arXiv subjects

Yangkang Chen

Publications and source records attributed to Yangkang Chen.

12 recordsLinked to original sources

arXiv2026

Physics-based deep learning for non-stationary adaptive multiple suppression

Surface-related multiple elimination (SRME) is an indispensable processing step in marine seismic exploration, comprising two main components: multiple prediction and adaptive subtraction. While the multiple prediction is theoretically data-driven and relies on the data itself, the adaptive subtraction step requires a fairly subjective manual control. Our approach introduces a purely data-driven and physics-based deep learning (PDL) algorithm for improving the adaptive multiple subtraction to significantly enhanced performance. There are two main innovations in the proposed deep-learning (DL) multiple subtraction approaches: first, being data-driven and self-supervised, which removes the dependence on inflexible label preparation and model training processes; secondly, being governed by the adaptive matching filtering (AMF) equation to guide the training process. The DL module serves as a strong regression filter analogous to the traditionally known AMF. We segment a moderately sized seismic profile and an initial multiple model into a large number of patches using a patching scheme for self-contained training. The number of patches is controlled by the patch size and the shift size to enable a sufficient number of training samples required by mainstream DL platforms. The patching-based self-training and regression approach, PDL, is inherently a non-stationary matching approach that aims to obtain a globally optimal matching from the initial multiple models to the input full wavefield data through iterative patching-based training. It is also closely connected with the non-stationary regression approach, which was developed almost two decades ago. However, the PDL approach achieves even stronger regression performance due to the backpropagation-based optimization mechanism in DL, and has shown significantly improved multiple subtraction performance over a number of examples.

physics.geo-ph↗

arXiv2026

Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent

Full waveform inversion (FWI) is a powerful tool for high-resolution subsurface model reconstruction, but it remains highly nonlinear and ill-posed, especially when the initial model is inaccurate or the acquired data are noisy and incomplete. Annealed Stein variational gradient descent (ASVGD) provides a particle-based Bayesian framework for FWI by approximating the posterior distribution with an ensemble of velocity models, thereby enabling uncertainty quantification beyond a single deterministic solution. However, conventional ASVGD-FWI commonly relies on simple handcrafted priors, such as Gaussian or smoothing assumptions, which are often insufficient to represent complex geological structures. To address this limitation, we introduce a learned diffusion model (DM) as an implicit regularization mechanism within the ASVGD-FWI framework. Instead of explicitly evaluating the diffusion prior density, the trained diffusion model acts as a learned geological projection operator that guides updated particles toward the distribution of plausible velocity models. In this way, the proposed method combines data consistency from FWI, posterior diversity from ASVGD, and structural realism from the diffusion prior. Numerical experiments demonstrate that the diffusion-regularized ASVGD-FWI produces more geologically consistent mean models, suppresses nonphysical artifacts, and yields uncertainty estimates that are more concentrated around structurally complex and poorly constrained regions. These results suggest that learned diffusion priors can effectively enhance Bayesian FWI by improving both inversion stability and the interpretability of posterior uncertainty.

stat.ML↗

arXiv2026

Fault-conditioned Seismic Image Generation using Denoising Diffusion Probabilistic Modeling and Neural Style Transfer

Seismic data augmentation is critical for training robust deep learning (DL) models for fault detection and characterization, yet conventional approaches remain inadequate. Geometric transforms, e.g., flips or rotations, and noise injection fail to capture realistic seismic textures, while physics-based forward modeling is computationally expensive and often poorly aligned with the statistical characteristics of field data. We present a denoising diffusion probabilistic model (DDPM) framework that learns the high-dimensional distribution of seismic images directly from field data via iterative noise injection and learned denoising. We develop two variants: an unconditional model (U-DDPM) that generates realistic post-stack seismic patches and a fault-conditioned model (FC-DDPM) that produces diverse seismic realizations that honor user-specified fault geometries encoded as binary masks. Three open-source field datasets with differing amplitude scales and processing histories are jointly standardized for training, demonstrating cross-survey generalization. Generated images from U-DDPM reproduce the dominant textural patterns, amplitude distributions, and reflector continuity observed in real seismic data. FC-DDPM maintains structural fidelity to imposed fault masks while introducing realistic variability in surrounding seismic textures, enabling one-to-many realizations from a single structural template. Frequency-wavenumber spectral analysis confirms that synthetic samples preserve the spatiotemporal bandwidth and dip content of the training distribution. The proposed framework provides a practical, controllable augmentation mechanism for expanding limited fault-labeled training sets without computationally expensive forward modeling or survey-specific parameter tuning, directly addressing a key bottleneck in DL-based seismic interpretation.

