Systems and methods for optimizing injection wells

Abstract

Implementations described and claimed herein provide systems and methods for optimizing a development plan for one or more injection wells. Systems and methods disclosed herein include obtaining reservoir data using at least one of a computing device, one or more sensors, or one or more databases; generating reservoir flow simulation data using the reservoir data, the reservoir flow simulation data including one or more subsurface flows of a hydrocarbon reservoir; and generating forecast data for the one or more injection wells by inputting the reservoir flow simulation data for the one or more subsurface flows into one or more machine learning models, the one or more machine learning models trained using historical well training data and reservoir physics data.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application is related to U.S. Provisional Application No. 63 / 766,182 , entitled “Robust Water-Alternating-Gas (WAG) Well Level Forecasting” filed on March 3, 2025, which is specifically incorporated by reference herein in its entirety.TECHNICAL FIELD

[0002] Aspects of the present disclosure relate generally to systems and methods for the optimization of development plans for natural resource production, and more particularly, to optimization of development plans of injection wells in oil, gas, and water production systems.BACKGROUND

[0003] Injection wells are used in the oil industry to enhance resource production in hydrocarbon reservoirs. One technique that can be performed in injection wells is water alternating gas (WAG) technique. This technique involves alternating between water and gas injection into the hydrocarbon reservoir in order to help displace resources, such as oil, gas, and / or water, from the reservoir. It is difficult to accurately and efficiently forecast reservoirs and injection wells for applications using WAG due to the complex and large amount of data required.SUMMARY

[0004] Implementations described and claimed herein address the foregoing problems by providing systems and methods for optimizing development plans for injection wells. The systems and methods described herein efficiently and accurately forecast reservoirs, injection wells, and natural resource production, such as gas, oil, and water. In an implementation, the injection wells use a WAG technique for enhancing the natural resource production.

[0005] In one implementation, systems and methods are provided for rapid enhanced modeling combined with reservoir physics, thus creating a highly automated approach for accurate prediction of production fields and injection wells that utilize WAG injection techniques. In some implementations, the disclosed technology generates optimized development plans of injection wells such as, future WAG schedules and / or operations in order to maximize resource production. In one implementation, the disclosed technology provides a tool to produce accurate characteristics for wells and / or reservoirs in order to predict the effects of WAG techniques implemented using injection wells.

[0006] In one implementation, the methods and systems disclosed herein enable physics-based, fast, efficient, and reliable forecasting of WAG-type production from a well level to a reservoir level. The systems and methods disclosed herein provide optimization of injection activities and advanced production strategies. In some implementations, uncertainty quantification in forecasting is performed via an ensemble of models. In an implementation, enhanced forecasting predictions including reservoir physics enable optimal reservoir management and planning​. In an implementation, the systems and methods disclosed herein include improved forecasting for WAG systems and processes that enable quality and reliability for improved matching and forecasting in wells.

[0007] In an implementation, the methods and systems allow for rapid and reliable updates to the model and / or are configured to perform automated variance analysis for improved optimization and management strategies. In some implementations, the ability to quickly predict well characteristics and / or resource production from different scenarios allows for optimized development plans and / or increased forecasting in order to determine an optimal result. It is with these observations in mind, among others, that various implementations of the present disclosure were conceived and developed.

[0008] In some aspects, the techniques described herein relate to a system for forecasting reservoirs, the system including: a processing system in communication with a computing device, one or more sensors and one or more databases over a network, the processing system receiving reservoir data from at least one of the computing device, the one or more sensors, or the one or more databases; a reservoir flow simulation system generating reservoir flow simulation data for one or more subsurface flows of a reservoir using the reservoir data; and a forecast system generating forecast data based on the reservoir flow simulation data and using one or more machine learning models, the one or more machine learning models trained using reservoir physics and well data acquired during at least one of an oil production process, a gas production process, a water production process, a gas injection process, or a water injection process.

[0009] In some aspects, the techniques described herein relate to a system, further including an output system generating one or more graphical representations using the forecast data. In some aspects, the techniques described herein relate to a system, wherein the one or more graphical representations is modifiable based on user input. In some aspects, the techniques described herein relate to a system, wherein the reservoir flow simulation system generates the reservoir flow simulation data at least in part using radial basis function (RBF). In some aspects, the techniques described herein relate to a system, wherein the one or more machine learning models include an Ensemble Smoother using Multiple Data Assimilation and an Ensemble Kalman Filter.

[0010] In some aspects, the techniques described herein relate to a method for forecasting, the method including: obtaining reservoir data using at least one of a computing device, one or more sensors, or one or more databases; generating reservoir flow simulation data for one or more subsurface flows of a hydrocarbon reservoir using the reservoir data; and generating forecast data for one or more wells by inputting the reservoir flow simulation data for the one or more subsurface flows into one or more machine learning models, the one or more machine learning models trained using well training data and reservoir physics data, the well training data based on at least one of an oil production process, a gas production process, a water production process, a gas injection process, or a water injection process in the hydrocarbon reservoir.

[0011] In some aspects, the techniques described herein relate to a method, wherein the one or more machine learning models is updated at least in part by performing automated variance analysis of the forecast data. In some aspects, the techniques described herein relate to a method, wherein the forecast data includes at least one of oil responsivity, gas fit forecasting, water fit forecasting, and bottom hole pressure (BHP) forecasting. In some aspects, the techniques described herein relate to a method, further including generating output data using the forecast data.

[0012] In some aspects, the techniques described herein relate to a method, wherein the output data includes one or more graphical representations of well-level characteristics, the well-level characteristics including at least one of saturation, pressure, and responsivity. In some aspects, the techniques described herein relate to a method, further including generating backcasting information related to the forecast data to assess reliability of the forecast data. In some aspects, the techniques described herein relate to a method, further including identifying conduits between one or more individual wells of the hydrocarbon reservoir.

[0013] In some aspects, the techniques described herein relate to a method, wherein the forecast data includes instructions to optimize at least one of the oil production process, the gas production process, the water production process, the gas injection process, or the water injection process. In some aspects, the techniques described herein relate to one or more tangible non-transitory computer-readable storage media storing computer-executable instructions for performing a computer process on a computing system, the computer process including: obtaining reservoir data in a hydrocarbon reservoir from at least one of a computing device, one or more sensors, or one or more databases; generating reservoir simulation data using the reservoir data; generating forecast data for one or more wells based on the reservoir simulation data and using one or more machine learning models, the one or more machine learning models trained using well data acquired during at least one of an oil production process, a gas production process, a water production process, a gas injection process, or a water injection process and reservoir physics; and generating at least one visual dashboard using the forecast data.

