the data processing system labels the openhole logs 302 as either sand facies or mud facies (block 316). The labels are based on borehole images 318 and core descriptions 320 that indicate facies associations 322 of the wells from which the openhole well logs 302 were obtained. The data processing system generates the categorical label to represent the sand facies or the mud facies for depth intervals of the openhole wells logs 302. The data processing system trains a random forest classifier 324 using the openhole well logs 302 labeled with the facies associations 322.

The data processing system processes the sand and mud facies labels using a sand analyzer 326. The sand analyzer 326 generates two features, sand bulkiness/lamination and mud content associating sand. The sand analyzer 326 can generate the two features as described above for the sand analysis engine 232.

The data processing system trains 310 a second random forest classifier 328 using a training dataset including the openhole well logs 302 and the engineered features DPOR, DPORS, sand bulkiness/lamination, and mud content associating sand. The training data for the random forest classifier 328 is labeled with individual facies associations derived from the borehole images 318 and core descriptions 320. The labels used by the random forest classifier 328 are different than the labels used by the random forest classifier 324. The data processing system can tune the hyperparameters of the random forest classifier 328 using, for example, a grid search method as described above. The tuned random forest classifier 330 can be used to generate predicted facies associations 332. After training the random forest classifiers 324 and 328, the data processing system can use openhole well logs from wells without core descriptions and borehole images to predict the facies associations using the random forest classifiers 324 and 328. The final predicted facies associations can have the same or fewer facies associations as the input data. For example, the predicted facies associations can have from 2 facies associations up to 8 or more facies associations or between 4 to 6 facies associations. The variability of the facies associations is determined based on the heterogeneity of the depositional environment. The depositional environment can be, for example, dominated by fluvial channels and fluvial channel fill facies associations. Alternatively, the depositional environment can have a more heterogenous assemblage such as tidal flats, tidal channels, barrier, washover fans and lagoon facies associations.

FIG. 4 is a flowchart for an example method 400 for characterizing geological facies in a subsurface formation. The method 400 can be implemented on a data processing system such as a computer or control system (e.g., computer system 206 or the computer system of FIG. 6).

The data processing system accesses 402 porosity well logs from one or more wells in a subsurface formation. The data processing system can access the porosity well logs from, for example, a hardware data storage device. The porosity well logs include data representing measurements taken from the subsurface formation during a wireline operation (e.g., wireline operation 100). In some implementations, the porosity well logs include gamma ray logs, density logs, thermal neutron porosity logs, sonic logs, thorium logs, potassium logs, and/or uranium logs.

The data processing system generates 404 a first set of input features derived from the porosity well logs. The input features include relative differences between the porosity well logs. For example, the first set of input features can include a feature representing a difference between measured thermal neutron porosity and computed density porosity, and/or a feature representing a difference between computed sonic porosity and computed density porosity.

The data processing system identifies 406 sand and mud facies along a depth of the one or more wells by executing a first machine learning model that receives as input the porosity well logs. The first machine learning model can be, for example, a random forest model.

The data processing system processes 408 the sand and mud facies to generate a second set of input features indicating depositional settings of the sand facies. The second set of input features can include, for example, a feature representing a ratio of sand facies to mud facies and a feature representing a continuity of sand facies along a depth of the one or more wells.

The data processing system predicts 410 facies associations for the one or more wells by executing a second machine learning model that receives the first set and the second set of input features as input. The second machine learning model can be a random forest model different than the first machine learning model. In some implementations, the second machine learning model receives additional inputs, for example, the porosity well logs or other well log data.

The data processing system identifies 412 one or more locations to place one or more new wells in the subsurface formation based on the predicted facies associations. The facies associations indicate regions in the subsurface formation with a higher hydrocarbon potential than other regions in the subsurface formation.

In some implementations, the data processing system builds a 3D static geological model of the subsurface formation using the predicted facies associations. The facies associations represent distinct characteristics of the geology of the subsurface formation. The 3D geological model includes a digital representation of the subsurface formation with corresponding spatial distributions of geological, geophysical, and/or petrophysical properties.

In some implementations, the data processing system controls drilling equipment to drill 414 one or more new wells at the identified one or more locations in the subsurface formation. For example, the data processing system can generate control commands for the drilling equipment (on-site or remotely) based on the predicted facies associations to drill the wells at the identified locations. The facies associations indicate, for example, rock properties of the subsurface that can be used to determine drilling parameters (e.g., drilling speed, rate of penetration, etc.).

