arXiv subjects

Yangkang Chen

Publications and source records attributed to Yangkang Chen.

6 recordsLinked to original sources

arXiv2026

Diffusion-guided optimization for full waveform inversion

We present a diffusion-guided full waveform inversion (FWI) study in which pretrained diffusion generative models are used as learned regularizers inside a PDE-constrained seismic inversion loop. We compare three training-free guidance strategies: Manifold-Preserving Guided Diffusion (MPGD), SDEdit-based initialization, and Split Gibbs Diffusion Sampling (SGDS), which alternates between FWI likelihood updates and diffusion-prior denoising. The proposed workflow keeps wave-equation modeling in the inversion loop and uses a geological prior to stabilize model components that are weakly constrained by the seismic data. Controlled GeoFWI experiments, benchmark-scale Marmousi and Overthrust tests, a difficult Sigsbee2A salt test, and noise-degradation studies show that SGDS improves reconstruction quality relative to conventional L2 and total-variation regularized FWI in clean and moderately noisy synthetic settings. Overall, these experiments demonstrate that diffusion-guided optimization can serve as a practical learned regularization strategy for synthetic FWI benchmarks while preserving the wave-equation modeling loop.

physics.geo-ph↗

arXiv2026

Dispersion-Guided Physics-Aware Deep Inverse Operator for Surface Wave Mode Separation

Surface-wave (SW) dispersion analysis is widely used in near-surface geophysics and seismology to determine shear-wave velocity structures by measuring SW geometric dispersion in seismic data. Among the available approaches, multichannel analysis of surface waves (MASW) and two-station methods are commonly employed to extract dispersion information for SW inversion. However, the coexistence of fundamental and higher modes in seismic data poses challenges for these methods, particularly for two-station analysis. To separate the different mode components, we propose a physics-aware unsupervised deep-learning framework. The method acts as a deep inverse operator that directly separates fundamental- and higher-mode components in the time-space domain using an adaptive Gaussian mask constructed in the frequency-phase-velocity (f-v) domain. Physical constraints are incorporated into the loss function by maximizing energy concentration within the target mask while suppressing leakage outside it. Through backpropagation, the network learns the inverse mapping from physical constraints in the f-v domain to wavefield separation in the time-space domain without requiring labeled training data. Numerical experiments on both synthetic and field data show that the framework provides a robust and automated solution for SW mode separation, facilitating more reliable dispersion-curve picking and improving the accuracy of subsequent SW inversion.

physics.geo-ph↗

arXiv2026

Training a generalizable diffusion model for seismic data processing using a large-scale open-source waveform dataset

We introduce the Seismic Waveforms dataset for Automatic Neural-network processing (SWAN), a comprehensive and standardized benchmark designed to advance data-driven seismic signal processing. SWAN aggregates diverse synthetic and real seismic waveforms spanning a wide range of geological structures, noise conditions, propagation environments, and acquisition geometries, providing a unified foundation for training highly generalizable models. Leveraging this dataset, we develop and evaluate a conditionally constrained residual diffusion model for core seismic processing tasks, focusing on missing-trace reconstruction. Extensive experiments demonstrate that diffusion models trained on SWAN achieve state-of-the-art performance across heterogeneous testing scenarios, outperforming leading deep-learning and physics-based baselines on both synthetic benchmarks and field data examples. The results highlight SWAN's value as both a scalable training corpus and a rigorous evaluation framework, and illustrate the strong potential of diffusion-based architectures for robust, generalizable seismic data processing.

physics.geo-ph↗

arXiv2025

Learning from Imperfect Labels: A Physics-Aware Neural Operator with Application to DAS Data Denoising

