基于增强残差特征蒸馏的地震图像超分辨率重建

吴迪; 刘刚; 陈麒玉; 崔哲思; 方洪峰; 张策

doi:10.3799/dqkx.2026.076

您当前的位置：

首页 >

文章列表页 >

基于增强残差特征蒸馏的地震图像超分辨率重建

更新时间：2026-10-15

- 基于增强残差特征蒸馏的地震图像超分辨率重建
- Seismic Image Super⁃Resolution Reconstruction Based on Enhanced Residual Feature Distillation
- 地球科学 2026年51卷第9期页码：3501-3512
- 作者机构：
  
  1.中国地质大学（武汉）国家地理信息系统工程技术研究中心，计算机学院，湖北武汉 430078
  2.中国地质大学（武汉）智能地学信息处理湖北省重点实验室，湖北武汉 430078
  3.自然资源信息管理与数字孪生工程软件教育部工程研究中心，湖北武汉 430078
  4.贵州省战略矿产智慧勘查重点实验室，贵州贵阳 550081
  5.自然资源部资源定量评价与信息工程重点实验室，湖北武汉 430078
- 作者简介：
  
  吴迪（1999—），男，硕士研究生，研究方向为智能地学信息处理、三维地质建模.ORCID：0009⁃0006⁃5062⁃0461. E⁃mail：wu.di666@qq.com
  刘刚，ORCID：0000⁃0002⁃9651⁃4473. E⁃mail：liugang@cug.edu.cn
- 基金信息：
  
  国家自然科学基金项目(42372345;42172333);湖北省自然科学基金项目(2025AFB179);贵州省科技重大专项(黔科合重大[2025]016)
- DOI：10.3799/dqkx.2026.076
  中图分类号： P618
- 收稿：2025-12-23，
  
  纸质出版：2026-09-30
- 稿件说明：
移动端阅览
吴迪，刘刚，陈麒玉，崔哲思，方洪峰，张策，2026.基于增强残差特征蒸馏的地震图像超分辨率重建.地球科学，51（9）：3501-3512.

Wu Di，Liu Gang，Chen Qiyu，Cui Zhesi，Fang Hongfeng，Zhang Ce，2026.Seismic Image Super⁃Resolution Reconstruction Based on Enhanced Residual Feature Distillation.Earth Science，51（9）：3501-3512.
吴迪，刘刚，陈麒玉，崔哲思，方洪峰，张策，2026.基于增强残差特征蒸馏的地震图像超分辨率重建.地球科学，51（9）：3501-3512. DOI： 10.3799/dqkx.2026.076.

Wu Di，Liu Gang，Chen Qiyu，Cui Zhesi，Fang Hongfeng，Zhang Ce，2026.Seismic Image Super⁃Resolution Reconstruction Based on Enhanced Residual Feature Distillation.Earth Science，51（9）：3501-3512. DOI： 10.3799/dqkx.2026.076.

摘要

地震图像超分辨率重建对提升地震资料解释与地质建模精度具有重要作用，但现有方法模型规模较大、计算开销高，在强噪声和复杂地质结构条件下细节恢复能力有限.针对上述问题，本文提出了基于增强型残差特征蒸馏生成对抗网络（ERFDN-GAN）的地震图像超分辨率重建方法.该方法以增强型残差特征蒸馏模块（ERFDB）为基本单元，通过特征蒸馏机制降低模型复杂度，并引入空间注意力和通道注意力以增强特征表达能力.实验表明，该方法在PSNR和SSIM等指标上整体优于目前代表性方法，并能在复杂场景下保持较低复杂度和稳定的重建性能.所提出的ERFDN-GAN方法兼顾效率与精度，为地震资料解释、地质建模以及多源地学数据采集和挖掘的智能化处理提供了技术支撑.

Abstract

Seismic image super-resolution reconstruction is of great significance for improving the accuracy of seismic interpretation and geological modeling. However

existing methods often suffer from large model sizes and high computational costs

and exhibit limited detail recovery capability under strong noise and complex geological structures. To address these issues

this paper proposes an enhanced residual feature distillation generative adversarial network (ERFDN-GAN) for seismic image super-resolution reconstruction. The network is built upon enhanced residual feature distillation blocks (ERFDBs)

where a feature distillation mechanism is employed to reduce model complexity. Spatial attention and channel attention mechanisms are further introduced to enhance feature representation capability. Experimental results demonstrate that the proposed method achieves overall superior performance compared with representative methods in terms of PSNR and SSIM

while maintaining low model complexity and stable reconstruction performance under complex scenarios. The proposed ERFDN-GAN method effectively balances computational efficiency and reconstruction quality

providing technical support for seismic interpretation

geological modeling

and the intelligent acquisition and mining of multi-source geoscience data.

关键词

Keywords

references

Bashir, S. M. A., Wang, Y., Khan, M., et al., 2021. A Comprehensive Review of Deep Learning⁃Based Single Image Super⁃Resolution. PeerJ Computer Science , 7 : e621 . https://doi.org/10.7717/peerj⁃cs.621

Cheng, Z. H., Yuan, Y. J., Liu, S., et al., 2023. Application of Wideband Wavelet Deconvolution for Tight Oil Exploration. Geophysical Prospecting for Petroleum , 62 ( 1 ): 119 - 129 (in Chinese with English abstract) .

Dong, X. T., Lu, S. P., Lin, J., et al., 2024a. Can Deep Learning Compensate for Sparse Shots in the Imaging Domain? A Potential Alternative for Reducing the Acquisition Cost of Seismic Data. Geophysics , 89(2): V119-V137. https://doi.org/10.1190/geo2022⁃0711.1

Dong, X. T., Wei, C. X., Zhong, T., et al., 2024b. Seismic Data Reconstruction Based on a Multicascade Self⁃Guided Network. Geophysics , 89(3): V179-V195. https://doi.org/10.1190/geo2022⁃0712.1

Duan, J., Zhang, G. L., Li, X. W., et al., 2024. Seismic Facies⁃Guided Trace⁃by⁃Trace High⁃Precision Strong and Weak Reflection Separation. IEEE Transactions on Geoscience and Remote Sensing , 62 : 5912317. https://doi.org/10.1109/TGRS.2024.3386749

Elgendy, N. H., Reda, M., Elmashaly, M. M., et al., 2025. Three⁃Dimensional Reservoir Modeling of the Pliocene Reservoir Based on Seismic Data Advances for New Prospect Assessment. Marine Georesources & Geotechnology , 43 ( 7 ): 1281 - 1298 . https://doi.org/10.1080/1064119X.2024.2400689

Hamida, A., Alfarraj, M., Al⁃Shuhail, A. A., et al., 2023. Facies⁃Guided Seismic Image Super⁃Resolution. IEEE Transactions on Geoscience and Remote Sensing , 61 : 4503213. https://doi.org/10.1109/TGRS.2023.3289151

Jiang, C., Lü, Z. Y., Fang, L. H., 2024. Earthquake Detection Model Trained on Velocity and Acceleration Records and Its Application in Xinfengjiang Reservoir. Earth Science , 49 ( 2 ): 469 - 479 (in Chinese with English abstract) .

Kong, L. H., Wang, Y. M., Chang, D. X., et al., 2022. Contour Enhanced Image Super⁃Resolution. Journal of Visual Communication and Image Representation , 89 : 103659. https://doi.org/10.1016/j.jvcir.2022.103659

Li, F., Sun, W. Y., Wang, R., et al., 2025. Seismic Petrophysical Modeling and Key Reservoir Parameter Prediction of Ultra⁃Deepwater and Ultra⁃Shallow Unconsolidated Sandstone Reservoirs. Natural Gas Industry , 45 ( 6 ): 112 - 120 (in Chinese with English abstract) .

Li, J. C., Fang, F. M., Li, J. Q., et al., 2021. MDCN: Multi⁃Scale Dense Cross Network for Image Super⁃Resolution. IEEE Transactions on Circuits and Systems for Video Technology , 31 ( 7 ): 2547 - 2561 . https://doi.org/10.1109/TCSVT.2020.3027732

Li, J. T., Wu, X. M., Hu, Z. X., 2022a. Deep Learning for Simultaneous Seismic Image Super⁃Resolution and Denoising. IEEE Transactions on Geoscience and Remote Sensing , 60 : 5901611. https://doi.org/10.1109/TGRS.2021.3057857

Li, X. G., Wu, X., 2020. Progresses of Artificial Intelligence on Seismic Data Processing and Interpretation Reviewed from SEG Annual Meetings. World Petroleum Industry , 27 ( 4 ): 27 - 35 (in Chinese with English abstract) .

Li, Y., Zhang, G. L., Du, H., et al., 2022b. Multiscale Adaptive Side Window Filtering and Its Application on Seismic Data. IEEE Geoscience and Remote Sensing Letters , 19 : 8026405. https://doi.org/10.1109/LGRS.2022.3147837

Lin, L., Zhong, Z., Cai, C. Y., et al., 2024. SeisGAN: Improving Seismic Image Resolution and Reducing Random Noise Using a Generative Adversarial Network. Mathematical Geosciences , 56 ( 4 ): 723 - 749 . https://do i.org/10.1007/s11004⁃023⁃10103⁃8

Liu, J. L., Cao, J. X., Zhao, L. S., et al., 2024. Super⁃Resolution Reconstruction of Seismic Images Based on Deep Residual Channel Attention Mechanism. IEEE Access , 12 : 149032 - 149044 . https://doi.org/10.1109/ACCESS.2024.3477984

Liu, Y. M., Wei, H. J., Yuan, S., et al., 2022. Random Noise Removal of Seismic Data Based on Convolutioncycle Generation Adversarial Network. Journal of Jilin University ( Information Science Edition ), 40 ( 2 ): 231 - 239 (in Chinese with English abstract) .

