Back to results
US 9,852,373 B2Granted
Properties link for simultaneous joint inversion
AssigneeWesternGeco L.L.C.
InventorMichele De Stefano
Life of this patent
Estimating the term…
Abstract
A method can include receiving data associated with a geologic environment; based on at least a portion of the data, estimating relationships for multiple properties of the geologic environment; and based at least in part on the relationships, performing simultaneous joint inversion for at least one property of the geologic environment.
Claims18
A method comprising:
- training an artificial neural network based at least in part on clustered geologic property input values wherein the trained artificial neural network approximates at least one probability density function with a shape governed by a cross-property covariance matrix;
- receiving data for a geologic environment as acquired by field equipment;
- based on the data, estimating relationships for multiple properties of the geologic environment via the trained artificial neural network;
- based at least in part on the relationships, performing simultaneous joint inversion for at least one property of the geologic environment;
- and
- based at least in part on at least one of the at least one property, identifying a location of hydrocarbons in the geologic environment.
3 more elements
A system comprising:
- a processor;
- memory operatively coupled to the processor;
- and
- processor-executable instructions stored in the memory to instruct the system to:
- train an artificial neural network based at least in part on clustered geologic property input values wherein the trained artificial neural network approximates at least one probability density function with a shape governed by a cross-property covariance matrix;
- receive data for a geologic environment as acquired by field equipment;
- based on the data, estimate relationships for multiple properties of the geologic environment via the trained artificial neural network;
- based at least in part on the relationship, perform simultaneous joint inversion for at least one property of the geologic environment;
- and
- based at least in part on at least one of the at least one property, identify a location of hydrocarbons in the geologic environment.
7 more elements
One or more non-transitory computer-readable storage media comprising computer-executable instructions to instruct a computer to:
- train an artificial neural network based at least in part on clustered geologic property input values wherein the trained artificial neural network approximates at least one probability density function with a shape governed by a cross-property covariance matrix;
- receive data for a geologic environment as acquired by field equipment;
- based on the data, estimate relationships for multiple properties of the geologic environment via the trained artificial neural network;
- based at least in part on the relationship, perform simultaneous joint inversion for at least one property of the geologic environment;
- and
- based at least in part on at least one of the at least one property, identify a location of hydrocarbons in the geologic environment.
3 more elements
Dependencies are inferred from the claim text.