A Physics-Based Neural-Network Way to Perform Seismic Full Waveform Inversion

Abstract

Seismic full waveform inversion is a common technique that is used in the investigation of subsurface geology. Its classic implementation involves forward modeling of seismic wavefield based on a certain type of wave equation, which reflects the physics nature of subsurface seismic wavefield propagation. However, obtaining a good inversion result using traditional seismic waveform inversion methods usually comes with a high computational cost. Recently, with the emerging popularity of deep learning techniques in various computer vision tasks, deep neural network (DNN) has demonstrated an impressive ability in dealing with complex nonlinear problems, including seismic velocity inversion. Now, extensive efforts have been made in developing a DNN architecture to tackle the problem of seismic velocity inversion, and promising results have been achieved. However, due to the dependence of a labeled dataset, i.e., the barely accessible true velocity model corresponding to real seismic data, the current supervised deep learning inversion framework may suffer from limitations on generalization. One possible solution to mitigate this issue is to impose the governing physics into this kind of purely data-driven method. Thus, following the procedures of traditional seismic full waveform inversion, we propose a seismic waveform inversion network, namely SWINet, based on wave-equation-based forward modeling network cells. By treating the single-shot observation data and its corresponding shot position as training data pairs, the inverted velocity model can be obtained as the trainable network parameters. Moreover, since the proposed seismic waveform inversion method is performed in a neural-network way, its implementation and inversion effect could benefit from some built-in tools in Pytorch, such as automatic differentiation, Adam optimizer and minibatch strategy, etc. Numerical examples indicate that the SWINet method may possess great potential in resulting a good velocity inversion effect with relatively fast convergence and lower computation cost. INDEX TERMS acoustic wavefield modeling, deep learning inversion, seismic waveform inversion

Visual Relationship Detection with Multimodal Fusion and Reasoning

“…To determine whether two objects are related to one another, our proposed relationship proposal module is built on the feature extraction of the image module. The proposed relationship contains a multihead scaled dot-product attention sublayer [ 26 ], layer normalization [ 27 ], and N fully connected layers, where N is set to 3. The feature embedding of the feature extraction of an image module is denoted as , where K is the number of initial object-pairs.…”

Revisit Geophysical Imaging in A New View of Physics-informed Generative Adversarial Learning

“…velocity model obtained by using reverse-mode AD is the same as that computed in the adjoint state method. Yet other similar approaches were proposed in [60,61,62]. In [63], the authors improved upon [56] to perform inversions simultaneously for multiple parameters in elastic isotropic and anisotropic media.…”

Data-driven Full-waveform Inversion Surrogate using Conditional Generative Adversarial Networks

“…Convolutional neural networks (CNN) are getting more and more popular in geophysical applications, typically in classification and segmentation tasks [12], [13], [14], [15], and [16]. Moreover, recent studies have demonstrated the feasibility of geophysical modeling using CNNs [17], [18], and [19]. Fig.…”