Methods and systems for analyzing seismic amplitude

A machine-readable storage medium having stored thereon a computer program comprising a routine of set instructions for causing the machine to perform the steps of:

• identifying a seismic amplitude anomaly in seismic data of a portion of a subterranean formation;
• associating geological-property data and/or geophysical-parameter data corresponding to the seismic amplitude anomaly therewith;
• producing one or more seismic forward models each based on a scenario that accounts for an actual seismic amplitude response for the seismic amplitude anomaly and the geological-property data and/or geophysical-parameter data, wherein at least one of the one or more seismic forward models includes at least one seismic imaging artifact;
• adjusting input parameters for each of the one or more seismic forward models so that a seismic amplitude response produced by the seismic forward model at least substantially matches the actual seismic amplitude response for the seismic amplitude anomaly;
• training a supervised neural network using the one or more seismic forward models and corresponding adjusted input parameters;
• and
• generating a synthetic seismic forward model with the trained neural network.