Schlumberger Technology Corporation

Onesubsea IP UK Limited

Services Petroliers Schlumberger

Geoquest Systems B.v.

Nader Salman

Shashi Menon

Hans Eric Klumpen

Jing Zhang

Colin Wier

Neeraj Kamat

Hemant Arora

Debasish Das

Federico Sporleder

Gian-Marcio Gey

Stephanie Lee

Harshada Modak

David Seabrook

Rajarshi Ray

Guido Johannes Van Der Hoff

Michael Hermann Nickel

Mats Stivang Ramfjord

Julius Kusuma

Victor Aarre

Sepand Ossia

Dmitriy Gennadyevich Repin

Jack Vincent

Hilde Grude Borgos

Lukasz Zielinski

Edo Vincent Hoekstra

Ahmed Adnan Aqrawi

Bjarte Dysvik

Francis Grady

Matthieu Georges Maroun Najm

Pål Kjetil Kvamme

Victor Amblard

Vahagn Hakopian

Guillaume Le Moing

Olesya Zimina

Qiang Fu

Matthias Cremieux

Paal Kjetil Kvamme

Ahmed Adnan Agrawi

Pal Kjetil Kvamme

A method may include receiving a sustainability model indicative of expected sustainability parameters associated with implementing action plans that correspond to enterprise operations of an enterprise over a period of time, such that the enterprise operations correspond to production data performed in a hydrocarbon production system, facility data corresponding to buildings associated with the enterprise, or both. The method may also include receiving an indication to optimize one sustainability parameter and identifying an engineering workflow system that improves a first sustainability parameter associated with the one sustainability parameter. The method may involve sending the sustainability model to the engineering workflow system and receiving an action plan to improve the sustainability parameter, such that commands may be sent to devices based on the action plan to cause the one or more devices to adjust one or more respective operations.

Optimizing sustainability parameters with action plans for an enterprise

A method may include receiving production data and facility data associated with an enterprise, such that the production data includes operational tasks performed in a hydrocarbon production system, and the facility data includes one or more utility operations within one or more buildings associated with the enterprise. The method may also include receiving sustainability parameter data associated with one or more operations corresponding to the enterprise based on the production data and the facility data, generating a sustainability report representative of sustainability parameters associated with the operations of the enterprise based on the sustainability parameter data, and sending the sustainability report to one or more engineering workflow systems to determine action plans associated with improving the sustainability parameters. After receiving the action plans, the method includes sending commands to cause devices to adjust their respective operations.

Managing facility and production operations across enterprise operations to achieve sustainability goals

A method may include receiving a sustainability model indicative of a plurality of sustainability parameters associated with enterprise operations corresponding to production data for operational tasks performed in a hydrocarbon production system, facility data corresponding to utility operations within buildings associated with the enterprise, or both. The method involves simulating implementing action plans via devices that correspond to the enterprise operations over time to determine an amount of greenhouse gas (GHG) emissions associated with the enterprise over time, generating a GHG footprint evolution report based on the amount of GHG emissions, and identifying at least one of a plurality of engineering workflow systems to reduce the amount of GHG emissions based on the GHG footprint evolution report. The method involves sending commands to devices of the plurality of devices based on the action plan, such that the commands are cause the devices to adjust their operations.

Optimizing green house gas sustainability with action plans for an enterprise

A method includes receiving sustainability datasets associated with enterprise operations of an enterprise, such that the enterprise operations correspond to production data performed in a hydrocarbon production system, facility data related to utility operations within buildings associated with the enterprise, or both. The method may involve determining that one or more sustainability alerts are present for the enterprise operations based on the sustainability datasets; and identifying assets of the hydrocarbon production system, the one or more buildings, or both associated with the one or more sustainability alerts in response to determining that the one or more sustainability alerts are present. The method may include retrieving asset data associated with the assets, sending the asset data to engineering workflow systems, receiving updated action plans from the engineering workflow systems, and sending commands to devices to adjust operations based on the updated action plans.

Updating sustainability action plan for an enterprise based on detected sustainability alert

A method may include receiving production data and facility data associated with an enterprise, such that the production data includes operational tasks performed in a hydrocarbon production system and wherein the facility data includes utility operations within buildings associated with the enterprise. The method may involve receiving sustainability parameter data associated with operations corresponding to the enterprise based on the production data and the facility data, generating a sustainability report representative of sustainability parameters associated with the operations of the enterprise based on the sustainability parameter data, and sending the sustainability report to one or more engineering workflow systems to determine action plans associated with improving a portion of the sustainability parameters associated with the operational tasks. The method may then send commands to devices associated with the hydrocarbon production system based on the action plans, such that the commands cause the devices to adjust their respective operations.

Managing production operations to achieve sustainability goals

An enterprise system may include one or more devices with sensors that measure operational parameters of the devices. The enterprise system may also include a sustainability platform system that obtains a sustainability model representative of a state of operations of the enterprise based on the measured operational parameters and receives sustainability target data that includes one or more threshold limits, one or more ranges, or both for one or more sustainability parameters. The sustainability platform system may also obtain one or more action plans for adjusting respective operations of the devices based on the sustainability model and the sustainability target data, simulate a performance of the action plans over a period of time relative to the sustainability parameters, and determine whether the simulated performance of the action plans is effective.

