Revisit Geophysical Imaging in A New View of Physics-informed Generative Adversarial Learning
This work addresses geophysical imaging for subsurface modeling, offering a novel approach to improve inversion accuracy and robustness, though it appears incremental by building on existing neural network methods.
The authors tackled the challenges of seismic full waveform inversion, such as local minima and sensitivity to noise, by proposing an unsupervised physics-informed generative adversarial learning framework that accurately recovers synthetic models and outperforms classical algorithms.
Seismic full waveform inversion (FWI) is a powerful geophysical imaging technique that produces high-resolution subsurface models by iteratively minimizing the misfit between the simulated and observed seismograms. Unfortunately, conventional FWI with least-squares function suffers from many drawbacks such as the local-minima problem and computation of explicit gradient. It is particularly challenging with the contaminated measurements or poor starting models. Recent works relying on partial differential equations and neural networks show promising performance for two-dimensional FWI. Inspired by the competitive learning of generative adversarial networks, we proposed an unsupervised learning paradigm that integrates wave equation with a discriminate network to accurately estimate the physically consistent models in a distribution sense. Our framework needs no labelled training data nor pretraining of the network, is flexible to achieve multi-parameters inversion with minimal user interaction. The proposed method faithfully recovers the well-known synthetic models that outperforms the classical algorithms. Furthermore, our work paves the way to sidestep the local-minima issue via reducing the sensitivity to initial models and noise.