System and method for interpretation of well data
AssigneeChevron U.S.A. Inc.
InventorsDavid A. Wilkinson, Tina Yu
Life of this patent
Estimating the term…
Abstract
Well log data is assigned depositional labels by a soft computing method. A model is trained on an expert-interpreted well log by segmenting, assigning fuzzy symbols to the segments, and calculating attribute values for units labeled by the expert. From these values, classifiers are trained for each of a number of depositional types. Finally, a model is developed for translating fuzzy symbols into depositional labels. Once trained, the model is applied to well log data.
Claims15
A method of interpreting well log data indicative of physical attributes of a portion of a subterranean formation comprising:
- partitioning the well log data into segments, each segment representing a respective contiguous portion of the extent of the logged well;
- defining a membership function for each segment, the membership function defining a degree to which each segment belongs to a defined set;
- and
- determining, based on attribute values derived from previously interpreted depositional units, and the membership functions, a depositional type for each segment.
A system for automated interpretation of well log data indicative of physical attributes of a portion of a subterranean formation comprising:
- a data storage device, configured and arranged to store the well log data;
- a processor, configured and arranged to execute machine executable instructions to partition the well log data into segments, each segment representing a respective contiguous portion of the extent of the logged well, to define a membership function for each segment, the membership function defining a degree to which each segment belongs to a defined set, and to determine, based on attribute values derived from previously interpreted depositional units, and the membership functions, a depositional type for each segment.
Dependencies are inferred from the claim text.