Shell Usa, Inc.

Shell Oil Comapny

Shell Internationale Research Maatschappij, B.v.

Russell David Potter

Donald P Griffith

Sam Ahmad Zamanian

Stéphane Youri Richard Michael Joachim Gesbert

Oriol Falivene Aldea

Thomas Patrick Etienne Krayenbuehl

Thomas Peter Merrifield

Alessandro Frascati

Satyakee Sen

Sergey Frolov

Michele Bolla Pittaluga

Tjipto Santoso

A method for training a backpropagation-enabled segmentation process is used for identifying an occurrence of a sub-surface feature. A multi-dimensional seismic data set with an input dimension of at least two is inputted into a backpropagation-enabled process. A prediction of the occurrence of the subsurface feature has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.

Method for predicting subsurface features from seismic using deep learning dimensionality reduction for segmentation

A method for improving a backpropagation-enabled process for identifying subsurface features from seismic data involves a model that has been trained with an initial set of training data. A target data set is used to compute a set of initial inferences on the target data set that are combined with the initial training data to define updated training data. The model is trained with the updated training data. Updated inferences on the target data set are then computed. A set of further-updated training data is defined by combining at least a portion of the initial set of training data and at least a portion of the target data and associated updated inferences. The set of further-updated training data is used to train the model. Further-updated inferences on the target data set are then computed and used to identify the occurrence of a user-selected subsurface feature in the target data set.

Method for identifying subsurface features

A method for training a backpropagation-enabled regression process is used for predicting values of an attribute of subsurface data. A multi-dimensional seismic data set with an input dimension of at least two is inputted into a backpropagation-enabled process. A predicted value of the attribute has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.

Method for predicting subsurface features from seismic using deep learning dimensionality reduction for regression

A method for a method for identifying a subsurface pore-filling fluid and/or lithology. A training set of field-acquired geophysical data and/or simulated geophysical data is provided to train a backpropagation-enabled process. The trained process is used on a field-acquired data set that is not part of the training set to infer presence of a subsurface pore-filling fluid and/or lithology.

Method for identifying subsurface fluids and/or lithologies

A distribution of sand sediment class in a subsurface of the Earth is identified. Three-dimensional stratigraphic images of sediment distribution in a subsurface of the Earth are constructed, including at least two depositional domains, by simulating sediment transport and deposition over a selected time interval of sediments originating from one or more clastic sediment input sources. The simulation uses at least two equilibrium surfaces bounding the at least two depositional domains and at least two sediment classes, and updates the equilibrium surfaces in a sequence of timesteps, by accounting for sediment feed from the one or more clastic sediment input sources, erosion and deposition in accordance with mass-balance equality constraints. The images are used to identify a distribution of sand sediment class in the subsurface of the Earth suitable for acquiring hydrocarbons or fresh water, or for storing gas or liquids.

Constructing stratigraphic images of sediment distribution in a subsurface of the earth

The computer system and computer-implemented method allow a user to position an interactive cursor my interaction with a user-input device, to select a point anywhere within a 3D seismic data volume that is visible on a display. In response, the computer dynamically calculates a horizon-based stratal slice that includes the user-selected point. A selected attribute rendering from seismic data that is contained within the horizon-based stratal slice is automatically calculated and dynamically shown on a second display.

Growing community of inventors

Houston, TX, United States of America

Russell David Potter