Building FWI starting model from wells with dynamic time warping and convolutional neural networks

Full waveform inversion (FWI) needs a feasible starting model, because otherwise it might converge to a local minimum and the inversion result might suffer from detrimental artifacts. We built a feasible starting model from wells by applying dynamic time warping (DTW) localized rewarp and convolutional neural network (CNN) methods alternatively. We used the DTW localized rewarp method to extrapolate the velocities at well locations to the non-well locations in the model space. Rewarping is conducted based on the local structural coherence which is extracted from a migration image of an initial infeasible model. The extraction uses the DTW method. The purpose of velocity extrapolation is to provide sufficient training samples to train a CNN, which maps local spatial features on the migration image into the velocity quantities of each layer. We further designed an interactive workflow to reject inaccurate network predictions and to improve CNN prediction accuracy by incorporating the Monte Carlo dropout method. We demonstrated that the proposed method is robust against the kinematic incorrectness in the migration velocity model, and is capable to produce a feasible FWI starting model.