Abstract
Building realistic and reliable models of the subsurface is the primary goal of seismic imaging. We have constructed an ensemble of convolutional neural networks (CNNs) to build velocity models directly from the data. Most other approaches attempt to map full data into 2D labels. We exploit the regularity of seismic acquisition and train CNNs to map gathers of neighboring common midpoints (CMPs) to vertical 1D velocity logs. This allows us to integrate well-log data into the inversion. simplify the mapping by using the 1D labels, and accommodate larger dips relative to using single CMP inputs. We dynamically generate the training data in parallel with training the CNNs, which reduces over fitting. Data generation and training of CNNs is more computationally expensive than conventional full-waveform inversion (FWI). However, once the network is trained, data sets with similar acquisition parameters can be inverted much faster than with FWI. The multiCMP CNN ensemble is tested on multiple realistic synthetic models, performs well, and was combined with FWI for even better performance.