Schlumberger Technology Corporation

Cameron International Corporation

Services Petroliers Schlumberger

Geoquest Systems B.v.

Jose Celaya Galvan

Velizar Vesselinov

Crispin Chatar

Soumya Gupta

Sergey Doronichev

Emilien Dupont

Carlos Boneti

Andrey Sergeevich Konchenko

Suhas Suresha

Neil Holger White Eklund

Xiaotong Suo

Vladimir Zhernakov

Valerian Guillot

George E Mahley, Iii

Oleg O Medvedev

Shu Pan

Erik Burton

Ivan Alaniz

Vishakh Hegde

Atsushi Morisato

John Z Pang

Jason M Dietrich

Anthony Lichnewsky

Indranil Roychoudhury

Mugdha Bhusari

Prasham Sheth

Anatoly Aseev

Laetitia Shao

A method may include receiving, via one or more processors, a set of image data representative of equipment configured to distribute a gas. The method may then involve determining a type of equipment depicted in the first set of image data, retrieving a leak detection model corresponding to the type of equipment depicted in the first set of image data, and determining that a gas leak is present on the equipment based on the set of image data and the leak detection model. After determining that the gas leak is present, the method may include sending a notification to a computing device in response to detecting the gas leak.

Detecting gas leaks from image data and leak detection models

A subsurface structure identification system includes one or more processors and a memory coupled to the one or more processors. The memory is encoded with instructions that when executed by the one or more processors cause the one or more processors to provide a convolutional neural network trained to identify a subsurface structure in an input migrated seismic volume, and to partition the input migrated seismic volume into multi-dimensional sub-volumes of seismic data. The instructions also cause the one or more processors to process each of the multi-dimensional sub-volumes of seismic data in the convolutional neural network, and identify the subsurface structure in the input migrated seismic volume based on a probability map of the input migrated seismic volume generated by the convolutional neural network.

System and method for identifying subsurface structures

A system and method that include receiving offset well data collected from an offset well, wherein the offset well data comprises data representing a trajectory of an offset. The system and method also include receiving subject well data comprising a trajectory of at least a portion of a subject. The system and method additionally include determining a similarity value between the trajectory of the offset well and the subject well. The system and method also include selecting at least one offset well for offset well analysis based on the similarity value. The system and method further include adjusting at least one parameter of the subject well based on the offset well analysis.

Offset well analysis using well trajectory similarity

A method includes receiving training images representing a portion of a drilling rig over a first period of time, associating individual training images of the training images with times at which the individual training images were captured, determining a rig state at each of the times, classifying the individual training images based on the rig state at each of the times, training a machine learning model to identify rig state based on the classified training images, receiving additional images representing the portion of the drilling rig over a second period of time, and determining one or more rig states of the drilling rig during the second period of time using the machine learning model based on the additional images.

Rig state detection using video data

A method including generating, by a navigation service, a route for navigating from a route origin to a route destination using a private roads repository. The method includes identifying a ghost origin and a ghost destination of a ghost road along the route. The method includes sending, using an application programming interface of a base roads engine, a first request for a route from the ghost origin to the ghost destination. The method includes receiving, from the base roads engine in response to the first request, a replacement section from the ghost origin to the ghost destination. The method includes replacing, in the route, the ghost road with the replacement section to create an updated route including segments. The method includes generating an estimated travel time from the route origin to the route destination over the segments of the updated route. The method includes presenting the estimated travel time.

System for offsite navigation

A method for predicting a stick-slip event includes measuring one or more surface properties using a sensor at the surface. The method also includes measuring one or more downhole properties using a downhole tool in a wellbore. The method also includes determining that the one or more surface properties and the one or more downhole properties match a distribution. The distribution occurs before two or more previously-detected stick-slip events. The method also includes determining a likelihood that a stick-slip event will occur based at least partially upon the distribution that the one or more surface properties and the one or more downhole properties match.

System and method for predicting stick-slip

A system can include a processor; memory operatively coupled to the processor; and processor-executable instructions stored in the memory to instruct the system to: receive a marker on a well log for a well in a geographic region; and iteratively propagate the marker automatically to a plurality of well logs for other wells in the geographic region.

Well log correlation and propagation system

A method for offset well analysis includes receiving offset well data collected from an offset well, the offset well data including data representing a trajectory of an offset well, receiving subject well data comprising a trajectory of at least a portion of a subject well, partitioning the trajectory of the offset well into a plurality of offset well segments, partitioning the trajectory of the subject well into a plurality of subject well segments, determining a distance between at least some of the plurality of offset well segments and at least some of the plurality of subject well segments, selecting the offset well based in part on the distance, and performing an offset well analysis using the offset well and the subject well.

A method, apparatus, and program product utilize a disentangled factor learning framework to analyze petro-technical image data such as seismic image data to infer properties of a subsurface volume and/or to generate image data for use in training machine learning algorithms for use in petro-technical applications.

Disentanglement for inference on seismic data and generation of seismic data

Bayesian recursive estimation is used to analyze performance parameters of a membrane separation system based on historical operational data of a membrane system. Bayesian estimation considers historical data over prior time intervals to predict future membrane separation performance to avoid unexpected downtime and unanticipated maintenance. A set of state variables used for modeling performance is used with a degradation model of to anticipate performance changes and maintenance based on measured properties of permeate, non-permeate, and feed flows.

Health management of membrane gas separation systems

Growing community of inventors

Sunnyvale, CA, United States of America

Jose Celaya Galvan