2019/03/26 by Bas Peters, Eldad Haber, Peters, Bas +3 · 1 voice
Earth and Planetary Sciences · Engineering · #Seismic Imaging and Inversion Techniques #Reservoir Engineering and Simulation Methods #Hydraulic Fracturing and Reservoir Analysis
paper · pdf · doi:10.48550/arxiv.1903.11215
Neural-networks have seen a surge of interest for the interpretation of\nseismic images during the last few years. Network-based learning methods can\nprovide fast and accurate automatic interpretation, provided there are\nsufficiently many training labels. We provide an introduction to the field\naimed at geophysicists that are familiar with the framework of forward modeling\nand inversion. We explain the similarities and differences between deep\nnetworks to other geophysical inverse problems and show their utility in\nsolving problems such as lithology interpolation between wells, horizon\ntracking and segmentation of seismic images. The benefits of our approach are\ndemonstrated on field data from the Sea of Ireland and the North Sea.\n