Schlumberger Technology Corporation

Schlumberger Canada Limited

Services Petroliers Schlumberger

Schlumberger Holdings Limited

Geoquest Systems B.v.

Aria Abubakar

Tarek M Habashy

Hiren Maniar

Ping Zhang

David Lee Alumbaugh

Haibin Di

Shashi Menon

Gong Li Wang

Vikas Jain

Guozhong Gao

Keli Sun

Jianguo Liu

Xiaoli Chen

Thomas D Barber

Edward Nichols

David Furse Allen

Frank Morrison

Vladimir L'vovich Druskin

Mandar Shrikant Kulkarni

Purnaprajna Raghavendra Mangsuli

Cen Li

John C Rasmus

Nicolae Moldoveanu

Peter T Wu

Raj Banerjee

Ridvan Akkurt

Koji Ito

Lin Liang

Sylvain Wlodarczyk

John Paul Horkowitz

Atul Laxman Katole

Valerian Guillot

Florent D'Halluin

Yun Lin

Tao Zhao

Po-Yen Wu

Zhun Li

Anisha Kaul

Jeff Spath

Michael Thambynayagam

R K Michael Thambynayagam

Supriya Gupta

Ashok Belani

Aaron Scollard

Helen Xiaoyan Zhong

Ettore Mirto

Xiao Bo Hong

Hui Xie

Tianxia Zhao

QingFeng Zhu

Mikhail Zaslavsky

Yao Feng

Sunil Manikani

Vanessa Simoes

Chunpeng Zhao

Timothy J Roberts

Stewart Smith

Wenyi Hu

Karan Pathak

Ekansh Verma

Preeti Gupta

Denzil Francis Crasta

Gayatri Novenita

Yan Kai Xu

Peter M Van Den Berg

Tarek Habashy

Thomas Daniel Barber

A method includes receiving seismic data and an initial velocity model, generating a first seismic image based at least in part on the seismic data and the initial velocity model, training a machine learning model to predict salt masks based at least in part on seismic images, merging the initial velocity model and the first salt mask to generate a first modified velocity model, generating an updated velocity model based at least in part on the first modified velocity model, generating a second seismic image based at least in part on the updated velocity model, predicting a second salt mask based at least in part on the second seismic image and the updated velocity model, using the trained machine learning model, and merging the updated velocity model and the second salt mask to generate a second modified velocity model.

Automatic salt geometry detection in a subsurface volume

A method for digitizing image-based data includes receiving an image file including one or more target objects, generating an intermediate image by removing noise from the image file using a denoising machine learning model, identifying the one or more target objects included in the intermediate image using an object segmentation machine learning model, discretizing the one or more target objects that were identified using the trained object segmentation machine learning model, and storing the one or more target objects that were discretized in a data file, visualizing the one or more target objects, or both.

Raster image digitization using machine learning techniques

A method includes determining a top of salt (TOS) surface in a seismic volume based on a crossline direction of the seismic volume and an inline direction of the seismic volume. The method also includes determining a binary mask based upon the TOS surface. The method also includes sampling seismic data in the seismic volume to obtain a training seismic slice. The method also includes sampling the binary mask to obtain a mask slice. The method also includes selecting a first coordinate in the training seismic slice to produce a first tile. The method also includes selecting a second coordinate in the mask slice to produce a second tile. The method also includes generating or updating a model of the seismic volume based upon the first tile and the second tile.

Cascaded machine-learning workflow for salt seismic interpretation

A method includes receiving geophysical data representative of a geophysical structure; providing the geophysical data as one or more input data to a neural network; training the neural network to reconstruct the geophysical structure that was received and provide one or more uncertainty metrics for one or more features of the geophysical structure that is reconstructed; reconstructing, using the neural network that has been trained, the geophysical structure; and determining, using the neural network that has been trained, the one or more uncertainty metrics by implementing a second drop out condition on the one or more nodes of the one or more hidden layers of the neural network. The training is performed at least partially by implementing a first drop out condition on one or more nodes of one or more hidden layers of the neural network to randomly set an output of the one or more nodes to zero.

Uncertainty analysis for neural networks

A method includes receiving seismic training data comprising a plurality of images each including a plurality of traces, predicting a location of a feature in at least some of the plurality of traces based on a location of an amplitude peak therein, applying labels to the locations, classifying pixels of the plurality of images as representing the feature or not representing the feature, using a semantic segmentation model, adjusting the labels based on the classification of the pixels, training, using the adjusted labels and the seismic training data, a machine-learning model to identify the feature, and identifying the feature in a different seismic data set using the trained machine-learning model.

