Simultaneous shooting time-lapse seismic data deblending for CO2 monitoring and time lapse simultaneous shooting scheme recommender

A computing system, comprising:

• at least one processor;
• and
• a memory comprising at least one non-transitory, computer-readable medium storing instructions that, when executed by at least one of the at least one processor, cause the computing system to perform operations comprising:
• acquiring blended monitoring data, the blended monitoring data being blended according to a simultaneous shooting schedule scheme;
• generating pseudo-deblended monitoring data by applying a pseudo-deblending procedure to the blended monitoring data;
• generating common gathers of deblended monitoring data by inputting common gathers of the pseudo-deblended monitoring data to a neural network trained to produce the common gathers of the deblended monitoring data from the common gathers of the pseudo-deblended monitoring data produced from the blended monitoring data blended according to the simultaneous shooting schedule scheme;
• and
• the at least one processor sending a signal to a controller to cause a drilling tool to start performing a drilling operation in accordance with common gathers of deblended seismic data produced by the trained neural network,
• wherein the simultaneous shooting schedule scheme comprises firing a plurality of shots such that subsequent shots are fired before effects of a previous shot fade.

A non-transitory computer-readable medium having instructions for at least one processor stored thereon such that, when the at least one processor executes the instructions, the at least one processor performs operations comprising:

• acquiring unblended baseline seismic data;
• generating blended baseline seismic data by numerically blending the unblended baseline seismic data according to a simultaneous shooting schedule scheme to produce blended baseline seismic data;
• generating pseudo-deblended baseline seismic data by applying a pseudo-deblending procedure to the blended baseline seismic data;
• generating labels for machine learning from common gathers of the pseudo-deblended baseline seismic data and common gathers of the acquired unblended seismic data;
• training a neural network using the labels, the common gathers of the pseudo-deblended baseline seismic data, and the common gathers of the acquired unblended baseline seismic data, the neural network being trained to produce common gathers of deblended seismic data from the common gathers of the pseudo deblended baseline seismic data;
• and
• the at least one processor sending a signal to a controller to cause a drilling tool to start performing a drilling operation in accordance with the common gathers of deblended seismic data produced by the trained neural network,
• wherein the simultaneous shooting schedule scheme comprises firing a plurality of shots such that subsequent shots are fired before effects of a previous shot fade.