Abstract: A system and method for controlling a drilling tool inside a wellbore makes use of projection of optimal rate of penetration (ROP) and optimal controllable parameters such as weight-on-bit (WOB), and rotations-per-minute (RPM) for drilling operations. Optimum controllable parameters for drilling optimization can be predicted using a data generation model to produce synthesized data based on model physics, an ROP model, and stochastic optimization. The synthetic data can be combined with real-time data to extrapolate the data across the WOB and RPM space. The values for WOB an RPM can be controlled to steer a drilling tool. Examples of models used include a non-linear model, a linear model, a recurrent generative adversarial network (RGAN) model, and a deep neural network model.

Abstract: A computer implemented method, computer program product, and system for managing execution of a workflow comprising a set of subworkflows, comprising optimizing the set of subworkflows using a deep neural network, wherein each subworkflow of the set of subworkflows has a set of tasks, wherein each task of the sets of tasks has a requirement of resources of a set of resources; wherein each task of the sets of tasks is enabled to be dependent on another task of the sets of tasks, training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of said set of resources, wherein the training causes the neural network to learn relationships between the states of said set of resources, the said sets of tasks, their parameters and the obtained performance, optimizing an allocation of resources of the set of resources to each task of the sets of tasks to ensure compliance with a user-defined quality metric b

Abstract: A system can generate a trip map for adjusting a tripping operation in a wellbore. The system can receive input data from a downhole tool in a wellbore. The system can determine parameters for the tripping operation. The system can determine an overall condition for an interval of the wellbore based on the parameters. The system can determine a status for the parameters and for the overall condition based on a difference between the parameters or the overall condition and a corresponding optimized value. The system can generate a trip map using the parameters and the overall condition. The trip map can include a background shape and a polygon that can be positioned on the background shape. The polygon can include corners corresponding to the parameters and overall condition that are positioned angularly around the background. The trip map can be output to adjust the tripping operation.

Abstract: This disclosure presents a fault prediction system using a deep learning neural network, such as a convolutional neural network. The fault prediction system utilizes as input seismic data, and then derives various seismic attributes from the seismic data. In various aspects, the seismic attributes can be normalized and have importance coefficients determined. A sub-set of seismic attributes can be selected to reduce computing resources and processing time. The deep learning neural network can utilize the seismic data and seismic attributes to determine parameterized results representing fault probabilities. The fault prediction system can utilize the fault probabilities to determine fault predictions which can be represented as a predicted new seismic data, such as using a three-dimensional image.

Abstract: A system is described for estimating well production and injection rates of a subterranean reservoir using machine learning models. The system may include a processor and a non-transitory computer-readable medium comprising instructions that are executable by the processor to cause the processor to perform various operations. The processor may receive a set of static geological data about at least one subterranean reservoir in a subterranean formation. The processor may apply a trained convolutional neural network to the set of static geological data and data on initial states of dynamic reservoir properties to determine dynamic outputs of the subterranean reservoir. The processor may determine well data by extracting the set of static geological data and the dynamic outputs at well trajectories. And, the processor may apply a trained artificial neural network to the well data and subterranean grid information about the subterranean reservoir to generate estimated well production and injection rates.

Abstract: Systems and methods for predicting drilling tool failure based on an analysis of at least one of a plot of jerk and inverse jerk for the drilling tool and a plot of drilling tool failure pattern trends data.

Abstract: A method of predicting rock properties at a selectable scale is provided, including receiving coordinates of locations of respective sample points, receiving measurement data associated with measurements or measurement interpretations for each sample point, receiving for each sample point a scale that indicates the scale used to obtain the measurements and/or measurement interpretations, wherein different scales are received for different sample points. A deep neural network (DNN) is trained by applying the received coordinates, measurement data, and scale associated with each sample point and associating the sample point with a rock property as a function of the coordinates, measurement data, and scale applied for the sample point. The DNN is configured to generate rock property data for a received request point having coordinates and a selectable scale, wherein the rock property data is determined for the request point as a function of the coordinates and the selectable scale.

Abstract: A system is disclosed for detecting a problem associated with a drilling operation based on the properties of a formation cutting. The system can include a camera for generating an image of the formation cutting extracted from a subterranean formation. The system can include one or more sensors for detecting one or more characteristics of the subterranean formation or a well tool. The system can provide the image as input to a first model for determining one or more properties of the formation cutting based on the image. The system can provide the one or more properties and the one or more characteristics as input to a second model for detecting a downhole problem associated with the drilling operation. The system can transmit an alert indicating the downhole problem and optionally a recommended solution to a user.

Abstract: An information processing system having a processor and a memory device coupled to the processor, wherein the memory device includes a set of instruction that, when executed by the processor, cause the processor to receive a multi-dimensional grid of acoustic or elastic impedances determined from seismic survey data associated with a subterranean formation, receive elastic property data that describes elastic property characteristics used to sort pseudo-components, and wherein the respective pseudo-components are formed of a combination of two or more lithologies.

Abstract: A wellbore drilling system can generate a machine-learning model trained using historic drilling operation data for monitoring for a lost circulation event. Real-time data for a drilling operation can be received and the machine-learning model can be applied to the real-time data to identify a lost circulation event that is occurring. An alarm can then be outputted to indicate a lost circulation event is occurring for the drilling operation.

Abstract: A well system includes a fiber-optic cable positionable downhole along a length of a wellbore. The well system further includes an opto-electrical interface to communicatively couple to the fiber-optic cable to monitor a gas released from a well element within the wellbore. Further, the well system includes a processing device and a memory device that includes instructions executable by the processing device. The instructions cause the processing device to detect hydrogen absorption by the fiber-optic cable within the wellbore and determining a location of deterioration of the well element using the detected hydrogen absorption by the fiber-optic cable.