The data processing system can train the first and second machine learning models using training data. The data processing system obtains well logs and core sample data from one or more wells in the subsurface formation. In some implementations, the data processing system obtains borehole images from the one or more wells.

The data processing system forms a first training data set that includes the well logs as input features. The data processing system can label the well logs with first labels that include sand and mud facies determined based on the core sample data and/or borehole images. The data processing system trains the first machine learning model using the first training dataset. The data processing system processes the first labels to generate depositional setting features indicating depositional settings of the sand facies.

The data processing system generates a second training dataset that includes porosity derived features and the depositional setting features. The second training dataset can also include the well logs. The data processing system labels the second training dataset with facies associations determined from the core samples and/or borehole images. The data processing system trains the second machine learning model using the second training dataset.

FIG. 5 illustrates hydrocarbon production operations 500 that include both one or more field operations 510 and one or more computational operations 512, which exchange information and control exploration for the production of hydrocarbons. In some implementations, outputs of techniques of the present disclosure (e.g., the process 300 or method 400) can be performed before, during, or in combination with the hydrocarbon production operations 500, specifically, for example, either as field operations 510 or computational operations 512, or both.

Examples of field operations 510 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 510. 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 510 and responsively triggering the field operations 510 including, for example, generating plans and signals that provide feedback to and control physical components of the field operations 510. Alternatively, or in addition, the field operations 510 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 510 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 512 include one or more computer systems 520 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 512 can be implemented using one or more databases 518, which store data received from the field operations 510 and/or generated internally within the computational operations 512 (e.g., by implementing the methods of the present disclosure) or both. For example, the one or more computer systems 520 process inputs from the field operations 510 to assess conditions in the physical world, the outputs of which are stored in the databases 518. For example, seismic sensors of the field operations 510 can be used to perform a seismic survey to map subterranean 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 512 where they are stored in the databases 518 and analyzed by the one or more computer systems 520.

In some implementations, one or more outputs 522 generated by the one or more computer systems 520 can be provided as feedback/input to the field operations 510 (either as direct input or stored in the databases 518). The field operations 510 can use the feedback/input to control physical components used to perform the field operations 510 in the real world.

For example, the computational operations 512 can process the seismic data to generate three-dimensional (3D) maps of the subsurface formation. The computational operations 512 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 512 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 520 can update the 3D maps of the subsurface formation as information from one exploration well is received and the computational operations 512 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 512 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 512 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 512, 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 modeling 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. 6 is a block diagram of an example computer system 600 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 602 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 602 can include input devices such as keypads, keyboards, and touch screens that can accept user information. Also, the computer 602 can include output devices that can convey information associated with the operation of the computer 602. 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 602 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 602 is communicably coupled with a network 630. In some implementations, one or more components of the computer 602 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 602 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 602 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 602 can receive requests over network 630 from a client application (for example, executing on another computer 602). The computer 602 can respond to the received requests by processing the received requests using software applications. Requests can also be sent to the computer 602 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 602 can communicate using a system bus 603. In some implementations, any or all of the components of the computer 602, including hardware or software components, can interface with each other or the interface 604 (or a combination of both), over the system bus 603. Interfaces can use an application programming interface (API) 612, a service layer 613, or a combination of the API 612 and service layer 613. The API 612 can include specifications for routines, data structures, and object classes. The API 612 can be either computer-language independent or dependent. The API 612 can refer to a complete interface, a single function, or a set of APIs.

The service layer 613 can provide software services to the computer 602 and other components (whether illustrated or not) that are communicably coupled to the computer 602. The functionality of the computer 602 can be accessible for all service consumers using this service layer. Software services, such as those provided by the service layer 613, 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 602, in alternative implementations, the API 612 or the service layer 613 can be stand-alone components in relation to other components of the computer 602 and other components communicably coupled to the computer 602. Moreover, any or all parts of the API 612 or the service layer 613 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 602 includes an interface 604. Although illustrated as a single interface 604 in FIG. 6, two or more interfaces 604 can be used according to particular needs, desires, or particular implementations of the computer 602 and the described functionality. The interface 604 can be used by the computer 602 for communicating with other systems that are connected to the network 630 (whether illustrated or not) in a distributed environment. Generally, the interface 604 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 630. More specifically, the interface 604 can include software supporting one or more communication protocols associated with communications. As such, the network 630 or the interface's hardware can be operable to communicate physical signals within and outside of the illustrated computer 602.

