Super-resolution reconstruction of digital rock CT images based on residual attention mechanism

Abstract

Computer tomography technology is widely used in geological exploration because it is a nondestructive and three-dimensional imaging method that can be integrated with computer simulation. However, the large-scale application of the computer tomography technique is limited by economic costs and time consumption. Therefore, it is challenging and intractable to indicate the pore structure characteristics of rock. To address this issue, a super-resolution reconstruction algorithm based on convolutional neural networks, residual learning, and attention mechanism was proposed to generate super-resolution images in this study. This algorithm was applied to the reconstruction of carbonate rock and sandstone. The performance of two-dimensional image reconstruction was evaluated by quantitative extraction and qualitative visualization. The results from experiments indicate that the built model performs well on different upscaling factors and is superior to the existing super-resolution approaches based on convolutional neural network.

Cited as: Shan, L., Bai, X., Liu, C., Feng, Y., Liu, Y., Qi, Y. Super-resolution reconstruction of digital rock CT images based on residual attention mechanism. Advances in Geo-Energy Research, 2022, 6(2): 157-168. https://doi.org/10.46690/ager.2022.02.07

References

Andhumoudine, A. B., Nie, X., Zhou, Q., et al. Investigation of coal elastic properties based on digital core technology and finite element method. Advances in Geo-Energy Research, 2021, 5(1): 53-63.

Chen, R., Zhang, H., Liu, J. Multi-attention augmented network for single image super-resolution. Pattern Recognition, 2022, 122: 108349.

Dong, C., Loy, C.C., He, K., et al. Image super-resolution using deep convolutional networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38(2): 295-307.

Dong, C., Loy, C. C., Tang, X. Accelerating the super-resolution convolutional neural network. Paper Presented in Proceedings of the Computer Vision-ECCV European Conference, Amsterdam, The Netherlands, 11-14 October, 2016.

Engelmann, J. Lessmann, S. Conditional Wasserstein GANbased oversampling of tabular data for imbalanced learning. Expert Systems with Applications, 2021, 174: 114582.

Geng, T., Liu, X., Wang, X., et al. Deep shearlet residual learning network for single image super-resolution. IEEE Transactions on Image Processing, 2021, 30: 4129-4142.

He, D., Wang, L. Texture unit, texture spectrum, and texture analysis. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(4): 509-512.

He, K., Zhang, X., Ren, S., et al. Deep residual learning for image recognition. Paper Presented in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 26 June-1 July, 2016.

Ji, L., Lin, M., Jiang, W., et al. An improved method for reconstructing the digital core model of heterogeneous porous media. Transport in Porous Media, 2018, 121(2): 389-406.

Khan, A., Sohail, A., Zahoora, U. A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review, 2020, 53(8): 5455-5516.

Lin, C., Wu, Y., Ren, L., et al. Review of digital core modeling methods. Progress in Geophysics, 2018, 33(2): 679-689. (in Chinese)

Liu, J., Zhang, W., Tang, Y., et al. Residual feature aggregation network for image super-resolution. Paper Presented in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Washington, USA, 13-19 June, 2020.

Liu, S., Sang, S., Wang, G., et al. FIB-SEM and X-ray CT characterization of interconnected pores in high-rank coal formed from regional metamorphism. Journal of Petroleum Science and Engineering, 2017, 148: 21-31.

Liu, Y., Shan, L., Yu, D. An echo state network with attention mechanism for production prediction in reservoirs. Journal of Petroleum Science and Engineering, 2022, 209: 109920.

Popel, M., Tomkova, M., Tomek, J., et al. Transforming machine translation: A deep learning system reaches news translation quality comparable to human professionals. Nature Communications, 2020, 11(1): 4381.

Qiu, D., Zheng, L., Zhu, J., et al. Multiple improved residual networks for medical image super-resolution. Future Generation Computer Systems, 2021, 116: 200-208.

Shan, L., Cao, L., Guo, B. Identification of flow units using the joint of WT and LSSVM based on FZI in a heterogeneous carbonate reservoir. Journal of Petroleum Science and Engineering, 2018, 161: 219-230.

Shi, W., Caballero, J., Huszár, F., et al. Real-time single image and video super-resolution using an efficient subpixel convolutional neural network. Paper Presented in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 21-26 July, 2016.

Song, H., Jin, Y., Cheng, et al. Learning interlaced sparse Sinkhorn matching network for video super-resolution. Pattern Recognition, 2022, 124: 108475.

Vaswani, A., Shazeer, N., Parmar, N., et al. Attention is all you need. Paper Presented in Proceedings of the Neural Information Processing Systems, California, USA, 4-10 December, 2017.

Wang, H., Hu, Q., Wu, C., et al. Dclnet: Dual closed-loop networks for face super-resolution. Knowledge-Based Systems, 2021, 222: 106987.

Wang, Y. D., Armstrong, R. T., Mostaghimi, P. Boosting resolution and recovering texture of 2D and 3D micro-CT images with deep learning. Water Resources Research, 2020a, 56(1): e 2019WR026052.

Wang, Y., Teng, Q., He, X., et al. CT-image of rock samples super resolution using 3D convolutional neural network. Computers & Geosciences, 2019, 133: 104314.

Wang, Z., Chen, J., Hoi, S. C. Deep learning for image super-resolution: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020b, 43(10): 3365-3387.

Yang, Y., Zhou, Y., Blunt, M. J., et al. Advances in multiscale numerical and experimental approaches for multiphysics problems in porous media. Advances in Geo-Energy Research, 2021, 5(3): 233-238.

Zeng, Y., Xiao, Z., Hung, K.W., et al. Real-time video super resolution network using recurrent multi-branch dilated convolutions. Signal Processing: Image Communication, 2021, 93: 116167.

Zha, W., Li, X., Xing, Y., et al. Reconstruction of shale image based on Wasserstein Generative Adversarial Networks with gradient penalty. Advances in Geo-Energy Research, 2020, 4(1): 107-114.

Zhang, Y., Li, K., Li, K., et al. Image super-resolution using very deep residual channel attention networks. Paper Presented in Proceedings of the Computer Vision-ECCV European Conference, Munich, Germany, 8-14 September, 2018.

Zhang, Y., Tian, Y., Kong, Y., et al. Residual dense network for image restoration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(7): 2480-2495.

Zuo, J., Wang, Z., Zhang, Y., et al. Research on image super-resolution algorithm based on mixed deep convolutional networks. Computers & Electrical Engineering, 2021, 95: 107422.