[0014] In some aspects, the techniques described herein relate to one or more tangible non-transitory computer-readable storage media, wherein the one or more machine learning models is updated at least in part by performing automated variance analysis of the forecast data. In some aspects, the techniques described herein relate to one or more tangible non-transitory computer-readable storage media, wherein the forecast data includes at least one of oil responsivity, gas fit forecasting, water fit forecasting, and bottom hole pressure (BHP) forecasting.

[0015] In some aspects, the techniques described herein relate to one or more tangible non-transitory computer-readable storage media, further including generating output data using the forecast data, wherein the output data includes one or more graphical representations of well-level characteristics, the well-level characteristics including at least one of saturation, pressure, and responsivity. In some aspects, the techniques described herein relate to one or more tangible non-transitory computer-readable storage media, further including generating backcasting information related to the forecast data to assess reliability of the forecast data.

[0016] In some aspects, the techniques described herein relate to one or more tangible non-transitory computer-readable storage media, further including identifying conduits between one or more individual wells of the hydrocarbon reservoir. In some aspects, the techniques described herein relate to one or more tangible non-transitory computer-readable storage media, wherein the forecast data includes instructions to optimize at least one of the oil production process, the gas production process, the water production process, the gas injection process, or the water injection process.

[0017] Other implementations are also described and recited herein. Further, while multiple implementations are disclosed, still other implementations of the presently disclosed technology will become apparent to those skilled in the art from the following detailed description, which shows and describes illustrative implementations of the presently disclosed technology. As will be realized, the presently disclosed technology is capable of modifications in various implementations, all without departing from the spirit and scope of the presently disclosed technology. Accordingly, the drawings and detailed description are to be regarded as illustrative in nature and not limiting.BRIEF DESCRIPTION OF THE DRAWINGS

[0018] FIG. 1 illustrates an example system for optimizing development plans for injection wells.

[0019] FIG. 2 illustrates an example processing system for optimizing development plans for injection wells.

[0020] FIG. 3 illustrates an example computing system that may implement various aspects of the systems and methods discussed herein.

[0021] FIG. 4A illustrates an example graphical representation of an oil phase training graph.

[0022] FIG. 4B illustrates an example graphical representation comparing predicted vs actual oil phase modeling.

[0023] FIG. 5A illustrates an example graphical representation of a gas phase training graph.

[0024] FIG. 5B illustrates an example graphical representation comparing the predicted vs actual gas phase modeling.

[0025] FIG. 6A illustrates an example graphical representation of a water phase training graph.

[0026] FIG. 6B illustrates an example graphical representation of a comparison between predicted vs actual water phase modeling.

[0027] FIG. 7A illustrates an example graphical representation of a gas injection phase training graph.

[0028] FIG. 7B illustrates an example graphical representation of a water injection phase training graph.

[0029] FIG. 8A illustrates an example graphical representation of a full field oil fit graph.

[0030] FIG. 8B illustrates an example graphical representation of a full field gas fit graph.

[0031] FIG. 9A illustrates an example graphical representation of a full field pressure overlay.

[0032] FIG. 9B illustrates an example graphical representation of a full field oil saturation overlay.

[0033] FIG. 9C illustrates an example graphical representation of a full field oil responsivity overlay.

[0034] FIG. 9D illustrates an example graphical representation of a full field gas responsivity overlay.

[0035] FIG. 10A illustrates an example graphical representation of a full field oil responsivity before lateral update.

[0036] FIG. 10B illustrates an example graphical representation of a full field oil responsivity after lateral update.

[0037] FIG. 11A illustrates an example graphical representation of a full field oil saturation before update.

[0038] FIG. 11B illustrates an example graphical representation of a full field oil saturation after update.

[0039] FIG. 12A illustrates an example graphical representation of a well oil forecast for multiple producing wells.

[0040] FIG. 12B illustrates an example graphical representation of a well oil forecast and bhp forecast for a single well.

[0041] FIG. 12C illustrates an example graphical representation of average BHP for all wells.

[0042] FIG. 13A illustrates an example graphical representation of an example conduit depicting gas injection rates for an injection well.

[0043] FIG. 13B illustrates an example graphical representation of an example conduit depicting gas production rate for a producing well.

[0044] FIG. 13C illustrates an example graphical representation of an example conduit depicting gas rate match between wells.

[0045] FIG. 13D illustrates an example graphical representation of an example reservoir overlay showing back test gas responsivity.

[0046] FIG. 14A illustrates an example graphical representation of an example oil responsivity forecasting in a single well.

[0047] FIG. 14B illustrates an example graphical representation of an example BHP forecasting in a single well.

[0048] FIG. 14C illustrates an example graphical representation of an example oil saturation forecasting in a single well.

[0049] FIG. 14D illustrates an example graphical representation of an example gas fit forecasting in a single well.

[0050] FIG. 14E illustrates an example graphical representation of an example water fit forecasting in a single well.

[0051] FIG. 15 illustrates example operations for optimizing a development plan for injection wells using the various systems described herein. .DETAILED DESCRIPTION

[0052] Implementations of the present disclosure involve systems and methods for extracting natural resources from reservoirs using WAG methods. Systems and methods disclosed herein provide physics-based approaches to generate and quantitatively optimize different scenarios in order to predict a maximum, quantified, predictable, and risk-adjusted return with regards to resource production. In one implementation, millions of operational scenarios that simulate WAG activities may be generated and efficiently analyzed (e.g., increased injection, resource production, etc.) in order to provide optimal forecast information.

[0053] In one implementation, the disclosed technology performs using one or more machine learning model(s), requiring minimal set up while running efficiently. The disclosed technology is easy to set up and maintain and can be updated frequently whenever new data is available. In some aspects, the disclosed systems and methods offer excellent long-term predictive capacity and physically realistic responses, even when available reservoir data is missing and / or suboptimal.

[0054] FIG. 1 illustrates an example system 100 that may implement various systems and methods discussed herein. The system 100 may include a processing system 102 configured to communicate with one or more user devices 104, one or more servers 106, one or more sensors 108, and / or one or more databases 110 via a network 112.

[0055] As depicted in FIG. 1, a network 112 may be used by one or more computing devices or data storage devices for implementing the systems and methods for optimization of development of an injection well. In one implementation, various components of the system 100, one or more user devices 104, one or more servers 106, one or more sensors 108, one or more databases 110, and / or other network components or computing devices described herein are communicatively connected to the network 112.

