De-aliased high-resolution Radon transform based on the sparse prior information from the convolutional neural network

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.