Feature detection in seismic data

A method includes receiving historical well-production data, and determining curve parameters based on the historical well production data. Determining the curve parameters includes accounting for uncertainty. The method also includes determining curve fits for the historical data based on the curve parameters using a plurality of models, calculating accuracy for each of the models based on a comparison of the curve fits to the well-production data, comparing the accuracy for each of the models using an information criteria that accounts for uncertainty, selecting one of the models based on the comparison, and determining an estimated ultimate recovery (EUR) for the well using at least the selected one of the models.

Probabilistic oil production forecasting

A machine-implemented method, at least one non-transitory computer-readable medium storing instructions, and a computing system are provided for attenuating noise. A computing system receives a seismic image and generates a first image using a first neural network configured to identify low-frequency ground roll in a seismic image, and a second image using a second neural network configured to identify reflections in the seismic image. A combined image is generated by combining the first image and the second image. The first neural network and the second neural network are adjusted to reduce a difference between the combined image and the seismic image using frequency constraint to guide separation of the seismic image into the first image and the second image.

Ground roll attenuation using unsupervised deep learning

A method can include receiving well logs, as series data, for wells, where the well logs represent stratigraphic characteristics of a field; for each of the well logs, generating a corresponding vector representation in a dimensional space using a transformer encoder; and determining similarity of the well logs via their corresponding vector representations to characterize well log quality for well log correlation of the field.

Well log correlation system

Systems, computer-readable media, and methods are provided. Blended baseline data is generated by numerically blending unblended baseline data according to a simultaneous shooting schedule scheme. Pseudo-deblended baseline seismic data is generated by applying a pseudo-deblending procedure to the blended baseline data. Machine learning labels are generated from common gathers of the pseudo-deblended baseline data and the unblended baseline data. A neural network is trained using the labels, the common gathers of the pseudo-deblended baseline data, and the unblended baseline data to produce common gathers of deblended baseline seismic data from the common gathers of the pseudo-deblended baseline seismic data.

Simultaneous shooting time-lapse seismic data deblending for CO2 monitoring and time lapse simultaneous shooting scheme recommender

A method includes receiving first training well logs, generating second training well logs by injecting one or more different types of systematic errors, random errors, or both into at least a portion of the first training well logs, training a machine learning model to correct well logs by configuring the machine learning model to reduce a dissimilarity between at least a portion of the first and second training well logs, receiving one or more implementation well logs, and generating one or more corrected well logs by correcting at least a portion of the one or more implementation well logs using the machine learning model that was trained.

Automatic well log correction

A method includes receiving well log data comprising a plurality of well logs, identifying one or more sections of one or more well logs of the plurality of well logs that have substantially complete data, training a reconstruction neural network to reconstruct incomplete well logs based on the one or more sections of the one or more well logs that have substantially complete data, and reconstructing one or more incomplete well logs of the plurality of well logs using the reconstruction neural network.

Unsupervised well log reconstruction and outlier detection

A method for seismic processing includes extracting, using a first machine learning model, one or more seismic features from seismic data representing a subsurface domain, receiving one or more well logs representing one or more subsurface properties in the subsurface domain, and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain at a location that does not correspond to an existing well based on the seismic data, the one or more well logs, and the one or more seismic features that were extracted from the seismic data.

Subsurface property estimation in a seismic survey area with sparse well logs

A method and apparatus for subsurface data processing includes determining a set of clusters based at least in part on measurement vectors associated with different depths or times in subsurface data, defining clusters in a subsurface data by classes associated with a state mode, reducing a quantity of the subsurface data based at least in part on the classes, and storing the reduced quantity of the subsurface data and classes with the state model in a training database for a machine learning process.

Apparatus and methods for improved subsurface data processing systems

A training log is selected from a plurality of well logs. A log window of a plurality of log windows is selected from the training log. A positive window is generated from the log window. A negative window is selected from the training log. A siamese neural network (SNN) is trained that includes a first self attention neural network (ANN) and a duplicate self attention neural network with the log window, the positive window, and the negative window, to recognize a similarity between the log window and the positive window and to differentiate against the negative window.

Machine learning based approach to detect well analogue

A computer-implemented method includes receiving a test seismic dataset associated with a known truth interpretation, receiving one or more hard constraints, training a machine learning system based on the test seismic dataset, the known truth interpretation, and the one or more hard constraints, determining an error value based on the training the machine learning system, adjusting the error value based on one or more soft constraints, updating the training of the machine learning system based on the adjusted error value, receiving a second seismic dataset after the updating the training; applying the second seismic dataset to the machine learning system to generate an interpretation of the second seismic dataset, generating a seismic image representing a subterranean domain based on the interpretation of the second seismic dataset, and outputting the seismic image.

Training a machine learning system using hard and soft constraints

Growing community of inventors

North Reading, MA, United States of America

Aria Abubakar