Semi-supervised Sequence Modeling for Elastic Impedance Inversion
This work addresses the lack of geophysical constraints in machine learning for seismic inversion, which is an incremental improvement for geophysics and energy exploration.
The authors tackled the problem of enforcing geophysical constraints in seismic inversion by developing a semi-supervised sequence modeling framework using recurrent neural networks for elastic impedance inversion from multi-angle seismic data, achieving an average correlation of 98% between estimated and target elastic impedance on a synthetic dataset.
Recent applications of machine learning algorithms in the seismic domain have shown great potential in different areas such as seismic inversion and interpretation. However, such algorithms rarely enforce geophysical constraints - the lack of which might lead to undesirable results. To overcome this issue, we have developed a semi-supervised sequence modeling framework based on recurrent neural networks for elastic impedance inversion from multi-angle seismic data. Specifically, seismic traces and elastic impedance (EI) traces are modeled as a time series. Then, a neural-network-based inversion model comprising convolutional and recurrent neural layers is used to invert seismic data for EI. The proposed workflow uses well-log data to guide the inversion. In addition, it uses seismic forward modeling to regularize the training and to serve as a geophysical constraint for the inversion. The proposed workflow achieves an average correlation of 98% between the estimated and target EI using 10 well logs for training on a synthetic data set.