arXiv subjects

Matteo Ravasi

Publications and source records attributed to Matteo Ravasi.

At least 19 recordsLinked to original sources

arXiv2026

Foundation Model-Assisted Full Waveform Inversion

Full waveform inversion (FWI) can recover high-resolution subsurface velocity models. Conventional waveform-difference objectives, however, are vulnerable to cycle skipping when the starting model is inaccurate. We introduce an FWI objective that compares features produced from modeled and observed seismic traces by SeisLM, a pretrained seismic foundation model. The SeisLM encoder remains frozen during inversion, and the feature discrepancy is differentiated with respect to the modeled traces to construct an adjoint source compatible with the standard adjoint-state framework. We also test a scheduled hybrid loss that combines the SeisLM feature loss with the conventional $L_2$ objective. Time-shift diagnostics show that the loss computed from features produced by the pretrained encoder has a broader and smoother basin around the correct alignment than either the waveform $L_2$ objective or the feature loss obtained from an encoder with the same architecture and randomly initialized parameters. In the Marmousi experiment, the SeisLM and hybrid objectives produce similar improvements during early-stage inversion and provide useful models for subsequent reflection-based $L_2$ refinement. In the 2D Overthrust experiment, which begins from a laterally invariant linear-gradient model, the SeisLM feature-loss workflow outperforms the conventional and hybrid workflows, indicating that introducing the $L_2$ contribution too early can reintroduce cycle-skipping sensitivity. In the 3D Overthrust experiment, conventional $L_2$ inversion stalls near the initial linear gradient, whereas the SeisLM feature loss guides the inversion toward a background model from which $L_2$ refinement recovers the principal structures. These results support using features produced by pretrained seismic networks to define early-stage FWI objectives rather than complete replacements for waveform-domain misfits.

physics.geo-ph↗

arXiv2025

Uncertainty Quantification in HSI Reconstruction using Physics-Aware Diffusion Priors and Optics-Encoded Measurements

Hyperspectral image reconstruction from a compressed measurement is a highly ill-posed inverse problem. Current data-driven methods suffer from hallucination due to the lack of spectral diversity in existing hyperspectral image datasets, particularly when they are evaluated for the metamerism phenomenon. In this work, we formulate hyperspectral image (HSI) reconstruction as a Bayesian inference problem and propose a framework, HSDiff, that utilizes an unconditionally trained, pixel-level diffusion prior and posterior diffusion sampling to generate diverse HSI samples consistent with the measurements of various hyperspectral image formation models. We propose an enhanced metameric augmentation technique using region-based metameric black and partition-of-union spectral upsampling to expand training with physically valid metameric spectra, strengthening the prior diversity and improving uncertainty calibration. We utilize HSDiff to investigate how the studied forward models shape the posterior distribution and demonstrate that guiding with effective spectral encoding provides calibrated informative uncertainty compared to non-encoded models. Through the lens of the Bayesian framework, HSDiff offers a complete, high-performance method for uncertainty-aware HSI reconstruction. Our results also reiterate the significance of effective spectral encoding in snapshot hyperspectral imaging.

cs.CV↗

arXiv2025

A Deep Learning-based time shift objective function for Full Waveform Inversion

Full Waveform Inversion (FWI) is a powerful technique for estimating high-resolution subsurface velocity models by minimizing the discrepancy between modeled and observed seismic data. However, the oscillatory nature of seismic waveforms makes point-wise discrepancy measures highly prone to cycle-skipping, especially when the initial velocity model is inadequate. To address this challenge, various alternative misfit functions have been proposed in the literature, each with unique strengths and limitations. Dynamic Time Warping (DTW) is a popular technique in signal processing for aligning time series using dynamic programming. While a differentiable variant of DTW has been recently proposed, its use in FWI is hindered by high-frequency artifacts in the adjoint source and the substantial computational cost of gradient evaluations. In this study, we propose a neural network-based approach to learn the time shifts that align two time series in a supervised manner. The trained network is then utilized to compare traces from observed and modeled seismic data, offering a stable and computationally efficient alternative to DTW. Furthermore, the inherent differentiability of neural networks via backpropagation enables seamless integration into the FWI framework as a misfit function. We validate this approach on two synthetic datasets, namely the Marmousi model and the Chevron blind test dataset, demonstrating in both cases a similar convergence behavior to that of SoftDWT whilst drastically reducing the computational time of the adjoint source calculation.

physics.geo-ph↗

arXiv2025

Representations for multidimensional down-down deconvolution of ocean-bottom seismic data: theory and practical implications

Multidimensional up-down deconvolution effectively eliminates surface-related multiples from ocean-bottom seismic data. Recently, several down-down deconvolution methods have been introduced as attractive alternatives. Whereas multidimensional up-down deconvolution fully accounts for lateral variations of the medium parameters, the underlying theory of some of the down-down deconvolution methods is essentially based on the assumption that the medium is horizontally layered. Using reciprocity theory, this assumption is circumvented. This leads to representations for either receiver-side or source-side multidimensional down-down deconvolution. Compared with multidimensional up-down deconvolution, receiver-side down-down deconvolution only utilizes the downgoing part of the wavefield that better samples the shallow subsurface, but it is not entirely data-driven. Source-side down-down deconvolution benefits from the better sampled source array, but in the presence of sparsely sampled receivers it requires solving an underdetermined system of linear equations.

physics.geo-ph↗

arXiv2025

Efficient Upside-Down Rayleigh-Marchenko Imaging through Self-Supervised Focusing Function Estimation

