Machine learning training set generation
AssigneeSchlumberger Technology Corporation
InventorsAhmed Adnan Aqrawi, Nader Salman, Guido Johannes van der Hoff
Life of this patent
Estimating the term…
Abstract
Systems, computer-readable media, and methods for generating machine learning training data by obtaining reservoir data, determining subsections of the reservoir data, labeling the subsections of the reservoir data to generate labeled reservoir data, and feeding the labeled reservoir data into an artificial neural network. The reservoir data can be labeled using analysis data or based on interpretive input from an interpreter.
Claims20
A method, comprising:
- obtaining reservoir data from a storage medium, the reservoir data comprising seismic data unformatted for a machine learning model;
- and
- converting the reservoir data into a machine learning training data set by:
- segmenting, by a crawler application executed by a processor, at least a section of the reservoir data into a connected sequence of subsections;
- and
- labeling, by the crawler application, the connected sequence of subsections of the reservoir data to generate labeled reservoir data, wherein labeling comprises, for each subsection of the connected sequence of subsections:
- retrieving a portion of the reservoir data that is in the subsection,
- converting the portion of the reservoir data into an n-tuple, and
- labeling the subsection according to a type of the portion of the reservoir data.
A computing system comprising:
- one or more processors;
- and
- a memory system comprising one or more non-transitory, computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising:
- obtaining reservoir data from a storage medium, the reservoir data comprising seismic data unformatted for a machine learning model;
- and
- converting the reservoir data into a machine learning training data set by:
- segmenting, by a crawler application executed by a processor, at least a section of the reservoir data into a connected sequence of subsections;
- and
- labeling, by the crawler application, the connected sequence of subsections of the reservoir data to generate labeled reservoir data, wherein labeling comprises, for each subsection of the connected sequence of subsections:
- retrieving a portion of the reservoir data that is in the subsection,
- converting the portion of the reservoir data into an n-tuple, and
- labeling the subsection according to a type of the portion of the reservoir data.
A non-transitory, computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations, the operations comprising:
- obtaining reservoir data from a storage medium, the reservoir data comprising seismic data unformatted for a machine learning model;
- and
- converting the reservoir data into a machine learning training data set by:
- segmenting, by a crawler application executed by a processor, at least a section of the reservoir data into a connected sequence of subsections;
- and
- labeling, by the crawler application, the connected sequence of subsections of the reservoir data to generate labeled reservoir data, wherein labeling comprises, for each subsection of the connected sequence of subsections:
- retrieving a portion of the reservoir data that is in the subsection,
- converting the portion of the reservoir data into an n-tuple, and
- labeling the subsection according to a type of the portion of the reservoir data.
Dependencies are inferred from the claim text.