De-aliased high-resolution Radon transform based on the sparse prior information from the convolutional neural network
Open Access
- 9 July 2022
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of Geophysics and Engineering
- Vol. 19 (4) , 663-680
Abstract
The resolution of Radon transform is crucial in seismic data interpolation. The high-frequency components usually suffer from serious aliasing problems while the sampling is insufficient. Constraining high-frequency components with unaliased low-frequency components is an effective method for improving the resolution of seismic data. However, it is difficult to obtain high-resolution low-frequency Radon coefficients by traditional analytical methods due to the strong correlation of basis functions. For this problem, a sparse inversion method using the neural network is proposed. First, the convolution model is deduced between the conjugated Radon solution and its ground truth. Then, a convolutional neural network (CNN), with the conjugate Radon solution as input, is designed to realize the deconvolution from the conjugate solution to the sparse and high-resolution Radon solution. Finally, the obtained sparse solution is regarded as prior knowledge of the iteratively reweighted least-squares algorithm. The proposed strategy has a distinct advantage in improving the resolution of low-frequency components, which helps overcome the aliasing. Interpolation experiments on synthetic and field data demonstrate the de-aliased performance of this CNN-based method.Keywords
This publication has 34 references indexed in Scilit:
- Seismic data interpolation by greedy local Radon transformGeophysics, 2010
- On the stability of the basis pursuit in the presence of noiseSignal Processing, 2006
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraintCommunications on Pure and Applied Mathematics, 2004
- Latest views of the sparse Radon transformGeophysics, 2003
- Spatial resolution improvement of remotely sensed images by a fully interconnected neural network approachIEEE Transactions on Geoscience and Remote Sensing, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- High-resolution velocity gathers and offset space reconstructionGeophysics, 1995
- Robust methods in inverse theoryInverse Problems, 1988
- Fast Ip solution of large, sparse, linear systems: Application to seismic travel time tomographyJournal of Computational Physics, 1988
- Velocity-stack and slant-stack stochastic inversionGeophysics, 1985