Abstract: A system for real-time steering of a drill bit includes a drilling arrangement and a computing device in communication with the drilling arrangement. The system iteratively, or repeatedly, receives new data associated the wellbore. At each iteration, a model, for example an engineering model, is applied to the new data to produce an objective function defining the selected drilling parameter. The objective function is modified at each iteration to provide an updated value for the selected drilling parameter and an updated value for at least one controllable parameter. In one example, the function is modified using Bayesian optimization The system iteratively steers the drill bit to obtain the updated value for the selected drilling parameter by applying the updated value for at least one controllable parameter over the period of time that the wellbore is being formed.

Abstract: A physics-influenced deep neural network (PDNN) model, or a deep neural network incorporating a physics-based cost function, can be used to efficiently denoise sensor data. To generate the PDNN model, noisy sensor data is used as training data input to a deep neural network and training output is valuated with a cost function that incorporates a physics-based model. An autoencoder can be coupled to the PDNN model and trained with the reduced-noise sensor data which is output from the PDNN during training of the PDNN or with a separate set of sensor data. The autoencoder detects outliers based on the reconstructed reduced-noise sensor data which it generates. Denoising sensor data by leveraging an autoencoder which is influenced by the physics of the underlying domain based on the incorporation of the physics-based model in the PDNN facilitates accurate and efficient denoising of sensor data and detection of outliers.

Abstract: Geosteering can be used in a drilling operation to create a wellbore that is used to extract hydrocarbons from a defined zone within the subterranean formation. According to some aspects, generating paths for the wellbore may include using path-planning protocols and pure-pursuit protocols. The pure-pursuit protocol may be executed to output a plurality of candidate drilling paths. The output may also include control parameters for controlling the drill bit. A trajectory optimizer may determine a result of multi-objective functions for each candidate path. A cost function may represent a cost or loss associated with a candidate path. Additionally, the trajectory optimizer may perform an optimization protocol, such as Bayesian optimization, on the cost functions to determine which candidate path to select. The selected candidate path may correspond to new control parameters for controlling the drill bit to reach the target location.

Abstract: The present disclosure is related to improvements in methods for evaluating formation fluid properties of interest in an in-production wellbore as well as evaluating health and functionalities of physical sensors present in and collecting data within the well. In one aspect, a method includes receiving data from one or more physical sensors within a wellbore; determining at least one formation property of the wellbore using one or more machine learning models receiving the data as input and generating reservoir simulation models using the at least one formation property.

Abstract: Certain aspects and features relate to a system for trajectory planning and control for new wellbores. Data can be received for multiple existing wells associated with a subterranean reservoir and used to train a deep neural network model to make accurate well property projections at any other location in the reservoir. A model of features for specific well locations based on seismic attributes of the well location can be automatically generated, and the model can be used in drilling trajectory optimization. In some examples, the system builds a deep neural network (DNN) model based on the statistical features, and trains the DNN model using Bayesian optimization to produce an optimized DNN model. The optimized model can be used to provide drilling parameters to produce an optimized trajectory for a new well.

Abstract: System and methods of controlling diversion for stimulation treatments in real time are provided. Input parameters are determined for a stimulation treatment being performed along a wellbore within a subsurface formation. The input parameters include selected treatment design parameters and formation parameters. A step-down analysis is performed to identify friction components of a total fracture entry friction affecting near-wellbore pressure loss during the stimulation treatment. Efficiency parameters are determined for a diversion phase of the stimulation treatment to be performed along a portion of the wellbore, based on the input parameters and the friction components. An amount of diverter to be injected during the diversion phase of the stimulation treatment is calculated based at least partly on the efficiency parameters.

Abstract: A method for fracturing a formation is provided. Real-time fracturing data is acquired from a well bore during fracturing operation. The real-time fracturing data is processed using a recurrent neural network trained using historical data from analogous wells. A real-time response variable prediction is determined using the processed real-time fracturing data. Fracturing parameters for the fracturing operation are adjusted in real-time based on the real-time response variable prediction. The fracturing operation is performed using the fracturing parameters that were adjusted based on the real-time response variable prediction.

Abstract: A model optimizer for predicting a drill bit variable can select a model from multiple models based on a learned preference. The preference may be updated according to preference indicator received from a user in response to an output model selection.

Abstract: Aspects of the subject technology relate to systems and methods for predicting physical characteristics of a physical environment using a physical characterization model trained based on simulated states of a modeled physical environment. A physical characterization model can be generated based on a plurality of simulated states of a modeled physical environment. Specifically, the physical characterization model can be trained by mapping simulated spatial properties of the modeled physical environment temporally across the plurality of simulated states of the modeled physical environment. Further, input state data describing one or more input states of a physical environment can be received. One or more physical characteristics of the physical environment can be predicted by applying the physical characterization model to the one or more input states of the physical environment.

Abstract: A method comprises: deriving fluid properties that provide for suspension of particulate diverting agents using a 3-dimensional flow model and based on a downhole temperature and at least one size characteristic of the particulate diverting agents; identifying a treatment fluid composition that comprises a nanoparticulate suspending agent and achieves the fluid properties using a relationship between the treatment fluid composition and the fluid properties; and preparing a treatment fluid or a treatment fluid additive based on the treatment fluid composition.

Abstract: Aspects of the present disclosure relate to receiving data associated with a subterranean reservoir to be penetrated by a wellbore and training a neural network with both the data and a physics-based first principles model. The neural network is then used to make predictions regarding the properties of the subterranean reservoir, and these predictions are in turn used to determine one or more controllable parameters for equipment associated with a wellbore. The controllable parameters can then be used to control equipment for formation, stimulation, or production relative to the wellbore.

