Determination of shallow seabed compaction and elastic properties remains a challenge, with precise measurements only being available at limited regions of interest. Seismic data usually covers a large area, and it is possible to take advantage of this coverage to estimate those properties. By treating the shallow seafloor subsurface as a gradient like analytical model, we can train a neural network to estimate directly from the data the elastic parameters that correspond to the observed data and compare it to another common inversion technique. This work shows the results of the method applied to estimate P-wave properties.

Keywords:
upstream oil & gas, reservoir characterization, exploration geophysicist, colorado school, estimation, dataset, society, artificial intelligence, international, applied geoscience
Subjects:
Reservoir Characterization, Information Management and Systems, Seismic processing and interpretation, Neural networks
This content is only available via PDF.
Copyright 2022, Society of Exploration Geophysicists and the American Association of Petroleum Geologists
You can access this article if you purchase or spend a download.