Abstract: A method, apparatus, and program product may utilize data associated with one or more electric submersible pumps (ESPs) to train a machine learning model and/or use a machine learning model to perform ESP failure analysis. In addition, one or more features from the data may be encoded into a machine-readable format to facilitate ingestion by the machine learning model.

Abstract: Embodiments of the present disclosure include a method that includes creating a deterministic model representing a production system. The model may include one or more inputs and parameters that are not deterministically known, and one or more outputs. A prior probability density function may be used to determine a prior uncertainty, and a measurement related to a first of the outputs may be obtained. The method may also include determining a posterior probability density function using the prior probability density function, the measurement, and a conditional probability density function. Embodiments of the present disclosure also include a computer-readable medium having a set of computer-readable instructions residing thereon that, when executed, perform acts comprising the foregoing method.

Abstract: Embodiments of the present disclosure include a method that includes creating a deterministic model representing a production system. The model may include one or more inputs and parameters that are not deterministically known, and one or more outputs. A prior probability density function may be used to determine a prior uncertainty, and a measurement related to a first of the outputs may be obtained. The method may also include determining a posterior probability density function using the prior probability density function, the measurement, and a conditional probability density function. Embodiments of the present disclosure also include a computer-readable medium having a set of computer-readable instructions residing thereon that, when executed, perform acts comprising the foregoing method.

Abstract: A method of managing a fluid or gas reservoir is disclosed which assimilates diverse data having different acquisition time scales and spatial scales of coverage for iteratively producing a reservoir development plan that is used for optimizing an overall performance of a reservoir.

Abstract: The invention relates to a method of performing a numerical model study to accurately forecast a production of a well in a reservoir. The method involves determining a property distribution of the reservoir using a three dimensional (3D) structure and property model for providing an estimate of a 3D structure, wherein the estimate of the 3D structure includes the property distribution, determining a grid system, including a grid and layering mechanism that is superimposed on said 3D structure and said property distribution associated with the digital 3D structure and property model, using a 3D simulator grid system, and determining a rock model using an initial 3D reservoir simulator in response to the estimate of the property distribution associated with the digital 3D structure and property model and the grid system associated with the 3D simulator grid system, wherein the rock model is used to accurately forecast the production of the well in the reservoir.

Abstract: A method of managing a fluid or gas reservoir is disclosed which assimilates diverse data having different acquisition time scales and spatial scales of coverage for iteratively producing a reservoir development plan that is used for optimizing an overall performance of a reservoir.

Abstract: A method of managing a fluid or gas reservoir is disclosed which assimilates diverse data having different acquisition time scales and spatial scales of coverage for iteratively producing a reservoir development plan that is used for optimizing an overall performance of a reservoir.

Abstract: A method and associated apparatus continuously optimizes reservoir, well and surface network systems by using monitoring data and downhole control devices to continuously change the position of a downhole intelligent control valve (ICV) (12) until a set of characteristics associated with the “actual” monitored data is approximately equal to, or is not significantly different than, a set of characteristics associated with “target” data that is provided by a reservoir simulator (32). A control pulse (18) having a predetermined signature is transmitted downhole thereby changing a position of the ICV. In response, a sensor (14) generates signals representing, “actual” monitoring data. A simulator (32) which models a reservoir layer provides “target” data.

Abstract: Systems and methods of managing a workflow of an oilfield activity are provided. A problem in the oilfield activity is identified, where the oilfield activity includes a number of tasks necessary to complete a project of a number of projects in the workflow, and where the number of tasks are arranged within a number of workflow states associated with the oilfield activity. A sequence for the number of tasks is selectively updated based on an analysis of the oilfield activity performed by a user. The project is analyzed by examining a progress of the project within one of the number of workflow states to obtain a decision, where the project is associated with the problem. The problem is resolved in the oilfield activity based on the decision.

Abstract: A method of managing a fluid or gas reservoir is disclosed which assimilates diverse data having different acquisition time scales and spatial scales of coverage for iteratively producing a reservoir development plan that is used for optimizing an overall performance of a reservoir.