[0056] The user device 104 can be a terminal, personal computer, smartphone, tablet, laptop, workstation, or other personal computing device used by an individual (e.g., the operator) to receive notifications and enter data via one or more input and / or output systems. These systems may be part of or separate from the user device 104. For instance, the operator can input data related to one or more wells into the processing system 102 through interactive user interfaces on the user device 104. In some cases, the user device 104 may output data such as display plots, analytical information, forecast data, optimized development plans, notifications, and alerts using graphical user interfaces, like those illustrated in FIGS. 4A–14E. The user interface may also be used to interact with data, including graphical representations from FIGS. 4A–14E, training data, forecasts, development plans, production maps, and variances between different data sets, as non-limiting examples.

[0057] In some examples, the server 106 may host the system. Additionally or alternatively, the server 106 may host a website or an application that users may visit to access the system 100. The server 106 may be a single server, a plurality of servers with each server being a physical server or a virtual machine, or a collection of physical servers and virtual machines. In another implementation, a cloud hosts one or more components of the system. The system 100, the user devices 104, the server 106, and other resources connected to the network 112 may access one or more additional servers for access to one or more websites, applications, web services, interfaces, etc. that are used for resource development and / or generating development plan(s). In one implementation, the server 106 may also host a search engine that the system uses for accessing and modifying information, including without limitation, reservoir data, parameters, a user interface, etc.

[0058] In one implementation, the one or more databases 110 may be used to store reservoir data, such as structured and unstructured data captured from disparate sources associated with wells, reservoir(s), etc. Some of the data may be captured directly, for example using one or more sensors 108 deployed at wells, reservoir(s), etc. Such data may include historical information obtained via the one or more sensors 108 and / or other sources. Such data may include core, well log, fluid sampling, production rates (e.g., resource produced per unit time), injection rates (e.g., tracking the volumes of water and gas injected), pressure data, location data, top hole pressure, bottom hole pressure, reservoir pressure, temperature, fluid flow rates, etc. Additionally or alternatively, some of the data may be obtained from public sources in accordance with regulatory requirements. In some examples, the reservoir data may include data input or otherwise obtained via an interface, at the direction of one or more computing units, and / or the like. In some examples, the one or more databases 110 may be used to store training data, forecast data, production plans, injection plans, development plans, optimization, input data, and / or output data.

[0059] In some examples, at least a portion of the data is obtained by one or more sensors 108 disposed in a well or at a surface during well tests, reservoir tests, and / or well operations (e.g., oil production, gas production, water production, gas injection, water injection, performance of a WAG technique, etc.). For instance, pressure, temperature, and / or flow rates may be continuously monitored throughout operation of a well using one or more pressure sensors, one or more temperature sensors, and / or one or more flow rate sensors.

[0060] The system 100 is configured to receive user input via one or more input systems using, for example, the user device 104 to input text, audio, and / or interact with an interactive user interface displayed on one or more output systems of, for example, the user device 104. In an implementation, the reservoir data is received directly from the one or more sensors 108 via a wired or wireless connection. As illustrated in greater detail below, any and / or all of the processing system 102, the user device(s) 104, and the one or more databases 110 may, in some instances, be special-purpose computing devices configured to perform specific functions.

[0061] FIG. 2 illustrates the processing system 102 which can include one or more computing devices (e.g., servers, routers, user interface devices, internet telephony computing device, and the like) that store and / or retrieve data in the one or more databases 110, generate user interfaces, etc. The processing system 102 includes a reservoir simulation system 202, a forecast system 204, one or more memory device(s) 206, an output system 208, and / or communication interface(s) 210. The communication interface(s) 210 is able to communicate with the one or more input systems and one or more output systems of one or more computing devices via the network(s) 112. For instance, the communication interface(s) 210 may be a network interface configured to support communication between the processing system 102 and the network(s) 112.

[0062] The processing system 102 can be configured to execute one or more algorithms to perform the techniques, as discussed in greater detail below. For instance, the one or more algorithms can include one or more machine learning algorithms. The one or more machine learning algorithms can be one or more models, such as, for example, a linear regression model, an unsupervised neural network model, gradient boosted trees, random decision forest, etc. The one or more machine learning models may be built from historical data associated with natural resource reservoirs and / or events for an area, such as a production field that includes natural resource reservoirs, and may be stored, for example, at one or more databases. Thus, the one or more machine learning models leverage historical data to generate optimized development plans. The processing system 102 can be configured to monitor and store (e.g., with appropriate permissions) data for further analysis and / or training of the machine learning model(s). In an implementation, the processing system 102 is configured to transmit data related to the machine learning model(s) to another computing device or database, such as the one or more databases 110. In an implementation, the processing system 102 is associated with an organization or entity.

[0063] In an implementation, the processing system 102 includes instructions that direct and / or cause the reservoir simulation system 202 to execute processing techniques on reservoir data to generate one or more reservoir simulations using the reservoir data. The reservoir simulation system 202 may provide the one or more reservoir simulations (e.g., reservoir simulation data) to the forecast system 204 and / or the output system 208.

[0064] The reservoir simulation system 202 may use a small amount of reservoir data available to generate one or more reservoir models. The one or more reservoir models may be a Low order continuous scale simulation (LOCSIM) model, which is a mixed domain decomposition method for comprehensive modeling of connected fault vectors. The LOCSIM model allows modeling flows with open, partially open and closed faults, and / or a dual point scheme-based no-flow boundaries. The one or more models may utilize a radial basis function (RBF), which is a real-valued function 𝜑 whose value depends only on the distance between the input and some fixed point, either the origin, so that 𝜑 ( 𝑥 )= 𝜑 ^(‖𝑥‖), or some other fixed point 𝑐 , called a center, so that 𝜑 ( 𝑥 )= 𝜑 ^(‖𝑥−𝑐‖). Any function 𝜑 that satisfies the property 𝜑 ( 𝑥 )= 𝜑 ^(‖𝑥‖) is a radial function. The RBFs can be used to approximate solutions for areas where data is not available (e.g., at some well locations, production sites, and / or injection sites). The reservoir simulation data may be one or more models of a reservoir and / or reservoir properties. In some examples, the reservoir simulation data may include one or more subsurface flows of a reservoir or reservoir field (e.g., reservoir flow simulation data). In some examples, the reservoir simulation data may include subsurface flows for more than one reservoir and / or reservoir field.

