Neural-networks for geophysicists and their application to seismic data interpretation
It provides an incremental introduction to neural networks for geophysicists, aiming to facilitate faster and more accurate seismic interpretation.
The paper introduces neural networks to geophysicists for seismic data interpretation, demonstrating their utility in tasks like lithology interpolation, horizon tracking, and segmentation on field data from the Sea of Ireland and North Sea.
Neural-networks have seen a surge of interest for the interpretation of seismic images during the last few years. Network-based learning methods can provide fast and accurate automatic interpretation, provided there are sufficiently many training labels. We provide an introduction to the field aimed at geophysicists that are familiar with the framework of forward modeling and inversion. We explain the similarities and differences between deep networks to other geophysical inverse problems and show their utility in solving problems such as lithology interpolation between wells, horizon tracking and segmentation of seismic images. The benefits of our approach are demonstrated on field data from the Sea of Ireland and the North Sea.