5 April 2022 in Geophysics
In seismic field acquisition, some of the measurements that are intended to be recorded are lost due to excessive noise contamination or because we are unable to occupy the required source or receiver locations. When these issues are severe, the missing data can cause images to be suboptimal. To enhance seismic data, deep learning has been used to perform denoising and data interpolation tasks, but it has rarely been used for both tasks in a unified framework. We have developed a modified residual dense network (RDN), a deep neural network for simultaneously removing noise and interpolating missing data. In addition, we augment the training data by varying source wavelets and constructing negative copied samples. After training, the modified RDN provides a one-stop solution for denoising and interpolation. To validate our approach, we test the modified RDN for random/coherent noise removal and regularly/irregularly subsampled seismic data interpolation. Compared with the benchmark methods, our approach can significantly improve performance in synthetic data (at least 2.41 in signal-to-noise ratio) and reduce undesired artifacts in marine field data.
1 January 2023 in Applied Mathematics for Modern Challenges
Limited-angle computed tomography (LACT) has gained significant attention in recent years due to its wide range of applications. Despite the numerous algorithms proposed to improve imaging quality, reconstructing fine details remains a challenging problem. In this paper, we propose a novel hybrid domain framework that combines classical methods and learning-based methods to address this challenge. Our framework decomposes the solution of the least-squares problem into back-projection and deconvolution steps, leading to a significant improvement in reconstruction quality. Furthermore, we employ a conditional diffusion model to further fine-tune the reconstruction results, simultaneously preserving data consistency and enhancing the realness of the reconstructed images. The effectiveness of the proposed framework is evaluated using the Helsinki Tomography Challenge 2022 (HTC 2022) dataset. Comparative evaluations demonstrate that our framework outperforms previous methods in both visual quality and quantitative measures. These findings highlight the potential of the proposed framework in improving LACT reconstruction and offer valuable insights for advancing imaging techniques in various fields.
15 November 2023 in SIAM Journal on Scientific Computing
Full waveform inversion (FWI) is a powerful tool for high-resolution subsurface parameter reconstruction. Due to the existence of local minimum traps, the success of the inversion process usually requires a good initial model. Our study primarily focuses on understanding the impact of source wavelets on the landscape of the corresponding optimization problem. We thus introduce a decomposition scheme that divides the inverse problem into two parts. The first step transforms the measured data into data associated with the desired source wavelet. Here, we consider inversions with known and unknown sources to mimic real scenarios. The second subproblem is the conventional FWI, which is much less dependent on an accurate initial model since the previous step improves the misfit landscape. A regularized deconvolution method and a convolutional neural network are employed to solve the source transformation problem. Numerical experiments on the benchmark models demonstrate that our approach improves the gradient’s quality in the subsequent FWI and provides a better inversion performance.