[0065] The reservoir simulation data may be used by the forecast system 204 to create a forecast and / or optimized development plan for one or more wells, reservoirs, etc. For example, the forecast system 204 may apply one or more machine learning models to the reservoir simulation data in order to produce forecast data. The forecast system 204 may provide forecast data generated to the output system for generating one or more optimized development plans, one or more visual dashboard, one or more graphical representations, etc.

[0066] The forecast system 204 utilizes reservoir simulation data from the reservoir simulation system 202, a data physics engine, and an ensemble-based approach with multiple realizations (MR). The data physics engine combines machine learning and physics models to simulate reservoir properties while maintaining realistic physics constraints. Reservoir properties are input into the engine to generate predicted properties, such as subsurface flow modeling. Discrepancies are quantitatively captured using methods like Ensemble Smoothing with Multiple Data Assimilation (ESMDA) and an Ensemble Kalman filter (EnKF) to update uncertainty based on variances between forecast and actual data. The system ensures efficient data smoothing by executing smoothing functions multiple times using ESMD and / or EnKF. The data physics engine, updated with a minimized vector RBF representation, refines uncertainty through an ensemble-based MR process. Flow equations are solved in each realization with minimal solution points and approximated using continuous functions for a high-resolution model with reduced uncertainty.

[0067] The forecast system 204 generates solutions approximated with continuous functions for high-resolution development plans and WAG models for production forecasts. The executed processes are automated with minimal or no user input and integrated for rapid model calibration and forecasting, allowing recalibration with new data inputs. Embedding the ESMDA / EnKF process accounts for multiple uncertainties in the data. This structured approach ensures that the forecast system 204 effectively manages uncertainty and enhances model accuracy through integrated processes and advanced algorithms.

[0068] Training involves inputting parameters like resource production or injection rates. For example, oil, water, and gas production and injection rates during WAG cycles may be input. The training may begin with a larger dataset followed by a limited dataset for back-testing, using ESMDA iterations for preconditioning and EnKF. The number of training iterations can be customized, ranging from 1-10, 1-50, 1-100, as non-limiting examples. The forecast system 204 may generate commands for injection or resource production based on an optimized development plan created using the forecast data.

[0069] The output system 208 may execute processing techniques to output the development plan. In some examples, the output of the development plan may include visual representations, such as plots, maps, pressure maps, bar graphs, or other graphical illustrations that may be provided via user interface on for example, a computing device, such as user device 104. The output of the development may be modified by a user in order to input new data and / or update the output.

[0070] Data may be exchanged sequentially and / or simultaneously among the reservoir simulation system 202, the forecast system 204, and / or the output system 208 so that the systems may coordinate while executing processing techniques. The reservoir simulation system 202 and / or the forecast system 204 can be configured to execute one or more algorithms to perform the techniques. For instance, the one or more algorithms can include one or more machine learning algorithms. The one or more machine learning algorithms can be one or more models, such as, for example, a linear regression model, an unsupervised neural network model, gradient boosted trees, random decision forest, etc. The one or more machine learning models may be built from well data, which can be historical data associated with oil, water, and gas production systems or water and gas injection systems that is stored, for example, at one or more databases 110. In some implementations, the well data includes water-cut (water content in produced fluid), gas-oil ratio (GOR) (ratio of gas produced to oil produced), temperature of the produced fluids (e.g., to identify potential thermal effects or changes in reservoir conditions), fluid responsivity, saturation levels, cumulative production, oil viscosity (resistance of oil to flow), etc. In an implementation, resource production (e.g., gas, oil, water, etc.) and / or injection data is generated by processing large amounts of data associated with a large number of oil, gas, and water production and injection systems. In some implementations, the processing is performed in real-time or near real-time, to allow for analysis of resource production systems to assist in optimization decisions, such as, for example, development plans involving injection cycles, resource production, well spacing, well completions, well designs, lateral information, conduit placement, protests of well permits, well operations (e.g., drilling schedules), and / or legal agreements, as non-limiting examples.

[0071] Referring to FIG. 3, a detailed description of an example computing system 300 having at least one computing device 302 that may implement various systems and methods discussed herein is provided. The computing device 302 may be applicable to the system 100, the server 106, the user devices 104, the processing system 102, and other computing or network devices. It will be appreciated that specific implementations of these devices may be of differing possible specific computing architectures not all of which are specifically discussed herein but will be understood by those of ordinary skill in the art.

[0072] In some instances, the computing device 302 can include a computer, a personal computer, a desktop computer, a laptop computer, a terminal, a workstation, a server device, a cellular or mobile phone, a mobile device, a smart mobile device a tablet, a wearable device (e.g., a smart watch, smart glasses, a smart epidermal device, etc.) a multimedia console, a television, an Internet-of-Things (IoT) device, a smart home device, a medical device, a virtual reality (VR) or augmented reality (AR) device, a vehicle (e.g., a smart bicycle, an automobile computer, etc.), and / or the like. The computing device 302 may be integrated with, form a part of, or otherwise be associated with the systems described herein. It will be appreciated that specific implementations of these devices may be of differing possible specific computing architectures not all of which are specifically discussed herein but will be understood by those of ordinary skill in the art.

[0073] The computing device 302 may be a computing system capable of executing a computer program product to execute a computer process. Data and program files may be input to the computing device 302, which reads the files and executes the programs therein. Some of the elements of the computing device 302 include one or more processors 304, one or more memory devices 306, and / or one or more ports, such as input / output (IO) port(s) 308 and communication port(s) 310. Additionally, other elements that will be recognized by those skilled in the art may be included in the computing device 302 but are not explicitly depicted in FIG. 3 or discussed further herein. Various elements of the computing device 302 may communicate with one another by way of the communication port(s) 310 and / or one or more communication buses, point-to-point communication paths, or other communication means.

[0074] The processor 304 may include, for example, a central processing unit (CPU), a microprocessor, a microcontroller, a digital signal processor (DSP), and / or one or more internal levels of cache. There may be one or more processors 304, such that the processor 304 comprises a single central-processing unit, or a plurality of processing units capable of executing instructions and performing operations in parallel with each other, commonly referred to as a parallel processing environment.

[0075] The computing device 302 may be a conventional computer, a distributed computer, or any other type of computer, such as one or more external computers made available via a cloud computing architecture. The presently described technology is optionally implemented in software stored on the data storage device(s) such as the memory device(s) 306, and / or communicated via one or more of the I / O port(s) 308 and the communication port(s) 310, thereby transforming the computing device 302 in FIG. 3 to a special purpose machine for implementing the operations described herein. Moreover, the computing device 302, as implemented in the systems in FIGS. 1-3, receives various types of input data (e.g., the sensor data, reservoir data, well data, etc.) and transforms the input data through various stages of the data flow into new types of data files (e.g., well development plans, optimization data, etc.). Moreover, these new data files are transformed further into output data and sent to the computing device 302 to provide information regarding the data, which enables the computing device 302 to do something it could not do before— using probabilistic subsurface flow simulations to optimize well and / or reservoir development plans.