Abstract: A method for detecting anomalies in a piece of wellsite equipment. The method may include measuring data related to the piece of wellsite equipment. The method may also include encoding the measured data with a first autoencoder to produce a first set of encoded data. The method may further include performing a first Gaussian process regression (“GPR”) on the first set of encoded data to produce a first set of results that identifies a first anomaly in the measured data and that provides a first confidence interval for the first anomaly.

Abstract: A system and method for controlling multiple drilling tools inside wellbores makes use of Bayesian optimization with range constraints. A computing device samples observed values for controllable drilling parameters such as weight-on-bit, mud flow rate and drill bit rotational speed in RPM and evaluates a selected drilling parameter such a rate-of-penetration and hydraulic mechanical specific energy for the observed values using an objective function. Range constraints including the physical drilling environment and the total power available to all drilling tools within the drilling environment can be continuously learned by the computing device as the range constraints change. A Bayesian optimization, subject to the range constraints and the observed values, can produce an optimized value for the controllable drilling parameters to achieve a predicted value for the drilling parameters.

Abstract: A hydraulic fracturing flow simulation method includes identifying one or more reservoir layers contacted by a wellbore, the reservoir layers including a network of fractures. The method further includes determining a current network state that includes flow parameter values at discrete points arranged one-dimensionally along the wellbore and at discrete points arranged one-dimensionally along each fracture, the flow parameter values including concentrations of multiple proppant types or sizes. The method further includes constructing a set of linear equations for deriving a subsequent network state from the current network state while accounting for interaction and settling of the multiple proppant types or sizes. The method further includes repeatedly solving the set of linear equations to obtain a sequence of subsequent network states. The method further includes displaying the time-dependent spatial distribution.

Abstract: Systems and methods for controlling drilling operations are provided. A controller for a drilling system may provide drilling parameters such as weight-on-bit and rotation rate parameters to the drilling system, based on a machine-learned reward policy and a model-based prediction. The machine-learned reward policy may be generated during drilling operations and used to modify recommended values from the model-based prediction for subsequent drilling operations to achieve a desired rate-of-penetration.

Abstract: A system and method for controlling a gas supply to provide gas lift for wellbore(s) using Bayesian optimization. A computing device controls a gas supply to inject gas into wellbore(s). The computing device receives first reservoir data associated with a first subterranean reservoir and simulates production using the first reservoir data, using a model for the first subterranean reservoir. The production simulation provides first production data. The computing device receives second reservoir data associated with a subterranean reservoir and simulates production using the second reservoir data, using a model for the second subterranean reservoir. The production simulation provides second production data. A Bayesian optimization of an objective function of the first and second production data subject to any gas injection constraints can be performed to produce gas-lift parameters. The gas-lift parameters can be applied to the gas supply to control injection of gas into the wellbore(s).

Abstract: A system and method for controlling a gas supply to provide gas lift for a production wellbore makes use of Bayesian optimization. A computing device controls a gas supply to inject gas into one or more wellbores. The computing device receives reservoir data associated with a subterranean reservoir to be penetrated by the wellbores and can simulate production using the reservoir data and using a physics-based or machine learning or hybrid physics-based machine learning model for the subterranean reservoir. The production simulation can provide production data. A Bayesian optimization of an objective function of the production data subject to any gas injection constraints can be performed to produce gas lift parameters. The gas lift parameters can be applied to the gas supply to control the injection of gas into the wellbore or wellbores.

Abstract: System and methods for optimizing parameters for drilling operations are provided. Real-time data including values for input variables associated with a current stage of a drilling operation along a planned well path are acquired. A neural network model is trained to produce an objective function defining a response value for at least one operating variable of the drilling operation. The response value for the operating variable is estimated based on the objective function produced by the trained neural network model. Stochastic optimization is applied to the estimated response value so as to produce an optimized response value for the operating variable. Values of controllable parameters are estimated for a subsequent stage of the drilling operation, based on the optimized response value of the operating variable. The subsequent stage of the drilling operation is performed based on the estimated values of the controllable parameters.

Abstract: System for optimizing operation of an oil and gas well employs multi-objective Bayesian optimization of wellbore parameters to minimize scaling and corrosion. The system may contain instrumentation for measuring temperature, pressure, at least one production parameter and at least one ion concentration of the fluid in the wellbore. The system may also have a processor for performing a calculation procedure to determine an anticipated corrosion rate (“Vbase”) and a scaling index (“Is”) reflecting a tendency of scale to form in the wellbore based on the measurements provided by the instrumentation, where Vbase and Is are calculated along the length of the wellbore. Based on a selected set of optimization points taken from the calculations of Vbase and Is, the system may control the alkalinity and flow rate of the fluid based on the multi-objective optimization to simultaneously optimize scaling and corrosion.

Abstract: A method includes receiving a training selection of a first set of faults located in a first subset of a seismic dataset for a subsurface geologic formation, detecting a second set of faults in the seismic dataset based on fault interpretation operations using a first set of interpretation parameters, and determining a difference between the first set of faults and the second set of faults. The method also includes generating a second set of interpretation parameters for the fault interpretation operations based on the difference between the first set of faults and the second set of faults, and determining a feature of the subsurface geologic formation based on fault interpretation operations using the second set of interpretation parameters.