Linrong Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Linrong Wang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Fan Min
School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu, China
5 shared publications - Guojie Song
School of Sciences, Southwest Petroleum University, Chengdu 610500, China
3 shared publications - Shulin Pan
Southwest Petroleum University
3 shared publications - Shaowen Wang
Earth Systems Science and Engineering King Abdullah University of Science and Technology Thuwal Saudi Arabia
2 shared publications Tariq Alkhalifah
2 shared publicationsBenwen Zhang
School of Intelligent Science and Technology, Sichuan Minzu College, Kangding, China
1 shared publication
Latest Publications
- Open Access
- 1 December 2026
- Published by KEAI Publishing in Artificial Intelligence in Geosciences
- Vol. 7 (4)
Seismic data interpolation using implicit neural representations with Fourier–hash features
- 1 December 2026
- Published by KEAI Publishing in Artificial Intelligence in Geosciences
- Vol. 7 (4)
Open AccessSeismic data interpolation using implicit neural representations with Fourier–hash features
- Open Access
- 27 October 2026
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 3 (5)
G 2 IFWI: Gradient‐Coupled Diffusion Priors for Regularizing Implicit Full Waveform Inversion
Full waveform inversion (FWI) aims to recover high‐resolution subsurface velocity models but remains highly ill‐posed due to strong nonlinearity, cycle‐skipping, and solution non‐uniqueness. Implicit neural representations (INRs) with multiresolution hash encoding provide an efficient continuous parameterization for implicit FWI (IFWI). However, IFWI can still produce geologically unrealistic structures and spurious high‐frequency artifacts. We propose a learned regularization framework that integrates a denoising diffusion probabilistic model (DDPM) into multiresolution hash encoding‐based IFWI, as a Gradient‐Coupled Diffusion Prior for IFWI (IFWI). The inversion is guided by the joint optimization of the physics‐based IFWI gradient and the score gradient derived from the diffusion prior. If available, well‐log measurements are further imposed through guidance to anchor the inversion locally. Experiments on both synthetic examples and a challenging short‐offset field data set demonstrate that the proposed framework improves inversion stability, suppresses artificial high‐frequency features, and enhances reconstruction accuracy.
- 27 October 2026
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 3 (5)
Open AccessG 2 IFWI: Gradient‐Coupled Diffusion Priors for Regularizing Implicit Full Waveform Inversion
Full waveform inversion (FWI) aims to recover high‐resolution subsurface velocity models but remains highly ill‐posed due to strong nonlinearity, cycle‐skipping, and solution non‐uniqueness. Implicit neural representations (INRs) with multiresolution hash encoding provide an efficient continuous parameterization for implicit FWI (IFWI). However, IFWI can still produce geologically unrealistic structures and spurious high‐frequency artifacts. We propose a learned regularization framework that integrates a denoising diffusion probabilistic model (DDPM) into multiresolution hash encoding‐based IFWI, as a Gradient‐Coupled Diffusion Prior for IFWI (IFWI). The inversion is guided by the joint optimization of the physics‐based IFWI gradient and the score gradient derived from the diffusion prior. If available, well‐log measurements are further imposed through guidance to anchor the inversion locally. Experiments on both synthetic examples and a challenging short‐offset field data set demonstrate that the proposed framework improves inversion stability, suppresses artificial high‐frequency features, and enhances reconstruction accuracy.
- Open Access
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 66574-66592
Can Knowledge Distillation Enable Seismic Interpolation, Super-Resolution, and Denoising Simultaneously?
In seismic data processing, interpolation, super-resolution, and denoising are three key issues to improve data quality. While deep learning methods have successfully addressed one or two of these tasks, simultaneously resolving all three within a single network faces difficulties. These include conflicting objectives and complex network design. This paper proposes a heterogeneous knowledge distillation architecture comprising a teacher network (TNet) and a student network (SNet). TNet implements super-resolution and denoising tasks, while SNet implements interpolation task. This separation avoids goal conflicts between the networks. SNet retains TNet’s structure but reduces channels by half, simplifying both architectures. SNet combines data consistency loss and distillation loss. The data consistency loss integrates $\ell _{1}$ and multi-scale structural similarity. The distillation loss employs synchronous positive-negative learning. Consequently, SNet inherits TNet’s capabilities and further refines them during optimization. For comparison, we combine three interpolation algorithms with three super-resolution algorithms and select the one with the best performance. Experimental results on four field data show the superiority of our method over the counterpart in terms of data quality at a lower computational cost.