Abstract: An intelligent data management system leverages heterogeneous database technologies and cloud technology to manage data for reservoir simulations across the lifetime of a corresponding energy asset(s) and facilitates access of that data by various consumers despite changing compute platforms and adoption of open source paradigms. The intelligent data management system identifies the various data units that constitute a reservoir simulation output for storage and organization. The intelligent data management system organizes the constituent data units across a file system and object database based on correspondence with different simulation run attributes: project, study, and model. The intelligent data management system also learns to specify or guide configuration of simulation runs.

Abstract: A drilling device may use a concurrent path planning process to create a path from a starting location to a destination location within a subterranean environment. The drilling device can receive sensor data. A probability distribution can be generated from the sensor data indicating one or more likely materials compositions that make up each portion of the subterranean environment. The probability distribution can be sampled, and for each sample, a drill path trajectory and drill parameters for the trajectory can be generated. A trained neural network may evaluate each trajectory and drill parameters to identify the most ideal trajectory based on the sensor data. The drilling device may then initiate drilling operations for a predetermined distance along the ideal trajectory.

Abstract: System and methods for automated seismic processing are provided. Historical seismic project data associated with one or more historical seismic projects is obtained from a data store. The historical seismic project data is transformed into seismic workflow model data. At least one seismic workflow model is generated using the seismic workflow model data. Responsive to receiving seismic data for a new seismic project, an optimized workflow for processing the received seismic data is determined based on the at least one generated seismic workflow model. Geophysical parameters for processing the seismic data with the optimized workflow are selected. The seismic data for the new seismic project is processed using the optimized workflow and the selected geophysical parameters.

Abstract: A method includes selecting a model for a simulation of hydrocarbon recovery from a reservoir having a plurality of fractures during injection of an injected gas into the plurality of fractures. Selecting the model includes determining a flux ratio of a convection rate to a diffusion rate for the reservoir, determining whether the flux ratio is less than a threshold, and in response to the flux ratio being less than the threshold, selecting the model that includes diffusion. Selecting the model includes performing the simulation of the hydrocarbon recovery from the reservoir based on the model.

Abstract: A location of a cut and an amount of force to be used in a pull operation for a plug & abandonment (P&A) operation can be determined. Measurements of at least one characteristic of fluids and solids disposed in an annulus defined between a casing and a wall of a wellbore can be received. A total fluid and solid friction force drag can be determined using hydrostatic force that is determined from the measurements. A mechanical friction force drag can be determined based on a weight of the casing. The mechanical friction force drag and the total fluid and solid friction force drag can be used to determine a friction factor. The friction factor can be used to determine a depth location at which to cut the casing and a pull force for pulling the casing from the wellbore in the P&A operation.

Abstract: A method and system to drill a wellbore and identify drill bit failure by deconvoluting sensor data. The method comprises drilling the wellbore using a drill bit; and measuring data indicative of a parameter associated with the drill bit using a sensor located in the wellbore. The method also comprises decomposing the data to generate an intrinsic mode function of the drill bit data; and analyzing the intrinsic mode function to identify a drill bit failure. The system for drilling the wellbore comprises a drill bit; a sensor; and a processor. The sensor is located in the wellbore and operable to measure data indicative of a parameter associated with the drill bit. The processor is in communication with the sensor and operable to decompose the data to generate an intrinsic mode function of the drill bit data; and analyze the intrinsic mode function to identify a drill bit failure.

Abstract: A system is described for determining an analogue geological feature. The system may include a processor and a non-transitory computer-readable medium comprising instructions that are executable by the processor to cause the processor to perform various operations. The system may generate, by extracting parameter signatures for geological features, a database including parameters about geological features associated with parameter signatures. The system may receive data including parameters and a feature-type about a geological feature of interest. The system may generate a signature including values for a subset of the feature-of-interest parameters selected based on the geological feature of interest for the feature-of-interest using the data. The system may execute a comparison of the feature signature to the parameter signatures included in the database for identifying an analogue geological feature for the feature of interest.

Abstract: The disclosure presents processes for improving the design phase of plastic material lined tubular structures used downhole of a borehole. A plastic material lined tubular structure model is utilized for tubular structures that have a metal layer, a grout layer, and a plastic material layer. The model can use a modified wall thickness for the metal layer. A strength model can be applied to the modified critical dimensions, e.g., wall thickness parameters. A thermal model can be applied to the tubular structure to determine pressure and temperature parameters. The strength model and the thermal model outputs can be utilized by a stress analyzer to determine loads, safety factors, and design limit parameters. The plastic material lined tubular structure model can enable more efficient use of tubular structures, designing a longer operational lifetime, such as in acidic environments, or the use of thinner structures while maintaining a satisfactory operational lifetime.

Abstract: The disclosure presents a technique to generate a fracture model using a differential stress map and model inputs. The technique simulates the fracture model using fracture fronts, initiated at perforations of a perforation stage of a hydraulic fracturing (HF) wellbore. Each fracture front is evaluated using a propagation step of a fracture model process. Using the relative differential stress states, a fracture pattern is composited to the fracture model. At each propagation step, the total energy available from the simulated HF fluid being pumped into the wellbore location is reduced by the amount necessary to generate the computed fractures. Once the remaining energy is reduced to a level where no further fractures can be created, or if a map boundary is encountered, the fracture model process terminates. The generated fracture model can be communicated to update HF job plans, wellbore placements, and other uses of the fracture model.