Abstract: A method and associated apparatus continuously optimizes reservoir, well and surface network systems by using monitoring data and downhole control devices to continuously change the position of a downhole intelligent control valve (ICV) (12) until a set of characteristics associated with the “actual” monitored data is approximately equal to, or is not significantly different than, a set of characteristics associated with “target” data that is provided by a reservoir simulator (32). A control pulse (18) having a predetermined signature is transmitted downhole thereby changing a position of the ICV. In response, a sensor (14) generates signals representing, “actual” monitoring data. A simulator (32) which models a reservoir layer provides “target” data.

Abstract: Sensors are permanently placed in the ground near observation and injection wells in order to passively and continuously monitor the status of seawater advance toward fresh water aquifers near coastal cities as well as the status of fresh water injected into the injection wells. Such sensor devices are installed in the ground and electrically connected to surface acquisition equipment that would, without human intervention, transmit acquired data to a centralized facility for processing and interpretation. Various types of sensors can be used: the sensors used for general reservoir monitoring and/or the sensors used for leak detection, soil heating, and temperature mapping. Alternatively, a special type of sensor can be designed and provided for the purpose of monitoring the status of seawater advance toward fresh water aquifers.

Abstract: Sensors are permanently placed in the ground near observation and injection wells in order to passively and continuously monitor the status of seawater advance toward fresh water aquifers near coastal cities as well as the status of fresh water injected into the injection wells. Such sensor devices are installed in the ground and electrically connected to surface acquisition equipment that would, without human intervention, transmit acquired data to a centralized facility for processing and interpretation. Various types of sensors can be used: the sensors used for general reservoir monitoring and/or the sensors used for leak detection, soil heating, and temperature mapping. Alternatively, a special type of sensor can be designed and provided for the purpose of monitoring the status of seawater advance toward fresh water aquifers.

Abstract: A Tracking Dip Estimator software including a novel Multi-Sine Tracking Software is adapted to be stored in a computer system memory for instructing a processor to produce a “first output” including a plurality of tracks in response to input borehole image data, and a “second output” including a plurality of “dip data” d in response to the plurality of tracks, the Tracking Dip Estimator software generating the “first output” and “second output” by: (1) pre-processing the input borehole image data with a Detector to output a plurality of image edge elements called “reports”, (2) using the reports as input to a Multi-Sine Tracking software that recursively develops a “first output” including a plurality of tracks, or a plurality of connected sets of track points, lying along sinusoidal dip events in the input borehole image data; the Multi-Sine Tracking software has embedded mathematical models for sinusoidal dip events, (3)

Abstract: Methods for locating an oil-water interface in a petroleum reservoir include taking resistivity and pressure measurements over time and interpreting the measurements. The apparatus of the invention includes sensors preferably arranged as distributed arrays. According to a first method, resistivity and pressure measurements are acquired simultaneously during a fall-off test. Resistivity measurements are used to estimate the radius of the water flood front around the injector well based on known local characteristics. The flood front radius and fall-off pressure measurements are used to estimate the mobility ratio. According to a second method, resistivity and pressure measurements are acquired at a variety of times. Prior knowledge about reservoir parameters is quantified in a probability density function (pdf). Applying Bayes' Theorem, prior pdfs are combined with measurement results to obtain posterior pdfs which quantify the accuracy of additional information.

Abstract: A system and method for evaluating a geological formation is described which compares actual wireline log measurements from a number of wireline logging tools to predicted tool response logs. The system and method uses a forward model of each tool response, given a formation description, to predict a set of wireline logs. Comparing the predicted logs with the actual measured logs yields a mismatch error. The system and method iteratively adjusts the formation description to minimize the mismatch error to obtain a "best" formation description. In one form, the formation description includes petrophysical properties (porosity, density, saturation) and geometry properties (dip, bedding, invasion). In a more complicated form, the formation description also includes a model of petrophysical mixing laws and formation material content. In the special case of a horizontally layered formation and linear tool response models, there exists a computationally efficient version of the system and method.

Abstract: Due to irregularities associated with the borehole of an oil well, a depth determination system for a well logging tool, suspended from a cable in the borehole of the oil well, produces a correction factor, which factor is added to or subtracted from a surface depth reading on a depth wheel, thereby yielding an improved indication of the depth of the tool in the borehole. The depth determination system includes an accelerometer on the tool, a depth wheel on the surface for producing a surface-correct depth reading, a computer for a well logging truck and a depth determination software stored in the memory of the computer. The software includes a novel parameter estimation routine for estimating the resonant frequency and the damping constant associated with the cable at different depths of the tool in the borehole.