[0076] The one or more memory device(s) 306 may include any non-volatile data storage device capable of storing data generated or employed within the computing device 302, such as computer executable instructions for performing a computer process, which may include instructions of both application programs and an operating system (OS) that manages the various components of the computing device 302. The memory device(s) 306 may include, without limitation, magnetic disk drives, optical disk drives, solid state drives (SSDs), flash drives, and the like. The memory device(s) 306 may include removable data storage media, non-removable data storage media, and / or external storage devices made available via a wired or wireless network architecture with such computer program products, including one or more database management products, web server products, application server products, and / or other additional software components. Examples of removable data storage media include Compact Disc Read-Only Memory (CD-ROM), Digital Versatile Disc Read-Only Memory (DVD-ROM), magneto-optical disks, flash drives, and the like. Examples of non-removable data storage media include internal magnetic hard disks, SSDs, and the like. The one or more memory device(s) 306 may include volatile memory (e.g., dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and / or non-volatile memory (e.g., read-only memory (ROM), flash memory, etc.).

[0077] Computer program products containing mechanisms to effectuate the systems and methods in accordance with the presently described technology may reside in the memory device(s) 306 which may be referred to as machine-readable media. It will be appreciated that machine-readable media may include any tangible non-transitory medium that is capable of storing or encoding instructions to perform any one or more of the operations of the present disclosure for execution by a machine or that is capable of storing or encoding data structures and / or modules utilized by or associated with such instructions. Machine-readable media may include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store the one or more executable instructions or data structures.

[0078] In some implementations, the computing device 302 includes one or more ports, such as the I / O port(s) 308 and the communication port(s) 310, for communicating with other computing, network, or vehicle computing devices. It will be appreciated that the I / O port 308 and the communication port 310 may be combined or separate and that more or fewer ports may be included in the computing device 302. The I / O port 308 may be connected to an I / O device, or other device, by which information is input to or output from the computing device 302. Such I / O devices may include, without limitation, one or more input devices, output devices, and / or environment transducer devices.

[0079] In one implementation, the input devices convert a human-generated signal, such as, human voice, physical movement, physical touch or pressure, and / or the like, into electrical signals as input data into the computing device 302 via the I / O port 308. Similarly, the output devices may convert electrical signals received from the computing device 302 via the I / O port 308 into signals that may be sensed as output by a human, such as sound, light, and / or touch. The input device may be an alphanumeric input device, including alphanumeric and other keys for communicating information and / or command selections to the processor 304 via the I / O port 308. The input device may be another type of user input device including, but not limited to direction and selection control devices, such as a mouse, a trackball, cursor direction keys, a joystick, and / or a wheel; one or more sensors, such as a camera, a microphone, a positional sensor, an orientation sensor, an inertial sensor, and / or an accelerometer; and / or a touch-sensitive display screen (“touchscreen”). The output devices may include, without limitation, a display, a touchscreen, a speaker, a tactile and / or haptic output device, and / or the like. In some implementations, the input device and the output device may be the same device, for example, in the case of a touchscreen.

[0080] In some implementations, environment transducer devices may convert one form of energy or signal into another for input into or output from the computing device 302 via the I / O port 308. For example, an electrical signal generated within the computing device 302 may be converted to another type of signal, and / or vice-versa. In one implementation, the environment transducer devices sense characteristics or aspects of an environment local to or remote from the computing device 302, such as, light, sound, temperature, pressure, magnetic field, electric field, chemical properties, physical movement, orientation, acceleration, gravity, and / or the like.

[0081] In one implementation, the communication port 310 is connected to the network(s) 112 so the computing device 302 can receive network data useful in executing the methods and systems set out herein as well as transmitting information and network configuration changes determined thereby. Stated differently, the communication port 310 connects the computing device 302 to one or more communication interface devices configured to transmit and / or receive information between the computing device 302 and other devices by way of one or more wired or wireless communication networks or connections. Examples of such networks or connections include, without limitation, Universal Serial Bus (USB), Ethernet, Wi-Fi, Bluetooth®, Near Field Communication (NFC), and so on. One or more such communication interface devices may be utilized via the communication port 310 to communicate with one or more other machines, either directly over a point-to-point communication path, over a wide area network (WAN) (e.g., the Internet), over a local area network (LAN), over a cellular network (e.g., third generation (3G), fourth generation (4G), Long-Term Evolution (LTE), fifth generation (5G), etc.) or over another communication means. Further, the communication port 310 may communicate with an antenna or other link for electromagnetic signal transmission and / or reception.

[0082] The computing device 302 set forth in FIG. 3 is but one possible example of a computer system that may employ or be configured in accordance with aspects of the present disclosure. It will be appreciated that other non-transitory tangible computer-readable storage media storing computer-executable instructions for implementing the presently disclosed technology on a computing system may be utilized.

[0083] Additionally, the systems and operations disclosed herein represent an improvement to the technical field of predictive modeling. For instance, the processing system 102 can generate an optimized development plan from available data related to a plurality of resource production and / or injection systems. Moreover, the optimized development plan can be leveraged to provide a highly efficient and effective analysis of resource production and injection systems. As described above, the forecasting may be performed in part, by using resource production training data and / or injection data, such as water production, oil production, gas production, gas injection, water injection, etc.

[0084] In some examples, the systems and methods described herein provide a specific improvement to computer-based reservoir simulation and forecasting technology. Traditional reservoir simulation systems require computationally intensive full-scale numerical solvers that operate over high-resolution grids with large solution spaces, resulting in significant computational burden, slow convergence, and limited ability to perform rapid scenario testing. In contrast, the present disclosure implements a low-order continuous scale simulation (LOCSIM) framework combined with minimized radial basis function (RBF) representations to reduce the dimensionality of the solution space while preserving physical constraints of subsurface flow. By reducing the number of solution points required to approximate reservoir behavior and by representing subsurface flow dynamics using continuous approximations, the system can significantly reduce computational complexity relative to conventional finite-difference or full-physics simulators.

[0085] Further, the disclosed forecast system integrates physics-based modeling with ensemble-based machine learning techniques, including Ensemble Smoothing with Multiple Data Assimilation (ESMDA) and Ensemble Kalman filtering (EnKF), in a structured, automated updating process. This integration enables iterative variance reduction and uncertainty quantification while maintaining physical consistency of the modeled reservoir system.