physics.geo-ph↗

arXiv2026

GeoFWI3D: Large-scale 3D Velocity Model Dataset for Deep Learning-assisted Seismic Imaging

We introduce GeoFWI3D, a large-scale open-source benchmark dataset of geologically plausible 3D subsurface models designed to accelerate deep learning (DL) assisted seismic imaging and full waveform inversion (FWI). FWI is a physics-driven, wave-equation-based optimization technique used in seismic imaging to estimate the subsurface properties. However, traditional FWI is highly non-linear, non-unique, and ill-posed. The iterative process often converges to local minima when the starting model is insufficiently accurate. Most importantly, 3D FWI is prohibitively expensive. With the advent of DL, a direct mapping between the shot gathers and subsurface properties can be established by training a network on realistic models. The primary bottleneck for such approaches is the lack of large-scale, realistic training datasets. GeoFWI3D addresses this gap with 10,000 geologically diverse velocity models at 96x96x96 resolution, spanning four structural complexity classes: pure stratigraphy, faulted networks, salt diapirism, and complex coupled fault-salt systems. Each model is accompanied by co-registered multi-modal labels including compressional velocity (Vp), zero-offset seismic reflectivity, relative geologic time (RGT), and semantic fault/salt masks. To facilitate systematic evaluation, we introduce benchmark tasks covering fault detection, joint salt body segmentation and chronostratigraphy prediction, FWI, wavefield and traveltime surrogates using neural operators, and generative modeling with a 3D diffusion model. We present baseline results for each task to establish reference performance metrics for future users. The dataset is publicly available under Creative Commons Attribution 4.0 International.

physics.geo-ph↗

arXiv2026

Multi-Modal Surface Wave Inversion using Physics Guided Variational Autoencoders

The growth in seismic acquisition techniques has led to large-scale surveys, making traditional manual dispersion analysis logistically and computationally prohibitive. While deep learning techniques can offer an automated alternative, standard convolutional neural networks (CNNs) often fail to account for the non-uniqueness of the inverse problem and can produce geologically unrealistic, smooth velocity models. To address these challenges, we propose a physics-guided multi-modal variational autoencoder (PG-VAE) for scalable near-surface characterization. Our framework introduces a multi-stream fusion strategy that maps independent latent features from both raw shot gathers and spectral-dispersion images by leveraging the physics of Rayleigh-wave dispersion. We implement a specialized decoder architecture with learned transposed convolutions and residual refinement to enforce a structural bias towards layered earth models. Physics guidance is incorporated via a differentiable surrogate network that serves as a forward-consistency regularizer, penalizing predictions that violate the physics of Rayleigh-wave dispersion. The network is trained on diverse synthetic data generated via elastic modeling, and then validated on unseen synthetic data, and subsequently evaluated on an ultra-high-density field dataset from the Devine test site in Texas. We also employ gradient-weighted class activation mapping (Grad-CAM) to examine the input features contributing to the network predictions. The proposed method could serve as a scalable tool for near-surface characterization and as an initial model-building tool for high-resolution elastic full-waveform inversion.

physics.geo-ph↗

arXiv2026

Multi-Track Time-Series Burst-Overlap Interferometry for Resolving Horizontal Deformation in Earthquake-Cycle Studies

Interferometric Synthetic Aperture Radar (InSAR) is intrinsically insensitive to the north-south component of crustal motion because of its near-polar geometry, which makes accurate quantification of this deformation a persistent limitation of InSAR. We introduce a Multi-track Time-Series Burst-Overlap Interferometry (MTSB) framework that delivers absolute, ITRF-referenced deformation fields across representative interseismic, coseismic, and postseismic applications by combining optimized phase linking, a unified time-series framework for separating deformation and residual misregistration, and block-wise spectral analysis. Case studies spanning co-, inter-, and postseismic phases demonstrate that MTSB accurately resolves along-track horizontal deformation, with primary sensitivity to north-south motion, while substantially reducing orbit-related artifacts. Independent comparisons with GNSS indicate centimeter-level agreement for postseismic and coseismic displacement estimates and millimeter-per-year agreement for interseismic velocities. The resulting deformation fields improve constraints on regional plate kinematics and fault kinematics, facilitate more reliable Euler-pole estimation, and provide by-product orbital corrections for conventional InSAR processing.

physics.geo-ph↗

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↗