Building accurate training images for automatic seismic interpretation

摘要

Automatic propagation of real-world parent seismic images to efficiently generate a collection of realistic synthetic child training images to train a model for accurate automatic seismic interpretation. A 3D structural model in a present-day geological space (e.g., G_B) depicting subsurface locations of particles (e.g., in region B) may be transformed by a 3D coordinate space transformation (e.g., uvt_B) to a depositional space (e.g., G*_B) depicting past depositional locations of those particles (e.g., corresponding depositional region B). A real-world parent image depicting subsurface locations of particles (e.g., in region A) may be transformed, via a forward transformation (e.g., uvt_A), to a depositional seismic image in the depositional space of the three-dimensional structural model (e.g., G*_A=G*_B). A reverse transformation (e.g., uut_B⁻¹) may transform the depositional seismic image from the depositional space into synthetic child training images in the present-day geological space (e.g., G_B) for training the model.