[0086] Unlike generic data analysis systems, the disclosed architecture improves the functioning of the computing system itself by reducing required processor cycles through low-order modeling; decreasing memory usage through minimized vector representations; enabling rapid recalibration without full-model reinitialization; and / or improving convergence stability of ensemble realizations. These improvements constitute a technological enhancement to reservoir simulation computing systems.

[0087] Turning to FIG. 4A, an example graphical representation of an oil phase training graph that may be used for training the system described in FIGS. 1-3 is illustrated. The graphical representation of FIG. 4A depicts well count information, production rates, actual aggregate, and mean information. During an oil production phase of a well using WAG, measurements may be collected and stored in one or more databases 110. Some example measurements include oil production rate(s), water-cut (water content in produced fluid), gas-oil ratio (GOR) (ratio of gas produced to oil produced), pressure rates, injection rates (e.g., tracking the volumes of water and gas injected), temperature of the produced fluids (e.g., to identify potential thermal effects or changes in reservoir conditions), oil responsivity, oil saturation levels, cumulative production, oil production rate(s) (e.g., volume of oil produced per unit time), oil viscosity (resistance of the oil to flow), etc. The data may be stored in one or more databases 110 or used to train (or update training of) one or more machine learning models of the forecast system 204. In some examples, the data may be used to calculate variances in order to refine one or more machine learning models and / or quantify uncertainty in one or more machine learning models of the reservoir simulation system 202 or the forecast system 204.

[0088] FIG. 4B illustrates an example graphical representation comparing predicted vs actual oil phase production data. In some examples, actual oil phase production data may be used to calculate variances between the forecast oil phase data and the actual oil phase data. Such data may be used to further refine the forecast data, the one or more machine learning models, and / or to quantify uncertainties of the forecast data. The data may be provided by the forecast system 204 to the output system 208 for display as a graphical representation or other visual representation, such as a visual dashboard. In some examples, the forecast system 204 also provides the data to one or more databases 110.

[0089] FIG. 5A illustrates an example graphical representation 500 of a gas phase training graph. The graphical representation of FIG. 5A depicts well count information, production rates, actual aggregate, and mean information. During gas production in a well using WAG, measurements taken include one or more of gas production rates, gas composition, water cut, oil production rate, gas-oil ratio (GOR), pressure, temperature, time of gas breakthrough, injected gas rates, injected water rates, WAG ratio, and injection pressures, as non-limiting examples. The data may be stored in one or more databases 110 or used to train (or update training of) one or more machine learning models of the forecast system 204. In some examples the data may be used to calculate variances in order to refine one or more machine learning models and / or quantify uncertainty in one or more machine learning models of the reservoir simulation system 202 or the forecast system 204.

[0090] FIG. 5B illustrates an example graphical representation 510 comparing predicted data vs actual gas phase. In some examples, actual gas phase production data may be used to calculate variances between the forecast gas phase data and the actual gas phase data. Such data may be used to further refine the forecast data, the one or more machine learning models, and / or to quantify uncertainties of the forecast data. The data may be provided by the forecast system 204 to the output system 208 for display as a graphical representation or other visual representation. In some examples, the forecast system 204 also provides the data to one or more databases 110. In some examples, outlier data points 520 may be indicative of one or more conduits as described further below with regards to FIGS. 13A-13D.

[0091] FIG. 6A illustrates an example graphical representation 600 of a water phase training graph. The graphical representation of FIG. 6A depicts well count information, production rates, actual aggregate, and mean information. Measurements taken during water phase training include water-cut, water production rates, etc. The data may be stored in one or more databases 110 or used to train (or update training of) one or more machine learning models of the forecast system 204. In some examples the data may be used to calculate variances in order to refine one or more machine learning models and / or quantify uncertainty in one or more machine learning models of the reservoir simulation system 202 or the forecast system 204.

[0092] FIG. 6B illustrates a graphical representation 610 of a comparison between predicted vs actual water phase data. In some examples, actual water phase production data may be used to calculate variances between the forecast water phase data and the actual water phase data. Such data may be used to further refine the forecast data, the one or more machine learning models, and / or to quantify uncertainties of the forecast data. The data may be provided by the forecast system 204 to the output system 208 for display as a graphical representation or other visual representation. In some examples, the forecast system 204 also provides the data to one or more databases 110.

[0093] FIG. 7A illustrates an example graphical representation 700 of an example gas injection phase training graph. FIG. 7B illustrates a graphical representation 710 of an example water injection phase training graph. FIGS. 7A and 7B include production rates, well count information, actual aggregate information, and mean information. Measurements taken include injection parameters, such as water injection rates (e.g., volume of water injected per unit of time), gas injection rates (e.g., volume of gas injected per unit of time), WAG ratio (ratio of water to gas injected), injection pressures, wellhead pressure, temperature of produced fluids, time of gas breakthrough (e.g., time at which gas reaches the production well after injection), etc. These measurements provide insight into WAG cycles, optimizing injection parameters, maximizing oil recovery, and analyzing the effectiveness of WAG processes by providing valuable information about reservoir behavior, fluid interactions, and the overall effectiveness of the WAG technique, and are used to train one or more machine models as described above.

[0094] FIG. 8A illustrates an example graphical representation 800 of an example full field oil fit graph and includes historical field data, fit field data (e.g., forecast data), and backcast data. The full field oil fit graph is used to illustrate the fit of oil production data across a reservoir field. The graph is used to compare predicted oil production data against actual production data to assess the accuracy and effectiveness of forecast data. For example, the backcast data assesses the reliability of the forecast data by forecasting backward in time to quantify uncertainties in the forecast data relative to past data. The graphical representation 800 provides quantifiable and visual feedback as to how well the forecast data aligns with the observed data. In some examples, the graphical representation 800 is presented via a graphical user interface and may be modifiable via user input.

[0095] FIG. 8B illustrates an example graphical representation 810 of an example full field gas fit graph and includes historical field data, fit field a data (e.g., forecast data), and backcast data. The graphical representation 810 is used to illustrate the fit of gas production data across a reservoir field. The graphical representation 810 compares predicted gas phase vs actual gas phase information. The graph provides quantifiable and visual feedback as to how well the model predictions align with the observed data. In some examples, the graphical representation 810 is presented via a graphical user interface and may be modifiable via user input.

