Guojie Song

Prof. Dr. Guojie Song


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 April 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
FMfan min
fan min
LWLinrong Wang
Linrong Wang
PSPan Shulin
Pan Shulin
GSGuojie Song
Guojie Song
Super-resolution reconstruction is an essential task of seismic inversion due to the low resolution and strong noise of field data. Popular deep networks derived from U-Net lack the ability to recover detailed edge features and weak signals. In this paper, we propose a dual decoder U-Net (D 2 UNet) to explore both detail and edge information of the data. The encoder inputs the low resolution image and the edge image obtained through the Canny algorithm. Edge image can provide rich shape and boundary information, which is helpful to generate more accurate and high-quality data. The dual decoder consists of a main decoder for high-resolution recovery and an edge decoder for edge contour detection. These two decoders interact with a texture warping module (TWM) with deformable convolution. TWM aims to distort realistic edge details to match the fidelity of low resolution inputs, especially the location of edges and weak signals. The loss function is a combination of L 1 loss and multi-scale structural similarity loss (MS-SSIM) to ensure perception quality. Results on synthetic and field seismic images show that D 2 UNet not only improves the resolution of noisy seismic images, but also maintains the image fidelity.

13 November 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
FMfan min
fan min
LWLinrong Wang
Linrong Wang
PSPan Shulin
Pan Shulin
GSGuojie Song
Guojie Song

23 October 2022 in Artificial Intelligence Review
Verified
Journal Article
Closed access
PDF file
KQKun Qian
Kun Qian
XMXue-Yang Min
Xue-Yang Min
YCYusheng Cheng
Yusheng Cheng
GSGuojie Song
Guojie Song
FMfan min
fan min

14 February 2020 in Geophysics
Verified
Journal Article
Closed access
GSGuojie Song
Guojie Song
XZXinmin Zhang
Xinmin Zhang
ZWZhiliang Wang
Zhiliang Wang
YCYali Chen
Yali Chen
PCPuchun Chen
Puchun Chen
Viscous seismic wave propagation simulation using the fractional order equation has attracted much recent attention. However, conventional finite-difference (FD) methods of the fractional partial difference equation adopt a global difference operator to approximate the fractional derivatives, which reduces the computational efficiency dramatically. To improve the efficiency of the FD method, we have developed a reasonable truncated stencil pattern by strict mathematical derivation and adopted an asymptotic local FD (ALFD) method. Theoretical analysis and numerical results indicate that the ALFD method is accurate and efficient. In fact, our numerical results illustrate that the numerical solution solved by the ALFD method has a maximum relative error not exceeding 0.014% compared to the reference solution (applied to a finely meshed computational domain). The computation speed of ALFD is also significantly faster than that of the original FD method. The computational time of the three ALFD methods satisfying a different preset accuracy is only approximately 2.71%, 1.26%, and 0.78% of that of the original fractional wave equation FD method. The ALFD method provides a useful tool for viscoelastic seismic wavefield propagation simulation.

25 January 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
XZXing-Yi Zhang
Xing-Yi Zhang
FMfan min
fan min
PSPan Shulin
Pan Shulin
QXQiong Xu
Qiong Xu
XMXue-Yang Min
Xue-Yang Min
KWKe Wang
Ke Wang
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 paper, we propose a dual decoder network with curriculum learning (DD-Net) 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 pre-network 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.

29 June 2022 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
YWYinghe Wu
Yinghe Wu
PSPan Shulin
Pan Shulin
JCJingyi Chen
Jingyi Chen
GSGuojie Song
Guojie Song
QGQiyong Gou
Qiyong Gou
Surface-wave analysis methods have been widely applied to construct near-surface shear-wave velocity structures. Whether it is an active source or passive source, the near-surface shear-wave velocity structure is obtained by inverting the surface-wave dispersion curve. In order to solve the problems of low inversion efficiency and poor inversion results in traditional surface-wave exploration, we have studied the surface-wave inversion methods based on deep learning technology. In this study, we propose a long short-term memory (LSTM) surface-wave inversion method based on the first height last velocity (FHLV) loss function. The core of our proposed method is the FHLV loss function consisting of two parts: a speed loss and a thickness loss, which improves the overall prediction accuracy through optimizing the learning process of the thickness parameter by the network. To verify the accuracy of the proposed LSTM surface-wave inversion method based on the FHLV loss function, experiments are conducted on both synthetic and real datasets. The results show that our proposed method can efficiently and accurately invert the near-surface shear-wave velocity structure.