Full-waveform inversion is an important and widely used method to reconstruct subsurface velocity images. Waveform inversion is a typical nonlinear and ill-posed inverse problem. Existing physics-driven computational methods for solving waveform inversion suffer from the cycle-skipping and local-minima issues, and do not mention that solving waveform inversion is computationally expensive. In recent years, data-driven methods become a promising way to solve the waveform-inversion problem. However, most deep-learning frameworks suffer from the generalization and overfitting issue. In this article, we developed a real-time data-driven technique and we call it VelocityGAN, to reconstruct accurately the subsurface velocities. Our VelocityGAN is built on a generative adversarial network (GAN) and trained end to end to learn a mapping function from the raw seismic waveform data to the velocity image. Different from other encoder–decoder-based data-driven seismic waveform-inversion approaches, our VelocityGAN learns regularization from data and further imposes the regularization to the generator so that inversion accuracy is improved. We further develop a transfer-learning strategy based on VelocityGAN to alleviate the generalization issue. A series of experiments is conducted on the synthetic seismic reflection data to evaluate the effectiveness, efficiency, and generalization of VelocityGAN. We not only compare it with the existing physics-driven approaches and data-driven frameworks but also conduct several transfer-learning experiments. The experimental results show that VelocityGAN achieves the state-of-the-art performance among the baselines and can improve the generalization results to some extent.

Data-Driven Seismic Waveform Inversion: A Study on the Robustness and Generalization

Measuring three components of particle velocity along with the pressure brings significant benefits to towed marine seismic data. In addition to well-known deghosting benefits, we show that the particle velocity components add important constraints that enable reconstruction of the wavefield between the multicomponent streamers. Finally, we outline several cases of particular interest that will make towed marine seismic data more "3D like".

On the Use of Multicomponent Streamer Recordings for Reconstruction of Pressure Wavefields in the Crossline Direction

https://link.springer.com/content/pdf/10.1007/s12182-020-00431-3.pdf

A review on reflection-waveform inversion

Removing the receiver ghost before migration provides better low and high frequency response as well as a higher signal-to-noise ratio. We recognize these benefits for preprocessing steps like multiple suppression and velocity analysis. In this paper, we modify a previously published bootstrap approach that self-determines its own parameters for receiver deghosting in a x t  window. Similarly to the x t  bootstrap method, the recorded data is first used to create a mirror data set through a 1D ray-tracing-based normal moveout correction method. The recorded and mirror data are then transformed into p   domain and used to jointly invert for the receiver-ghost-free data. We apply this new algorithm to two field data sets with: 1) constant streamer depth of 27 m; and 2) variable streamer depth from 10 to 50 m. Our deghosting method effectively removes the receiver ghost, and the resulting image has broader bandwidth and a higher signal-to-noise ratio.

Premigration deghosting for marine streamer data using a bootstrap approach in tau-p domain

Full-waveform inversion (FWI), proposed by Lailly and Tarantola in the 1980s, is considered to be the most promising data-driven tool for automatically building velocity models. Many successful exa...

Full-waveform inversion for salt: A coming of age

Using full-waveform inversion (FWI) to update velocity models that contain salt bodies with high velocity contrasts is challenging. It is even harder if erroneous salt geometry is part of the velocity model. Shen et al. (2017) showed a successful FWI application that corrected some misinterpretation of salt structures and resulted in improved subsalt images at the Atlantis field in the Gulf of Mexico. Their study stressed the importance of the low frequencies (usable down to 1.6 Hz), full azimuths, and long offsets of OBN data. Encouraged by the success at Atlantis, we revisited some aspects of FWI algorithms to minimize cycle-skipping and amplitude discrepancy issues that are common in the presence of salt and salt misinterpretation. Here we present the use of traveltime misfit measured in frequency-dependent time windows as the FWI cost function. It is devised to minimize the negative impact from the amplitude discrepancy and cycleskipping between the recorded data and modeled synthetic data. Furthermore, we use the crosscorrelation coefficient between the recorded data and synthetic data as a weight function in gradient computation to promote traveltime measurements of higher quality. We demonstrate the effect of our approach using a full-azimuth streamer data set in an area of complex shallow salt bodies in the Gulf of Mexico.

Correcting for salt misinterpretation with full-waveform inversion

We investigated how current least-squares reverse time migration (LSRTM) methods perform on subsalt images. First, we compared the formulation of data-domain vs. image-domain least-squares migration (LSM), as well as methods using single-iteration approximation vs. iterative inversion. Next, we examined the resulting subsalt images of several LSRTM methods applied on both synthetic and field data. Among our tests, we found image-domain single-iteration LSRTM methods, including an extension from Guitton’s (2004) method in the curvelet domain, not only compensated for amplitude loss due to poor illumination caused by complex salt bodies, but also produced subsalt images with fewer migration artifacts in the field data. By contrast, an iterative inversion method showed its potential for broadening bandwidth in the subsalt, but was less effective in reducing noise. Based on our understanding, we summarize the current state of LSRTM for subsalt imaging, especially between singleiteration and iterative LSRTM methods.

Least-squares RTM: Reality and possibilities for subsalt imaging

FWI Imaging: Full-wavefield imaging through full-waveform inversion

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Ping Wang

Author Tools

Chat about Author