[0096] FIG. 9A illustrates an example graphical representation 900 of an example full field pressure overlay, including injector points and producer points. The graphical representation 900 is used to visualize the distribution of pressure across a hydrocarbon reservoir or reservoir field. It provides a comprehensive view of how pressure is distributed within the reservoir, including a visual depiction of higher and lower pressure areas, which can be used for understanding reservoir characteristics, production, and / or development strategies.

[0097] FIG. 9B illustrates an example graphical representation 910 of an example full field oil saturation overlay, including injector points and producer points. The graphical representation 910 is used to visualize the distribution of oil saturation across a hydrocarbon reservoir or reservoir field and provides a comprehensive view of how oil is distributed within the reservoir, which can be used for understanding reservoir characteristics, production, and / or development strategies.

[0098] FIG. 9C illustrates an example graphical representation 920 of an example full field oil responsivity overlay. The graphical representation 920 includes injector points and producer points. The graphical representation 920 is used to visualize oil responsivity across a reservoir or reservoir field, which can be used for understanding reservoir characteristics, production, and / or development strategies.

[0099] FIG. 9D illustrates an example graphical representation 930 of an example full field gas responsivity overlay, including injector points and producer points. The graphical representation 930 is used to visualize the distribution of gas responsivity across a hydrocarbon reservoir or reservoir field, which can be used for understanding reservoir characteristics, production, and / or development strategies.

[0100] FIG. 10A illustrates an example graphical representation 1000 of an example full field oil responsivity before an example lateral update, which is a horizontal well that can be drilled in order to provide access to additional areas of a reservoir. FIG. 10B illustrates an example graphical representation 1010 of a full field oil responsivity after the example lateral update. In some examples, the forecast system 204 is able to account for a lateral update in the forecast data in order to provide more accurate forecast data for a reservoir.

[0101] FIG. 11A illustrates an example graphical representation 1100 of a full field oil saturation before an example lateral update. FIG. 11B illustrates an example graphical representation 1110 of a full field oil saturation after the example lateral update. In some examples, the forecast system 204 is able to account for a lateral update in the forecast data in order to provide more accurate forecast data for a reservoir.

[0102] FIG. 12A illustrates an example graphical representation 1200 of an oil forecast for multiple producing wells. FIG. 12B illustrates an example graphical representation 1210 of an oil forecast and BHP forecast for a single well. FIG. 12C illustrates an example graphical representation 1220 of a forecast of average BHP for all wells of an example reservoir.

[0103] FIG. 13A illustrates an example graphical representation 1300 of an example conduit depicting forecast gas injection rates for an injection well. The graphical representation 1300 depicts gas injection rates as a function of time.

[0104] FIG. 13B illustrates an example graphical representation 1310 of an example conduit depicting forecast gas production rates for a producing well. The graphical representation 1310 depicts gas production rates as a function of time.

[0105] FIG. 13C illustrates an example graphical representation 1320 of an example conduit depicting gas rate match between wells. The graphical representation 1320 depicts responsivity and gas rates as a function of time. The graphical representation 1320 may be used to visually and quantitatively assess differences or variances between the forecast data and actual data. For example, high responsivity may correspond to high gas production and the graphical representation 1320 may be used to provide an assessment of accuracy of data and / or may be used for an optimized production and / or development plan.

[0106] FIG. 13D illustrates an example graphical representation 1330 of an example reservoir overlay showing back test gas responsivity, which is a map depicting gas responsivity for the example reservoir.

[0107] FIG. 14A illustrates an example graphical representation 1400 of an example oil responsivity forecasting in a single well. The graphical representation 1400 depicts historical field information, forecast oil field responsivity, field fit data, shut-in information for one or more conduits, backcast information, and base case information (e.g. initial modeling, reservoir simulation, etc.) as a function of time.

[0108] FIG. 14B illustrates an example graphical representation 1410 of an example BHP forecasting in a single well. The graphical representation 1410 depicts historical field information, forecast BHP, field fit data, shut-in information for one or more conduits, backcast information, and base case information (e.g. initial modeling, reservoir simulation, etc.) as a function of time.

[0109] FIG. 14C illustrates an example graphical representation 1420 of an example oil saturation forecasting in a single well. The graphical representation 1420 depicts historical field information, forecast oil saturation, field fit data, shut-in information for one or more conduits, backcast information, and base case information (e.g. initial modeling, reservoir simulation, etc.) as a function of time.

[0110] FIG. 14D illustrates an example graphical representation 1430 of an example gas fit forecasting in a single well. The graphical representation 1430 depicts historical field information, forecast gas rate, field fit data, shut-in information for one or more conduits, backcast information, and base case information (e.g. initial modeling, reservoir simulation, etc.) as a function of time.

[0111] FIG. 14E illustrates an example graphical representation 1440 of an example water fit forecasting in a single well. The graphical representation 1430 depicts historical field information, forecast water rate, field fit data, shut-in information for one or more conduits, backcast information, and base case information (e.g. initial modeling, reservoir simulation, etc.) as a function of time.

[0112] Turning to FIG. 15, example operations 1500 for optimizing development plans in a hydrocarbon reservoir are shown. In one implementation, an operation 1502 retrieves reservoir data. The reservoir data may include historical information obtained via the one or more sensors 108 and / or other sources. Such data may include core, well log, fluid sampling, production rates (e.g., resource produced per unit time), injection rates (e.g., tracking the volumes of water and gas injected), pressure data, location data, top hole pressure, bottom hole pressure, reservoir pressure, temperature, fluid flow rates, etc., or any combination thereof.

[0113] An operation 1504 generates reservoir flow simulation data for a hydrocarbon reservoir using the reservoir data. The reservoir simulation data may be generated using one or more models of a reservoir and / or reservoir properties. In some examples, the reservoir simulation data may be one or more subsurface flows of a reservoir or reservoir field (e.g., reservoir flow simulation data). In some examples, the reservoir simulation data may include subsurface flows for more than one reservoir and / or reservoir field.

[0114] An operation 1506 generates forecast data by inputting the reservoir simulation data into the one or more machine learning models. In some implementations, the one or more machine learning models are trained using well training data and reservoir physics data. The well training data may be historical data acquired during at least one of an oil production process, a gas production process, a water production process, a gas injection process, or a water injection process in the hydrocarbon reservoir. In some implementations, the well training data may be water-cut (water content in produced fluid), gas-oil ratio (GOR) (ratio of gas produced to oil produced), temperature of the produced fluids (e.g., to identify potential thermal effects or changes in reservoir conditions), fluid responsivity, saturation levels, cumulative production, oil viscosity (resistance of oil to flow), as non-limiting examples.

