Seismic Impedance Inversion Using Fully Convolutional Residual Network and Transfer Learning
The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
In this letter, we use a fully convolutional residual network (FCRN) for seismic impedance inversion. After training with appropriate data, the FCRN can effectively predict impedance with high accuracy, and have good robustness against noise and phase difference. However, it cannot give acceptable results in training and predicting models with different geological features. Transfer learning is later introduced to ease this problem. Marmousi2 and Overthrust models are used to verify the effectiveness of the proposed method. Tests show that after fine-tuned by five traces of Overthrust model, the FCRN trained on the Marmousi2 model can give a comparable result similarly predicted by the FCRN trained purely on the Overthrust model.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“of the first layer of each residual block, and of each residual block [6], [20], [21].”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“In 1998, LeCun et al. [5] Lingling Wang is with the Institute of Geophysics and Geomat-ics, China University of Geosciences, Wuhan 430074, China (e-mail: wangll@cug.edu.cn).”
BackgroundBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818 · cited 1×
“In addition, we apply batch normalization (BN) to the output of all the convolution layers except for the last layer to speed up network training [22]. where I ( s ) denotes the labeled impedance trace.”
MethodPan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 1×
“Many machine learning methods follow a crucial hypothesis that the data for training and for prediction must be in the same feature space, and same distribution [25].”
Background(2010) · International Conference on Machine Learning · Cited by 13,995
Fully convolutional networks for semantic segmentation
Shelhamer, E., Long, J., & Darrell, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2572683 · Cited by 11,898 · cited 2×
“able to predict from the inputs of arbitrary sizes [8].”
BackgroundMethodCubic convolution interpolation for digital image processing
Keys, R. (1981) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1981.1163711 · Cited by 3,255 · cited 1×
“Cubic convolution interpolation technique is utilized to generate 20 new impedance and seismic data traces between every two adjacent pseudowells [17].”
MethodEmpirical Evaluation of Rectified Activations in Convolutional Network
Xu, B., Wang, N., Chen, T., & Li, M. (2015) · arXiv · doi:10.48550/arxiv.1505.00853 · Cited by 2,264 · cited 1×
“of the first layer of each residual block, and of each residual block [6], [20], [21].”
BackgroundWu, X., Liang, L., Shi, Y., & Fomel, S. (2019) · GEOPHYSICS · doi:10.1190/geo2018-0646.1 · Cited by 898 · cited 1×
“CNNs and FCNs have been applied to tackle some geophysical problems, such as seismic waveform classification and first-break picking [9], [10], seismic data interpolation [11], and fault detection [12].”
MethodApplying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
Abdel-Hamid, O., Mohamed, A.-R., Jiang, H., & Penn, G. (2012) · 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2012.6288864 · Cited by 876 · cited 1×
“Digital Object Identifier 10.1109/LGRS.2019.2963106 architecture and since then CNNs have achieved outstanding performances in different areas such as computer vision [6], and speech recognition [7].”
BackgroundInfluentialConvolutional neural network for seismic impedance inversion
Das, V., Pollack, A., Wollner, U., & Mukerji, T. (2019) · Geophysics · doi:10.1190/geo2018-0838.1 · Cited by 471
Deep-learning-based seismic data interpolation: A preliminary result
Wang, B., Zhang, N., Lu, W., & Wang, J. (2019) · GEOPHYSICS · doi:10.1190/geo2017-0495.1 · Cited by 381 · cited 1×
“CNNs and FCNs have been applied to tackle some geophysical problems, such as seismic waveform classification and first-break picking [9], [10], seismic data interpolation [11], and fault detection [12].”
MethodDeep learning electromagnetic inversion with convolutional neural networks
Puzyrev, V. (2019) · Geophysical Journal International · doi:10.1093/gji/ggz204 · Cited by 299 · cited 1×
“With this advantage, FCNs can be used to solve inversion problems [18].”
MethodSeismic Waveform Classification and First-Break Picking Using Convolution Neural Networks
Yuan, S., Liu, J., Wang, S., Wang, T., & Shi, P. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2785834 · Cited by 296 · cited 1×
“CNNs and FCNs have been applied to tackle some geophysical problems, such as seismic waveform classification and first-break picking [9], [10], seismic data interpolation [11], and fault detection [12].”
MethodImpedance inversion by using the low-frequency full-waveform inversion result as an a priori model
Yuan, S., Wang, S., Luo, Y., Wei, W., & Wang, G. (2018) · Geophysics · doi:10.1190/geo2017-0643.1 · Cited by 101 · cited 1×
“Techniques for impedance inversion have received much attention over the last 40 years, evolving from direct inversion to model-based inversion, from linear inversion to nonlinear inversion, and from poststack inversion to prestack inversion, and so on [2], [3].”
BackgroundWu, H., Zhang, B., Li, F., & Liu, N. (2019) · Geophysics · doi:10.1190/geo2018-0389.1 · Cited by 91 · cited 1×
“CNNs and FCNs have been applied to tackle some geophysical problems, such as seismic waveform classification and first-break picking [9], [10], seismic data interpolation [11], and fault detection [12].”
MethodSelf-citation
Cited by
Deep learning in computational mechanics: a review
Herrmann, L., & Kollmannsberger, S. (2024) · Computational Mechanics · doi:10.1007/s00466-023-02434-4 · Cited by 162
Metadata
- Authors
- Wu, B., Meng, D., Wang, L., Liu, N., & Wang, Y.
- Venue
- IEEE Geoscience and Remote Sensing Letters
- Published
- 2020-12
- Volume
- 17
- Issue
- 12
- Pages
- 2140-2144
- ISSN
- 1545-598X (ISSN-L)
- 1558-0571
- OpenAlex
- W2999581854
- Cited by
- 161
- References
- 18
- FWCI
- 14.90
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.