Abstract: A method for estimating EM measurement uncertainty includes evaluating EM logging measurements with a trained machine learning model to estimate the measurement uncertainties of the EM logging measurements. The trained machine learning model is trained using a training data set made up of modeled EM logging measurements and corresponding measurement uncertainties.

Abstract: Embodiments presented provide for a method for defect recognition for pipes used in hydrocarbon recovery operations. In embodiments, a large foundation model is used to help automatically detect and characterize the defects, eliminating the need for expert analysis.

Abstract: Systems and methods are provided for analyzing sample images, such as for rock particles obtained during drilling of a geologic formation. The system and techniques utilize a Large Foundation Model (LFM) in the segmentation of rock particles. The LFM can receive an image (or image data) of rock particles as an input and generates segmentation of the image at a pixel level (i.e., each pixel of the image is classified) as a segmented image. Additionally, active annotation can be provided in conjunction with a graphics user interface (GUI) to allows for user interaction with images as well as selective segmentation of the images.

Abstract: A general-purpose workflow for automatic borehole sonic data classification to identify data into different physical categories and logging conditions, which are traditionally manually evaluated. The workflow uses machine learning techniques and physical knowledge for data classification, including pre-processing the high-dimensional high-quality dispersion modes extracted using a recently developed physical-driven ML enabled approach.

Abstract: A method can include receiving remarks associated with one or more field operations; processing the remarks for event detection using a dependency matcher and a machine learning model, where, responsive to the dependency matcher failing to detect an event, the processing implements the machine learning model to detect the event; and outputting at least the detected event.

Abstract: Embodiments presented provide for a detection of acoustic events during hydrocarbon recovery operations, such as during wireline investigations. In embodiments, an automated artificial intelligence method is used to analyze third interface echo events. Such analyzation allows operators to discriminate if the fluid within an annulus of the wellbore is a liquid, a solid or a gas.

Abstract: A method for detecting an object in a borehole includes acquiring at least two ultrasonic logs of a borehole section. Each of the ultrasonic logs includes ultrasonic measurements taken at a plurality of tool azimuths of a plurality of depths including a target depth. The method also includes inferring a VDL image relative to the target depth for each of the ultrasonic logs. Further, the method includes aligning the VDL images. Further still, the method includes merging the aligned VDL images into a high-resolution VDL image. Even further, the method includes detecting an object present in the borehole based on the high-resolution VDL image.

Abstract: Methods, computing systems, and machine-readable media for detecting downhole sand entry points are provided. A computing device receives a sand detection output of a product sand detection tool and a raw timeseries waveform corresponding to an input to the product sand detection tool. Based on the sand detection output, at least one downhole sand entry point is detected at a logging depth. In response to the detecting of the at least one downhole sand entry point. the computing device extracts a subset of features based on the raw timeseries waveform. The computing device determines whether the detecting is a true positive or a false positive based on the extracted subset of the features and a trained Random Forest classifier. A remedial action is performed regarding the at least one downhole sand entry point responsive to the determining that the detecting is the true positive.

Abstract: A method of producing a geothermal well includes obtaining site information including at least a site volume; obtaining drilling parameters; determining lengths and orientations of planned wellbores based at least partially on the site information and the drilling parameters.

Abstract: A system for wireline service planning and advising includes a receiver, one or more computing system processors, and a transmitter. The receiver is configured to receive, from a user of the system, an objective parameter for interpreting a state of a well barrier. The one or more computing system processors is in communication with the receiver and configured to generate a plurality of candidate services based on the objective parameter and a model of the well barrier, each candidate service specifying sensor data to be acquired using wireline tools, select at least one wireline service from the wireline candidate services based on a selection logic or input by the user, and generate an execution plan specifying operational parameters of the selected wireline service. The transmitter is in communication with the one or more computing system processors and configured to transmit the execution plan to execute the selected wireline service at a wellsite.

Abstract: A method can include acquiring acoustic signals responsive to emissions into equipment: and generating an output signal by inputting the acoustic signal into a machine learning model, where the output signal is indicative of a positional arrangement of two pieces of the equipment.

