地震数据插值之深度学习方法

1. 支持向量回归

1. Jia, Y., and J. Ma, 2017, What can machine learning do for seismic data processing? An interpolation application: Geophysics, 82, no. 3, V163–V177, doi: 10.1190/geo2016-0300.1. (SVR 方法从训练数据中挖掘出一个连续回归超平面，该超平面指示具有缺失轨迹的输入数据与输出完整数据之间的隐藏关系，然后使用学习的超平面对其他输入数据插入缺失的地震轨迹.)

2. GAN

1. Dario, A. B. O., S. F. Rodrigo, S. Reinaldo, and E. V. Brazil, 2018, Inter- polating seismic data with conditional generative adversarial networks: IEEE Geoscience and Remote Sensing Letters, 15, 1952–1956, doi: 10 .1109/LGRS.2018.2866199. (插值叠后数据缺失间隙)
2. S. Alwon, “Generative adversarial networks in seismic data processing,” in Seg Technical Program Expanded Abstracts, pp. 1991-1995, Aug. 2018.
3. A. Siahkoohi, R. Kumar and F. Herrmann, “Seismic data reconstruction with generative adversarial networks,” in 80th EAGE Conference and Exhibition, pp. 1-5, Jan. 2018. (可以处理严重欠采样的地震数据，但是，它要求一定百分比的完全采样的镜头可用作训练数据)
4. D.Oliveira, R. Ferreira, R. Silva and E. Vital Brazil, "Interpolating seismicdata with conditional generative adversarial networks,”IEEE Geosci.Remote S., vol. 15, no.12, pp.1952-1956, Sept.2018. (当数据结构复杂时，这可能会呈现较低的分辨率和一些非地质伪影)

3. Deep Priors

1. Q. Liu, L. Fu, and M. Zhang, “Deep-seismic-prior- based reconstruction of seismic data using convolutional neural networks,” Geophysics, 2019.

4. 残差网络

1. Wang, B., N. Zhang, W. Lu, and J. Wang, 2019, Deep-learning-based seismic data interpolation: A preliminary result: Geophysics, 84, no. 1, V11–V20, doi: 10.1190/geo2017-0495.1. （插值常规缺失数据）
2. Q. Wang, Z. Teng, J. Xing, J. Gao, W. Hu, and S. Maybank, “Learning attentions: Residual attentional siamese network for high performance online visual tracking,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 4854–4863.

5. 卷积自动编码器

1. Wang, Y., B. Wang, N. Tu, and J. Geng, 2020, Seismic trace interpolation for irregularly spatial sampled data using convolutional autoencoder: Geophysics, 85, no. 2, V119–V130, doi: 10.1190/geo2018-0699.1. (插入随机缺失数据)
2. S. Mandelli, V. Lipari, P. Bestagini and S. Tubaro, “Interpolation and denoising of seismic data using convolutional neural networks,” arXiv: 1901.07927 [cs.NE], 1-13, Jan. 2019. (需要使用大型数据集进行训练)

6. 迁移学习

1. Zhang, H., X. Yang, and J. Ma, 2020, Can learning from natural image denoising be used for seismic data interpolation? Geophysics, 85, no. 4, WA115–WA136, doi: 10.1190/geo2019-0243.1. (将训练有素的 CNN 降噪器集成到凸集投影 (POCS))

~~未完待续