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 66574-66592
Open AccessCan Knowledge Distillation Enable Seismic Interpolation, Super-Resolution, and Denoising Simultaneously?
In seismic data processing, interpolation, super-resolution, and denoising are three key issues to improve data quality. While deep learning methods have successfully addressed one or two of these tasks, simultaneously resolving all three within a single network faces difficulties. These include conflicting objectives and complex network design. This paper proposes a heterogeneous knowledge distillation architecture comprising a teacher network (TNet) and a student network (SNet). TNet implements super-resolution and denoising tasks, while SNet implements interpolation task. This separation avoids goal conflicts between the networks. SNet retains TNet’s structure but reduces channels by half, simplifying both architectures. SNet combines data consistency loss and distillation loss. The data consistency loss integrates $\ell _{1}$ and multi-scale structural similarity. The distillation loss employs synchronous positive-negative learning. Consequently, SNet inherits TNet’s capabilities and further refines them during optimization. For comparison, we combine three interpolation algorithms with three super-resolution algorithms and select the one with the best performance. Experimental results on four field data show the superiority of our method over the counterpart in terms of data quality at a lower computational cost.
- 11 January 2024
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 89 (6) , F117-F128
FWI-WF: Robust full-waveform inversion using hybrid Wasserstein-1 and Fourier metrics
The performance of full-waveform inversion (FWI) in constructing high-resolution subsurface models is closely related to the design of mismatch functions. The least-squares norm (ℓ2) is commonly used; however, it is prone to local minima when high-quality initial guess and low-frequency data are unavailable. The Wasserstein-1 (W1) metric captures time shifts more effectively, but it may be plagued by imprecise deep structures. The Fourier metric leverages power spectra from simulated and observed data, offering higher-resolution updates near solutions. We develop a progressive waveform inversion method called FWI-WF using W1 and Fourier metrics. Specifically, in the early stage of inversion, we apply greater weight to the W1 metric for constructing a good background model and avoiding falling into local minima. Then, the Fourier metric gradually dominates to refine edges and deep structures, providing high-resolution inversion results. During the optimization process, we use automatic differentiation to improve inversion efficiency. Experimental results on three baseline geologic models indicate that FWI-WF outperforms three state-of-the-art methods.
- 11 January 2024
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 89 (6) , F117-F128
FWI-WF: Robust full-waveform inversion using hybrid Wasserstein-1 and Fourier metrics
The performance of full-waveform inversion (FWI) in constructing high-resolution subsurface models is closely related to the design of mismatch functions. The least-squares norm (ℓ2) is commonly used; however, it is prone to local minima when high-quality initial guess and low-frequency data are unavailable. The Wasserstein-1 (W1) metric captures time shifts more effectively, but it may be plagued by imprecise deep structures. The Fourier metric leverages power spectra from simulated and observed data, offering higher-resolution updates near solutions. We develop a progressive waveform inversion method called FWI-WF using W1 and Fourier metrics. Specifically, in the early stage of inversion, we apply greater weight to the W1 metric for constructing a good background model and avoiding falling into local minima. Then, the Fourier metric gradually dominates to refine edges and deep structures, providing high-resolution inversion results. During the optimization process, we use automatic differentiation to improve inversion efficiency. Experimental results on three baseline geologic models indicate that FWI-WF outperforms three state-of-the-art methods.
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-13
D2UNet: Dual Decoder U-Net for Seismic Image Super-Resolution Reconstruction
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.
- 5 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 61 (01962892) , 1-13
D2UNet: Dual Decoder U-Net for Seismic Image Super-Resolution Reconstruction
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
- Published by Elsevier in Expert Systems with Applications
- Vol. 213
Fast convex set projection with deep prior for seismic interpolation
- 13 November 2022
- Published by Elsevier in Expert Systems with Applications
- Vol. 213
Fast convex set projection with deep prior for seismic interpolation