Supervised deep learning methods typically require large datasets and high-quality labels to achieve reliable predictions. However, their performance often degrades when trained on imperfect labels. To address this challenge, we propose a physics-aware loss function that serves as a penalty term to mitigate label imperfections during training. In addition, we introduce a modified U-Net-Enhanced Fourier Neural Operator (UFNO) that achieves high-fidelity feature representation while leveraging the advantages of operator learning in function space. By combining these two components, we develop a physics-aware UFNO (PAUFNO) framework that effectively learns from imperfect labels. To evaluate the proposed framework, we apply it to the denoising of distributed acoustic sensing (DAS) data from the Utah FORGE site. The label data were generated using an integrated filtering-based method, but still contain residual coupling noise in the near-wellbore channels. The denoising workflow incorporates a patching-based data augmentation strategy, including an uplifting step, spatial-domain convolutional operations, spectral convolution, and a projection layer to restore data to the desired shape. Extensive numerical experiments demonstrate that the proposed framework achieves superior denoising performance, effectively enhancing DAS records and recovering hidden signals with high accuracy.

physics.geo-ph↗

arXiv2024

Dictionary Learning with Convolutional Structure for Seismic Data Denoising and Interpolation

Seismic data inevitably suffers from random noise and missing traces in field acquisition. This limits the utilization of seismic data for subsequent imaging or inversion applications. Recently, dictionary learning has gained remarkable success in seismic data denoising and interpolation. Variants of the patch-based learning technique, such as the K-SVD algorithm, have been shown to improve denoising and interpolation performance compared to the analytic transform-based methods. However, patch-based learning algorithms work on overlapping patches of data and do not take the full data into account during reconstruction. By contrast, the data patches (CSC) model treats signals globally and, therefore, has shown superior performance over patch-based methods in several image processing applications. In consequence, we test the use of CSC model for seismic data denoising and interpolation. In particular, we use the local block coordinate descent (LoBCoD) algorithm to reconstruct missing traces and clean seismic data from noisy input. The denoising and interpolation performance of the LoBCoD algorithm has been compared with that of K-SVD and orthogonal matching pursuit (OMP) algorithms using synthetic and field data examples. We use three quality measures to test the denoising accuracy: the peak signal-to-noise ratio (PSNR), the relative L2-norm of the error (RLNE), and the structural similarity index (SSIM). We find that LoBCoD performs better than K-SVD and OMP for all test cases in improving PSNR and SSIM, and in reducing RLNE. These observations suggest a huge potential of the CSC model in seismic data denoising and interpolation applications.

physics.geo-ph↗

arXiv2020

Deep-Learning Inversion of Seismic Data

We propose a new method to tackle the mapping challenge from time-series data to spatial image in the field of seismic exploration, i.e., reconstructing the velocity model directly from seismic data by deep neural networks (DNNs). The conventional way of addressing this ill-posed inversion problem is through iterative algorithms, which suffer from poor nonlinear mapping and strong nonuniqueness. Other attempts may either import human intervention errors or underuse seismic data. The challenge for DNNs mainly lies in the weak spatial correspondence, the uncertain reflection-reception relationship between seismic data and velocity model, as well as the time-varying property of seismic data. To tackle these challenges, we propose end-to-end seismic inversion networks (SeisInvNets) with novel components to make the best use of all seismic data. Specifically, we start with every seismic trace and enhance it with its neighborhood information, its observation setup, and the global context of its corresponding seismic profile. From the enhanced seismic traces, the spatially aligned feature maps can be learned and further concatenated to reconstruct a velocity model. In general, we let every seismic trace contribute to the reconstruction of the whole velocity model by finding spatial correspondence. The proposed SeisInvNet consistently produces improvements over the baselines and achieves promising performance on our synthesized and proposed SeisInv data set according to various evaluation metrics. The inversion results are more consistent with the target from the aspects of velocity values, subsurface structures, and geological interfaces. Moreover, the mechanism and the generalization of the proposed method are discussed and verified. Nevertheless, the generalization of deep-learning-based inversion methods on real data is still challenging and considering physics may be one potential solution.

cs.CV↗