Uncertainty Maps for Seismic Images through Geostatistical Model Randomization

Much of the difficulties in characterizing complex reservoirs are related to the uncertainty associated with seismic interpretation. In this project, we examine two such sources: uncertainty in the velocity model, and ambiguities with expert interpretation due to conceptual geological uncertainty of reservoir structure. We address the first issue by presenting a geostatistical method for generating multiple velocity models to capture this uncertainty. We take this a step further by obtaining a set of migrated images using these multiple models, and build uncertainty maps based on local Euclidean and Procrustes distances between the migrated images. These uncertainty maps can aid an interpreter in deciding a) if certain structures actually are present in the image and b) the spatial placement of existing structures. An illustration to subsalt imaging is provided.