GEO-PHLGAPP-PHFeb 8, 2020

ML-misfit: Learning a robust misfit function for full-waveform inversion using machine learning

arXiv:2002.03163v23 citations
AI Analysis

This work addresses the challenge of designing robust misfit functions for geophysical imaging, but it is incremental as it builds on existing optimal transport and meta-learning approaches.

The authors tackled the problem of data-dependent performance in hand-crafted misfit functions for full-waveform inversion by proposing ML-misfit, a machine-learned misfit function, which demonstrated effectiveness and robustness when applied to the Marmousi model.

Most of the available advanced misfit functions for full waveform inversion (FWI) are hand-crafted, and the performance of those misfit functions is data-dependent. Thus, we propose to learn a misfit function for FWI, entitled ML-misfit, based on machine learning. Inspired by the optimal transport of the matching filter misfit, we design a neural network (NN) architecture for the misfit function in a form similar to comparing the mean and variance for two distributions. To guarantee the resulting learned misfit is a metric, we accommodate the symmetry of the misfit with respect to its input and a Hinge loss regularization term in a meta-loss function to satisfy the "triangle inequality" rule. In the framework of meta-learning, we train the network by running FWI to invert for randomly generated velocity models and update the parameters of the NN by minimizing the meta-loss, which is defined as accumulated difference between the true and inverted models. We first illustrate the basic principle of the ML-misfit for learning a convex misfit function for travel-time shifted signals. Further, we train the NN on 2D horizontally layered models, and we demonstrate the effectiveness and robustness of the learned ML-misfit by applying it to the well-known Marmousi model.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes