PDF(6318 KB)
Automatic identification method for earthquake fault interpretation based on CBAM-UNet
Jun WANG, Yan ZHAO, GuoXiang GAO
Prog Geophy ›› 2026, Vol. 41 ›› Issue (4) : 1776-1785.
PDF(6318 KB)
PDF(6318 KB)
Automatic identification method for earthquake fault interpretation based on CBAM-UNet
For the automatic identification of seismic faults, this study adopts a U-Net model integrating the CBAM (Convolutional Block Attention Module) attention mechanism and residual structures. Based on the U-Net encoder-decoder framework, the model introduces residual modules to enhance feature transmission stability and employs the CBAM module to strengthen fault-related feature responses, thereby improving the model's ability to identify fault boundaries and spatial continuity. Experimental results show that the model performs well in terms of fault continuity and recognition accuracy. Validation on 2D field seismic data and 3D seismic data further demonstrates that the model can effectively identify major fault structures while maintaining good structural consistency. The results indicate that the model can provide a useful reference for automatic seismic fault interpretation.
Deep learning / Seismic fault identification / U-Net / Residual structure / CBAM attention mechanism
|
|
|
|
|
|
|
Czink N, Mecklenbrauker C. 2006. A novel automatic cluster tracking algorithm. //2006 IEEE 17th International Symposium on Personal, Indoor and Mobile Radio Communications. Helsinki: IEEE, 1-5.
|
|
|
|
|
|
|
|
He K M, Zhang X Y, Ren S Q, et al. 2016. Deep residual learning for image recognition. //Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 770-778.
|
|
Ito Y, Tanimoto K. 1972. Method of numerical analysis of wave propagation—application to wave diffraction and refraction—. //Coastal Engineering 1972. Vancouver: ASCE, 503-522.
|
|
|
|
|
|
Mao A, Mohri M, Zhong Y. 2023. Cross-entropy loss functions: Theoretical analysis and applications. //Proceedings of the 40th International Conference on Machine Learning. Honolulu: PMLR, 23803-23828.
|
|
Milletari F, Navab N, Ahmadi S A. 2016. Ⅴ-net: Fully convolutional neural networks for volumetric medical image segmentation. //2016 Fourth International Conference on 3D Vision (3DV). Stanford: IEEE, 565-571.
|
|
Ronneberger O, Fischer P, Brox T. 2015. U-net: Convolutional networks for biomedical image segmentation. //18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer International Publishing, 234-241.
|
|
|
|
Tran D, Bourdev L, Fergus R, et al. 2015. Learning spatiotemporal features with 3D convolutional networks. //Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 4489-4497.
|
|
Vaswani A, Shazeer N, Parmar N, et al. 2017. Attention is all you need. //Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 6000-6010.
|
|
|
|
Woo S, Park J, Lee J Y, et al. 2018. CBAM: Convolutional block attention module. //Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich: Springer, 3-19.
|
|
Wood J, Kirschenbauer S, Döllner J, et al. 2005. Using 3D in visualization. //Exploring Geovisualization. Amsterdam: Elsevier, 293-312.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
感谢审稿专家提出的修改意见和编辑部的大力支持！
/
| 〈 |
|
〉 |