Abstract: A system and method for detecting defects in a tubular structure installed in a wellbore extending into a subterranean formation. An input image of the tubular structure contains input data indicative of a characteristic of the tubular structure. A background image is determined based on the input image. The background image contains background data indicative of the characteristic of the tubular structure associated with manufacturing of the tubular structure. A defect image is determined based on a difference between the input image and the background image. The defect image contains defect data indicative of the characteristic of the tubular structure associated with defects in the tubular structure.

Abstract: The disclosure relates to a method for flagging at least an event of interest in an unlabeled time series of a parameter relative to a wellsite (including to the well, formation or a wellsite equipment), wherein the time series of the parameter is a signal of the parameter as a function of time. The disclosure also relates to a method for evaluation a downhole operation such as a pressure test using a pressure time series. Such methods comprises collecting a time series, extracting at least an unlabeled subsequence of predetermined duration in the time series, and assigning an event of interest a label, in particular representative of the status of the downhole operation, to at least one of the unlabeled subsequences. A command may be sent to a wellsite operating system based on assigned label.

Abstract: Systems and methods presented herein include a cable spooling system that includes a drum configured to rotate about a central axis of the drum to wind and unwind a cable onto and from the drum as the drum rotates. The cable spooling system also includes one or more cameras configured to capture images of the drum as it rotates. The cable spooling system further includes one or more markers disposed on one or more flanges of the drum. The one or more markers are configured to be in view of the one or more cameras during a portion of rotation of the drum. In addition, the cable spooling system includes a data processing and control system configured to estimate an angular velocity of the drum using the images captured by the one or more cameras.

Abstract: Water detection and on-line measurement of water salinity is important for many applications in multiphase and wet gas flow metering. A system includes a sensor that measures a microwave signal reflected from a fluid and that generates measurement data based on the reflected microwave signal. The system also includes a processor that performs operations including receiving the measurement data, determining a set of fluid properties based on the measurement data, and receiving fluid classification data associated with the fluid; and generating a water in liquid ratio estimation or salinity value based on an analysis of the measurement data, the fluid classification data, the set of fluid properties, or any combination thereof.

Abstract: Embodiments of the present disclosure are directed towards systems and methods for automated stratigraphy interpretation from borehole images. Embodiments may include constructing, using at least one processor, a training set of synthetic images corresponding to a borehole, wherein the training set includes one or more of synthetic images, real images, and modified images. Embodiments may further include automatically classifying, using the at least one processor, the training set into one or more individual sedimentary geometries using one or machine learning techniques. Embodiments may also include automatically classifying, using the at least one processor, the training set into one or more priors for depositional environments.

Abstract: Using machine learning for sedimentary facies prediction by using one or more logs acquired in a borehole. This includes performing a petrophysical clustering of borehole depths wherein the depths of the borehole are gathered into clusters based on similarities in the one or more logs. Also performed is a log inclusion optimization, including a selection of one or more parameters of the petrophysical clustering, wherein the one or more parameters include a number and/or type of considered logs among the one or more logs and/or a clustering method. Also performed is a classification of the clusters into core depositional facies using one or more predetermined rules.

Abstract: The present disclosure introduces an apparatus including a toolstring for use in a tubular extending into a subterranean formation. The toolstring includes modular components that include one or more caliper modules and a power and control (P/C) module. The one or more caliper modules each include radially rotatable fingers for sensing an internal diameter of the tubular. The P/C module is operable for distributing power and control signals to the one or more caliper modules. The caliper and P/C modules are mechanically and electrically interconnected by common lower interfaces of the caliper and P/C modules.

Abstract: A system and method for detecting defects in a tubular structure installed in a wellbore extending into a subterranean formation. An input image of the tubular structure contains input data indicative of a characteristic of the tubular structure. A background image is determined based on the input image. The background image contains background data indicative of the characteristic of the tubular structure associated with manufacturing of the tubular structure. A defect image is determined based on a difference between the input image and the background image. The defect image contains defect data indicative of the characteristic of the tubular structure associated with defects in the tubular structure.

Abstract: The present disclosure introduces an apparatus including a toolstring for use in a tubular extending into a subterranean formation. The toolstring includes modular components that include one or more caliper modules and a power and control (P/C) module. The one or more caliper modules each include radially rotatable fingers for sensing an internal diameter of the tubular. The P/C module is operable for distributing power and control signals to the one or more caliper modules. The caliper and P/C modules are mechanically and electrically interconnected by common lower interfaces of the caliper and P/C modules.