[0115] In an implementation, operation 1508 may generate output data. For example, an optimized development plan, visual dashboard, and / or graphical representation(s) may be generated. Generating the development plan may include outputting the development plan for display and / or manipulation via one or more output systems 208 and / or one or more computing devices 302. In an implementation, the output data includes instructions to control one or more systems of a natural resource production system in accordance with the development plan.

[0116] In the present disclosure, the methods disclosed may be implemented as sets of instructions or software readable by a device. Further, it is understood that the specific order or hierarchy of steps in the methods disclosed are instances of example approaches. Based upon design preferences, it is understood that the specific order or hierarchy of steps in the method can be rearranged while remaining within the disclosed subject matter. The accompanying method claims present elements of the various steps in a sample order and are not necessarily meant to be limited to the specific order or hierarchy presented.

[0117] The described disclosure may be provided as a computer program product, or software, which may include a non-transitory machine-readable medium having stored thereon instructions, which may be used to program a computer system (or other electronic devices) to perform a process according to the present disclosure. A machine-readable medium includes any mechanism for storing information in a form (e.g., software, processing application) readable by a machine (e.g., a computer). The machine-readable medium may include, but is not limited to, magnetic storage medium, optical storage medium; magneto-optical storage medium, read only memory (ROM); random access memory (RAM); erasable programmable memory (e.g., EPROM and EEPROM); flash memory; or other types of medium suitable for storing electronic instructions.

[0118] While the present disclosure has been described with reference to various implementations, it will be understood that these implementations are illustrative and that the scope of the present disclosure is not limited to them. Many variations, modifications, additions, and improvements are possible. More generally, embodiments in accordance with the present disclosure have been described in the context of particular implementations. Functionality may be separated or combined in blocks differently in various embodiments of the disclosure or described with different terminology. These and other variations, modifications, additions, and improvements may fall within the scope of the disclosure as defined in the claims that follow.

Claims

1. A system for optimizing a development plan for one or more injection wells, the system comprising:a processing system in communication with a computing device, one or more sensors, and one or more databases over a network, the processing system receiving reservoir data from at least one of the computing device, the one or more sensors, or the one or more databases;a reservoir flow simulation system generating reservoir flow simulation data using the reservoir data, the reservoir flow simulation data including one or more subsurface flow rates of a reservoir;a forecast system generating forecast data by inputting the reservoir flow simulation data including the one or more subsurface flow rates into one or more machine learning models, the one or more machine learning models trained using reservoir physics and historical well data; andan output system generating output data using the forecast data.

2. The system of claim 1, wherein the output data includes one or more graphical representations generated using the forecast data.

3. The system of claim 1, wherein the historical well data is acquired during at least one of an oil production process, a gas production process, a water production process, a gas injection process, or a water injection process.

4. The system of claim 1, wherein the reservoir data includes at least one of core, well log, fluid sampling, production rates, injection rates, pressure data, location data, top hole pressure, bottom hole pressure, reservoir pressure, temperature, or fluid flow rates.

5. The system of claim 1, wherein a water-alternating-gas technique is performed based on the output data.

6. The system of claim 1, wherein the forecast data includes at least one of oil responsivity, gas fit forecasting, water fit forecasting, and bottom hole pressure (BHP) forecasting.

7. A method for optimizing a development plan for one or more injection wells, the method comprising:obtaining reservoir data using at least one of a computing device, one or more sensors, or one or more databases;generating reservoir flow simulation data using the reservoir data, the reservoir flow simulation data including one or more subsurface flow rates of a hydrocarbon reservoir;generating forecast data for the one or more injection wells by inputting the reservoir flow simulation data including the one or more subsurface flow rates into one or more machine learning models, the one or more machine learning models trained using historical well data and reservoir physics data; andgenerating output data using the forecast data.

8. The method of claim 7, wherein the one or more machine learning models is updated using an automated variance analysis of the forecast data.

9. The method of claim 7, wherein the historical well data is acquired during at least one of an oil production process, a gas production process, a water production process, a gas injection process, or a water injection process.

10. The method of claim 7, wherein the reservoir data includes at least one of core, well log, fluid sampling, production rates, injection rates, pressure data, location data, top hole pressure, bottom hole pressure, reservoir pressure, temperature, or fluid flow rates.

11. The method of claim 7, wherein the forecast data includes at least one of oil responsivity, gas fit forecasting, water fit forecasting, and bottom hole pressure (BHP) forecasting.

12. The method of claim 7, further comprising generating backcasting information based on the forecast data to indicate reliability of the forecast data.

13. The method of claim 7, further comprising identifying conduits between one or more wells of the hydrocarbon reservoir.

14. One or more tangible non-transitory computer-readable storage media storing computer-executable instructions that, when executed by a computing system, cause the computing system to perform a computer process for optimizing a development plan for one or more injection wells, the computer process comprising:obtaining reservoir data from at least one of a computing device, one or more sensors, or one or more databases;generating reservoir flow simulation data using the reservoir data, the reservoir flow simulation data including one or more subsurface flow rates of a hydrocarbon reservoir;generating forecast data for the one or more injection wells by inputting the reservoir flow simulation data including the one or more subsurface flow rates into one or more machine learning models, the one or more machine learning models trained using historical well data and reservoir physics data; andgenerating output data using the forecast data.

15. The one or more tangible non-transitory computer-readable storage media of claim 14, wherein the historical well data is acquired during at least one of an oil production process, a gas production process, a water production process, a gas injection process, or a water injection process.

16. The one or more tangible non-transitory computer-readable storage media of claim 14, wherein the reservoir data is at least one of core, well log, fluid sampling, production rates, injection rates, pressure data, location data, top hole pressure, bottom hole pressure, reservoir pressure, temperature, or fluid flow rates.

17. The one or more tangible non-transitory computer-readable storage media of claim 14, wherein the forecast data includes at least one of oil responsivity, gas fit forecasting, water fit forecasting, and bottom hole pressure (BHP) forecasting.

18. The one or more tangible non-transitory computer-readable storage media of claim 14, wherein the output data includes one or more graphical representations of well-level characteristics, the well-level characteristics including at least one of saturation, pressure, and responsivity.

19. The one or more tangible non-transitory computer-readable storage media of claim 14, further comprising generating backcasting information based on the forecast data to assess reliability of the forecast data.

20. The one or more tangible non-transitory computer-readable storage media of claim 14, further comprising identifying conduits between one or more individual wells of the hydrocarbon reservoir.

Images