DD-Net: Dual Decoder Network With Curriculum Learning for Full Waveform Inversion

Deep learning full waveform inversion (DL-FWI) is gaining much research interest due to its high prediction efficiency, effective exploitation of spatial correlation, and lack of the need for an initial estimate. As a data-driven approach, it has several key issues. For example, effective deep netwo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-17
Main Authors: Zhang, Xing-Yi, Min, Fan, Pan, Shulin, Xu, Qiong, Min, Xue-Yang, Song, Guojie, Wang, Ke
Format: Article
Language:English
Subjects:
Convolution
Curricula
Curriculum
Datasets
Decoders
Decoding
Deep learning
Design
Fitting
Full waveform inversion
neural network
parallel decoder
Petroleum
seismic images
Source code
Spatial data
Stratigraphy
Synthetic data
Task analysis
Training
Transfer learning
Velocity
Waveforms
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning full waveform inversion (DL-FWI) is gaining much research interest due to its high prediction efficiency, effective exploitation of spatial correlation, and lack of the need for an initial estimate. As a data-driven approach, it has several key issues. For example, effective deep networks need to be designed, the training process needs to be controlled, and the generalization ability needs to be enhanced. In this article, we propose a dual decoder network (DD-Net) with curriculum learning to handle these issues. First, we design a U-Net with two decoders to grasp the velocity value and stratigraphic boundary information of the velocity model. These decoders' feedback will be combined at the encoder to enhance the encoding of edge spatial information. Second, we introduce curriculum learning to network training by organizing data in three difficulty levels. The easy-to-hard training process enhances the data fitting of the network. Third, we apply the network to low-resolution seismic observations via a prenetwork dimension reducer. This can serve as a general design idea without destroying the original network characteristics. Experiments are undertaken on SEG salt datasets and four synthetic datasets from OpenFWI. The results show that our network is superior to other state-of-the-art data-driven networks. The source code is available at github.com/fansmale/ddnet.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2024.3358492