The computer 602 includes a processor 605. Although illustrated as a single processor 605 in FIG. 6, two or more processors 605 can be used according to particular needs, desires, or particular implementations of the computer 602 and the described functionality. Generally, the processor 605 can execute instructions and can manipulate data to perform the operations of the computer 602, including operations using algorithms, methods, functions, processes, flows, and procedures as described in the present disclosure.

The computer 602 also includes a database 606 that can hold data for the computer 602 and other components connected to the network 630 (whether illustrated or not). For example, database 606 can be an in-memory, conventional, or a database storing data consistent with the present disclosure. In some implementations, database 606 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 602 and the described functionality. Although illustrated as a single database 606 in FIG. 6, 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 602 and the described functionality. While database 606 is illustrated as an internal component of the computer 602, in alternative implementations, database 606 can be external to the computer 602.

The computer 602 also includes a memory 607 that can hold data for the computer 602 or a combination of components connected to the network 630 (whether illustrated or not). Memory 607 can store any data consistent with the present disclosure. In some implementations, memory 607 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 602 and the described functionality. Although illustrated as a single memory 607 in FIG. 6, two or more memories 607 (of the same, different, or combination of types) can be used according to particular needs, desires, or particular implementations of the computer 602 and the described functionality. While memory 607 is illustrated as an internal component of the computer 602, in alternative implementations, memory 607 can be external to the computer 602.

The application 608 can be an algorithmic software engine providing functionality according to particular needs, desires, or particular implementations of the computer 602 and the described functionality. For example, application 608 can serve as one or more components, modules, or applications. Further, although illustrated as a single application 608, the application 608 can be implemented as multiple applications 608 on the computer 602. In addition, although illustrated as internal to the computer 602, in alternative implementations, the application 608 can be external to the computer 602.

The computer 602 can also include a power supply 614. The power supply 614 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 614 can include power-conversion and management circuits, including recharging, standby, and power management functionalities. In some implementations, the power-supply 614 can include a power plug to allow the computer 602 to be plugged into a wall socket or a power source to, for example, power the computer 602 or recharge a rechargeable battery.

There can be any number of computers 602 associated with, or external to, a computer system containing computer 602, with each computer 602 communicating over network 630. 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 602 and one user can use multiple computers 602.

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 embodiments 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 embodiments are within the scope of the following claims.

Examples

In an example implementation, a method for characterizing geological facies in a subsurface formation includes accessing, from a hardware storage device by a data processing system, porosity well logs from one or more wells in a subsurface formation; generating, by the data processing system, a first set of input features derived from the porosity well logs, the input features including relative differences between the porosity well logs; identifying, by the data processing system, sand and mud facies along a depth of the one or more wells by executing a first machine learning model that receives as input the porosity well logs; processing, by the data processing system, the sand and mud facies to generate a second set of input features indicating depositional settings of the sand facies; predicting, by the data processing system, facies associations for the one or more wells by executing a second machine learning model that receives the first set and the second set of input features as input; and identifying, by the data processing system, one or more locations to place one or more new wells in the subsurface formation based on the predicted facies associations, the facies associations indicating regions in the subsurface formation with a higher hydrocarbon potential than other regions in the subsurface formation.

An aspect combinable with the example implementations includes generating control commands to control drilling equipment to drill the one or more new wells at the one or more identified locations.

Another aspect combinable with one, some, or all of the previous aspects includes building a three dimensional static geological model of the subsurface formation using the predicted facies associations, where the facies associations represent distinct characteristics of the geology of the subsurface formation.

In another aspect combinable with one, some, or all of the previous aspects, the first set of input features includes a feature representing a difference between measured thermal neutron porosity and computed density porosity, and a feature representing a difference between computed sonic porosity and computed density porosity.

In another aspect combinable with one, some, or all of the previous aspects, the second set of input features includes a feature representing a ratio of sand facies to mud facies and a feature representing a continuity of sand facies along a depth of the one or more wells.

Another aspect combinable with one, some, or all of the previous aspects includes obtaining well logs and core samples from one or more wells in the subsurface formation; forming a first training data set including the well logs as input features, the well logs labeled with first labels including sand and mud facies based on the core samples; training the first machine learning model using the first training dataset; processing the first labels to generate depositional setting features indicating depositional settings of the sand facies; generating a second training dataset, the second training dataset including porosity features and the depositional setting features, the second training dataset labeled with facies associations determined from the core samples; and training the second machine learning model using the second training dataset.

In another aspect combinable with one, some, or all of the previous aspects, the first and second machine learning models are each random forest models.