Min, F., Wang, L. R., Pan, S. L., et al., 2023. D2UNet: Dual Decoder U⁃Net for Seismic Image Super⁃ Resolution Reconstruction. IEEE Transactions on Geoscience and Remote Sensing , 61 : 5906913. https://doi.org/10.1109/TGRS.2023.3264459

Mousavi, S. M., Beroza, G. C., 2022. Deep⁃Learning Seismology. Science , 377 ( 6607 ): eabm4470 . https://doi.org/10.1126/science.abm4470

Mousavi, S. M., Beroza, G. C., 2023. Machine Learning in Earthquake Seismology. Annual Review of Earth and Planetary Sciences , 51 : 105 - 129 . https://doi.org/10.1146/annurev⁃earth⁃071822⁃100323

Ni, W. J., Liu, S. Y., Wang, L. P., et al., 2023. Wavelet Shaping Deconvolution Based on Deep Learning. Oil Geophysical Prospecting , 58 ( 6 ): 1313 - 1321 (in Chinese with English abstract) .

Piao, J., Xiong, J., Zheng, D. C., et al., 2026. Advances in Intelligent Processing of Seismic Data: Focal Mechanisms, Fault Zone Head Waves and Dynamic Triggering Detection and Analysis. Earth Science , 51 ( 1 ): 56 - 73 (in Chinese with English abstract)

Sun, Q. F., Xu, J. Y., Zhang, H. X., et al., 2022. Random Noise Suppression and Super⁃Resolution Reconstruction Algorithm of Seismic Profile Based on GAN. Journal of Petroleum Exploration and Production Technology , 12 ( 8 ): 2107 - 2119 . https://doi.org/10.1007/s13202⁃021⁃01447⁃0

Wang, F., Yin, D., Song, R. Y., 2023. Image Super⁃Resolution Using Only Low⁃Resolution Images. The Visual Computer , 39 ( 10 ): 5069 - 5084 . https://doi.org/10.1007/s00371⁃022⁃02646⁃4

Wu, H. B., Zhang, P. S., Xu, S. A., et al., 2025. Current Status and Future Trends of Seismic Prediction and Assessment Technology for Coalbed Methane Reservoirs. Coal Geology & Exploration , 53 ( 6 ): 233 - 245 (in Chinese with English abstract) .

Wu, X. M., Geng, Z. C., Shi, Y. Z., et al., 2020. Building Realistic Structure Models to Train Convolutional Neural Networks for Seismic Structural Interpretation. Geophysics , 85 ( 4 ): WA27 - WA39 . https://doi.org/10.1190/geo2019⁃0375.1

Wu, X. M., Liang, L. M., Shi, Y., et al., 2019. FaultSeg3D: Using Synthetic Data Sets to Train an End⁃to⁃End Convolutional Neural Network for 3D Seismic Fault Segmentation. Geophysics , 84 ( 3 ): IM35 - IM45 . https://doi.org/10.1190/geo2018⁃0646.1

Yuan, Y. J., Li, Y. C., Zhou, S. C., 2021. Multichannel Statistical Broadband Wavelet Deconvolution for Improving Resolution of Seismic Signals. IEEE Transactions on Geoscience and Remote Sensing , 59 ( 2 ): 1772 - 1783 . https://doi.org/10.1109/TGRS.2020.2997977

Zeng, D., Xu, Q., Pan, S. L., et al., 2023. Seismic Image Super⁃Resolution Reconstruction through Deep Feature Mining Network. Applied Intelligence , 53 ( 19 ): 21875 - 21890 . https://doi.org/10.1007/s10489⁃023⁃04660⁃y

Zhang, J. J., Yin, X. Y., Gu, Y. P., et al ., 2024. Sandstone Reservoir Rock Physics Modeling and Time⁃Lapse Seismic Analysis. Journal of Applied Geophysics , 222 : 105318. https://doi.org/10.1016/j.jappgeo.2024.105318

Zhao, Y. S., Yang, P., Xu, H. Q., et al., 2023. High⁃Resolution Seismic Processing Method Based on Tunable Factor Gabor Wavelet Transform. Oil Geophysical Prospecting , 58 ( 2 ): 345 - 350 (in Chinese with English abstract) .

Zhong, T., Yang, F. R., Dong, X. T., et al., 2024. SHBGAN: Hybrid Bilateral Attention GAN for Seismic Image Super⁃Resolution Reconstruction. IEEE Transactions on Geoscience and Remote Sensing , 62 : 5934312. https://doi.org/10.1109/TGRS.2024.3492142

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

贡嘎山东坡2022年泸定地震灾后滑坡区植被绿度演化特征

基于岩浆锆石微量元素的机器学习模型对斑岩铜矿成矿潜力的评估

准噶尔盆地西北缘哈山构造带断裂性质与演化

基于多普勒雷达的突发性灾害体智能识别

融合多源特征的轻量化深度学习跨场景滑坡智能识别