Multi-Scale Acoustic Velocity Inversion Based on a Convolutional Neural Network

The full waveform inversion at this stage still has many problems in the recovery of deep background velocities. Velocity modeling based on end-to-end deep learning usually lacks a generalization capability. The proposed method is a multi-scale convolutional neural network velocity inversion (Ms-CNN...

Full description

Saved in:
Bibliographic Details
Published inRemote sensing (Basel, Switzerland) Vol. 16; no. 5; p. 772
Main Authors Li, Wenda, Wu, Tianqi, Liu, Hong
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.03.2024
Subjects
Acoustic velocity
Algorithms
Artificial neural networks
CNN
Data processing
Datasets
Deep learning
full-waveform inversion
Machine learning
Methods
multi-scale
Neural networks
seismic data
Tomography
Velocity
Waveforms
China
Online AccessGet full text

Cover

More Information
Summary:The full waveform inversion at this stage still has many problems in the recovery of deep background velocities. Velocity modeling based on end-to-end deep learning usually lacks a generalization capability. The proposed method is a multi-scale convolutional neural network velocity inversion (Ms-CNNVI) that incorporates a multi-scale strategy into the CNN-based velocity inversion algorithm for the first time. This approach improves the accuracy of the inversion by integrating a multi-scale strategy from low-frequency to high-frequency inversion and by incorporating a smoothing strategy in the multi-scale (MS) convolutional neural network (CNN) inversion process. Furthermore, using angle-domain reverse time migration (RTM) for dataset construction in Ms-CNNVI significantly improves the inversion efficiency. Numerical tests showcase the efficacy of the suggested approach.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs16050772