Data driven approach to develop petrophysical interpretation models for complex reservoirs

A system comprising:

• at least one processor;
• and
• a memory coupled to the at least one processor having instructions stored therein, which when executed by the processor, cause the at least one processor to perform a plurality of operations, including operations to:
• receive, from one or more formation evaluation sensors, measurements of formation parameters during a first stage of a downhole operation within a reservoir formation;
• determine a correlation between each of the formation parameters and a target parameter of the reservoir formation, based on the received measurements;
• select one or more of the formation parameters as input parameters for a symbolic regression model, based on the correlation determined for each formation parameter;
• train a symbolic regression model to generate a plurality of candidate formation models representing the target parameter of the reservoir formation, based on the selected input parameters;
• apply one or more optimizations to the plurality of candidate formation models to determine a target petrophysical model of the reservoir formation;
• and
• estimate values of the target parameter for at least one layer of the reservoir formation, based on the target petrophysical model, wherein a second stage of the downhole operation is performed within the at least one layer of the reservoir formation based on the estimated values of the target parameter.

A non-transitory computer-readable medium having instructions stored thereon, which, when executed by a computer, cause the computer to perform a plurality of operations, including operations to:

• receive, from one or more formation evaluation sensors, measurements of formation parameters during a first stage of a downhole operation within a reservoir formation;
• determine a correlation between each of the formation parameters and a target parameter of the reservoir formation, based on the received measurements;
• select one or more of the formation parameters as input parameters for a symbolic regression model, based on the correlation determined for each formation parameter;
• train a symbolic regression model to generate a plurality of candidate formation models representing the target parameter of the reservoir formation, based on the selected input parameters;
• apply one or more optimizations to the plurality of candidate formation models to determine a target petrophysical model of the reservoir formation;
• and
• estimate values of the target parameter for at least one layer of the reservoir formation, based on the target petrophysical model, wherein a second stage of the downhole operation is performed within the at least one layer of the reservoir formation based on the estimated values of the target parameter.