In another example implementation, a system for characterizing geological facies in a subsurface formation includes one or more processors; a hardware storage device; and a computer readable medium storing instructions that when executed cause the one or more processors to perform operations including accessing, from the hardware storage device, porosity well logs from one or more wells in a subsurface formation; generating a first set of input features derived from the porosity well logs, the input features including relative differences between the porosity well logs; identifying sand and mud facies along a depth of the one or more wells by executing a first machine learning model that receives as input the porosity well logs; processing the sand and mud facies to generate a second set of input features indicating depositional settings of the sand facies; and predicting facies associations for the one or more wells by executing a second machine learning model that receives the first set and the second set of input features as input; and identifying one or more locations to place one or more new wells in the subsurface formation based on the predicted facies associations, the facies associations indicating regions in the subsurface formation with a higher hydrocarbon potential than other regions in the subsurface formation.

In an aspect combinable with the example implementation, the instructions include generating control commands to control drilling equipment to drill the one or more new wells at the one or more identified locations.

In another aspect combinable with one, some, or all of the previous aspects, the instructions include building a three dimensional static geological model of the subsurface formation using the predicted facies associations, where the facies associations represent distinct characteristics of the geology of the subsurface formation.

In another aspect combinable with one, some, or all of the previous aspects, the first set of input features includes a feature representing a difference between measured thermal neutron porosity and computed density porosity, and a feature representing a difference between computed sonic porosity and computed density porosity.

In another aspect combinable with one, some, or all of the previous aspects, the second set of input features includes a feature representing a ratio of sand facies to mud facies and a feature representing a continuity of sand facies along a depth of the one or more wells.

In another aspect combinable with one, some, or all of the previous aspects, the instructions include obtaining well logs and core samples from one or more wells in the subsurface formation; forming a first training data set including the well logs as input features, the well logs labeled with first labels including sand and mud facies based on the core samples; training the first machine learning model using the first training dataset; processing the first labels to generate depositional setting features indicating depositional settings of the sand facies; generating a second training dataset, the second training dataset including porosity features and the depositional setting features, the second training dataset labeled with facies associations determined from the core samples; and training the second machine learning model using the second training dataset.

In another aspect combinable with one, some, or all of the previous aspects, the first and second machine learning models are each random forest models.

In another example implementation, one or more non-transitory, machine-readable storage devices storing instructions for characterizing geological facies in a subsurface formation, the instructions being executable by one or more processors to cause performance of operations including accessing, from a hardware storage device, porosity well logs from one or more wells in a subsurface formation; generating a first set of input features derived from the porosity well logs, the input features including relative differences between the porosity well logs; identifying sand and mud facies along a depth of the one or more wells by executing a first machine learning model that receives as input the porosity well logs; processing the sand and mud facies to generate a second set of input features indicating depositional settings of the sand facies; predicting facies associations for the one or more wells by executing a second machine learning model that receives the first set and the second set of input features as input; and identifying one or more locations to place one or more new wells in the subsurface formation based on the predicted facies associations, the facies associations indicating regions in the subsurface formation with a higher hydrocarbon potential than other regions in the subsurface formation.

In an aspect combinable with the example implementation, the instructions include generating control commands to control drilling equipment to drill the one or more new wells at the one or more identified locations.

In another aspect combinable with one, some, or all of the previous aspects, the instructions include building a three dimensional static geological model of the subsurface formation using the predicted facies associations, where the facies associations represent distinct characteristics of the geology of the subsurface formation.

In another aspect combinable with one, some, or all of the previous aspects, the first set of input features includes a feature representing a difference between measured thermal neutron porosity and computed density porosity, and a feature representing a difference between computed sonic porosity and computed density porosity.

In another aspect combinable with one, some, or all of the previous aspects, the second set of input features includes a feature representing a ratio of sand facies to mud facies and a feature representing a continuity of sand facies along a depth of the one or more wells.

In another aspect combinable with one, some, or all of the previous aspects, the instructions include obtaining well logs and core samples from one or more wells in the subsurface formation; forming a first training data set including the well logs as input features, the well logs labeled with first labels including sand and mud facies based on the core samples; training the first machine learning model using the first training dataset; processing the first labels to generate depositional setting features indicating depositional settings of the sand facies; generating a second training dataset, the second training dataset including porosity features and the depositional setting features, the second training dataset labeled with facies associations determined from the core samples; and training the second machine learning model using the second training dataset.

In another aspect combinable with one, some, or all of the previous aspects, the first and second machine learning models are each random forest models.