Predicting sustainability action plan performance over time

A method includes receiving an updated sustainability report associated with enterprise operations of an enterprise, such that the enterprise operations correspond to production data corresponding to operational tasks performed in a hydrocarbon production system, facility data corresponding to utility operations within buildings associated with the enterprise, or both. A computing system performing the method previously received a sustainability report associated with the enterprise operations. The method involves identifying at least one sustainability parameter change between the sustainability report and the updated sustainability report that is greater than at least one threshold, identifying engineering workflow systems to determine action plans associated with improving the at least one sustainability parameter, and sending the updated sustainability report to the one or more engineering workflow systems. The method may include sending commands to one or more devices associated with the one or more enterprise operations based on the action plans.

Updating sustainability action plans for an enterprise based on performance of previously implemented action plans

A method may include receiving production data and facility data associated with an enterprise, such that the production data includes operational tasks performed in a hydrocarbon production system and facility data includes utility operations within buildings associated with the enterprise. The method may involve receiving sustainability parameter data associated with corresponding to the enterprise based on the production data and the facility data. The method may include generating a sustainability report representative of sustainability parameters associated with the operations of the enterprise based on the sustainability parameter data, sending the sustainability report to engineering workflow systems that determine action plans associated with improving the sustainability parameters associated with the one or more utility operations, and sending commands to devices associated with the buildings based on the action plans, such that the commands cause the plurality of devices to adjust their respective operations.

Managing facility operations to achieve sustainability goals

Machine learning based methane emissions monitoring includes collecting sensor data from sensors and applying an augmentation model to the sensor data to form a regression training set. A classification training set for a classification model is created by replacing regression output values from the regression training set with classification output values. The classification output values include binary values. Machine learning based methane emissions monitoring further includes training the regression model with the regression training set to generate a regression prediction and training the classification model with the classification training set to generate a classification prediction.

Machine learning based methane emissions monitoring

A method can include receiving labeled images; acquiring unlabeled images; performing active learning by training an inspection learner using at least a portion of the labeled images to generate a trained inspection learner that outputs information responsive to receipt of one of the unlabeled images by the trained inspection learner; based at least in part on the information, making a decision to call for labeling of the one of the unlabeled images; receiving a label for the one of the unlabeled images; and further training the inspection learner using the label.

Active learning for inspection tool

Techniques for semantic segmentation of images are presented. The techniques include obtaining a semantic segmentation model, the semantic segmentation model having been trained using a first subset of sliding windows and corresponding first ground truth masks for the first subset of sliding windows; ranking a plurality of sliding windows from a corpus of training images according to an uncertainty metric; selecting a next subset of sliding windows from the corpus of training images based on the ranking and based on a similarity metric for one or more characteristics of a sliding window relative to other sliding windows; providing a collaborative user interface; receiving ground truth masks for the next subset of sliding windows using the collaborative user interface; and retraining the semantic segmentation model using the next subset of sliding windows and the ground truth masks for the next subset of sliding windows.

Adaptive learning for semantic segmentation

An active learning framework is provided that employs a plurality of machine learning components that operate over iterations of a training phase followed by an active learning phase. In each iteration of the training phase, the machine learning components are trained from a pool of labeled observations. In the active learning phase, the machine learning components are configured to generate metrics used to control sampling of unlabeled observations for labeling such that newly labeled observations are added to a pool of labeled observations for the next iteration of the training phase. The machine learning components can include an inspection (or primary) learning component that generates a predicted label and uncertainty score for an unlabeled observation, and at least one additional component that generates a quality metric related to the unlabeled observation or the predicted label. The uncertainty score and quality metric(s) can be combined for efficient sampling of observations for labeling.

Active learning framework for machine-assisted tasks

A method for controlling a subsea vehicle. The method includes receiving sensor data representing a subsea environment from one or more sensors of the subsea vehicle. The method identifies one or more objects present in the subsea environment based on the sensor data using an artificial intelligence machine. The method transmits at least a portion of the sensor data, including an identification of the one or more objects, to a user interface. The method includes receiving a requested vehicle task from the user interface. The requested vehicle task being selected by a user via the user interface. The method performs the requested vehicle task without vehicle position control from the user.

Systems and methods of pilot assist for subsea vehicles

Methods, computing systems, and computer-readable media for interpreting seismic data, of which the method includes receiving seismic data representing a subterranean volume, and determining a feature-likelihood attribute of at least a portion of a section of the seismic data. The feature-likelihood attribute comprises a value for elements of the section, the value being based on a likelihood that the element represents part of a subterranean feature. The method also includes identifying contours of the subterranean feature based in part on the feature-likelihood attribute of the section, and determining a polygonal line that approximates the subterranean feature.

Automatic feature extraction from seismic cubes

A method for detecting an unknown fault in a target seismic volume. The method includes generating a number of patches from a training seismic volume that is separate from the target seismic volume, where a patch includes a set of training areas, generating a label for assigning to the patch, where the label represents a subset, of the set of training areas, intersected by an known fault specified by a user in the training seismic volume, training, during a training phase and based at least on the label and the training seismic volume, a machine learning model, and generating, by applying the machine learning model to the target seismic volume during a prediction phase subsequent to the training phase, a result to identify the unknown fault in the target seismic volume.

Growing community of inventors

Arlington, MA, United States of America

Nader Salman