The Upside-Down Rayleigh-Marchenko (UD-RM) method has recently emerged as a powerful tool for retrieving subsurface wavefields and images free from artifacts caused by both internal and surface-related multiples. Its ability to handle acquisition setups with large cable spacing or sparse node geometries makes it particularly suitable for ocean-bottom seismic data processing. However, the widespread application of the method is limited by the high computational cost required to estimate the focusing functions, especially when dealing with large imaging domains. To address this limitation, a self-supervised learning approach is proposed to accelerate the estimation of the focusing functions. Specifically, a U-Net network is trained on a small subset of image points from within the target area of interest, whose focusing functions are pre-computed using the conventional iterative scheme. The network is tasked to predict both the up- and down-going focusing functions from an initial estimate of the subsurface wavefields. Once trained, the network generalizes to remaining unseen imaging locations, enabling direct prediction of the focusing functions. Validation on a synthetic dataset with both dense and sparse receiver sampling using progressively fewer training points demonstrates the method's effectiveness. In both cases, the resulting images closely match those obtained from the UD-RM method with focusing functions retrieved by the conventional iterative approach at a much lower cost and significantly outperform mirror migration (when the same input dataset is used). Finally, an application to the Volve field data confirms the method's robustness in practical scenarios. The proposed approach enables seismic imaging at a fraction of the computational cost of the conventional UD-RM approach while maintaining imaging quality, underscoring its potential for large-scale seismic applications.

physics.geo-ph↗

arXiv2025

Geophysical inverse problems with measurement-guided diffusion models

Solving inverse problems with the reverse process of a diffusion model represents an appealing avenue to produce highly realistic, yet diverse solutions from incomplete and possibly noisy measurements, ultimately enabling uncertainty quantification at scale. However, because of the intractable nature of the score function of the likelihood term (i.e., $\nabla_{\mathbf{x}_t} p(\mathbf{y} | \mathbf{x}_t)$), various samplers have been proposed in the literature that use different (more or less accurate) approximations of such a gradient to guide the diffusion process towards solutions that match the observations. In this work, I consider two sampling algorithms recently proposed under the name of Diffusion Posterior Sampling (DPS) and Pseudo-inverse Guided Diffusion Model (PGDM), respectively. In DSP, the guidance term used at each step of the reverse diffusion process is obtained by applying the adjoint of the modeling operator to the residual obtained from a one-step denoising estimate of the solution. On the other hand, PGDM utilizes a pseudo-inverse operator that originates from the fact that the one-step denoised solution is not assumed to be deterministic, rather modeled as a Gaussian distribution. Through an extensive set of numerical examples on two geophysical inverse problems (namely, seismic interpolation and seismic inversion), I show that two key aspects for the success of any measurement-guided diffusion process are: i) our ability to re-parametrize the inverse problem such that the sought after model is bounded between -1 and 1 (a pre-requisite for any diffusion model); ii) the choice of the training dataset used to learn the implicit prior that guides the reverse diffusion process. Numerical examples on synthetic and field datasets reveal that PGDM outperforms DPS in both scenarios at limited additional cost.

physics.geo-ph↗

arXiv2024

Reciprocity-aware adaptive tile low-rank factorization for large-scale 3D multidimensional deconvolution

Low-rank regularization is an effective technique for addressing ill-posed inverse problems when the unknown variable exhibits low-rank characteristics. However, global low-rank assumptions do not always hold for seismic wavefields; in many practical situations, local low-rank features are instead more commonly observed. To leverage this insight, we propose partitioning the unknown variable into tiles, each represented via low-rank factorization. We apply this framework to regularize multidimensional deconvolution in the frequency domain, considering two key factors. First, the unknown variable, referred to as the Green's function, must maintain symmetry according to the reciprocity principle of wave propagation. To ensure symmetry within the tile-based low-rank framework, diagonal tiles are formulated as the product of a low-rank factor and its transpose if numerically rank-deficient. Otherwise, they are represented by preconditioned dense forms. Symmetry in off-diagonal elements is achieved by parameterizing sub-diagonal tiles as the product of two distinct low-rank factors, with the corresponding super-diagonal tiles set as their transposes. Second, the rank of the Green's function varies with frequency; in other words, the Green's function has different ranks at different frequencies. To determine the numerical rank and optimal tile size for each frequency, we first solve the multidimensional deconvolution problem using a benchmark solver. Based on these results, we estimate the optimal tile size and numerical rank for our proposed solver.

physics.geo-ph↗

arXiv2024

Annealed Stein Variational Gradient Descent for Improved Uncertainty Estimation in Full-Waveform Inversion

In recent years, Full-Waveform Inversion (FWI) has been extensively used to derive high-resolution subsurface velocity models from seismic data. However, due to the nonlinearity and ill-posed nature of the problem, FWI requires a good starting model to avoid producing non-physical solutions. Moreover, conventional optimization methods fail to quantify the uncertainty associated with the recovered solution, which is critical for decision-making processes. Bayesian inference offers an alternative approach as it directly or indirectly evaluates the posterior probability density function. For example, Markov Chain Monte Carlo (MCMC) methods generate multiple sample chains to characterize the solution's uncertainty. Despite their ability to theoretically handle any form of distribution, MCMC methods require many sampling steps; this limits their usage in high-dimensional problems with computationally intensive forward modeling, as is the FWI case. Variational Inference (VI), on the other hand, provides an approximate solution to the posterior distribution in the form of a parametric or non-parametric proposal distribution. Among the various algorithms used in VI, Stein Variational Gradient Descent (SVGD) is recognized for its ability to iteratively refine a set of samples to approximate the target distribution. However, mode and variance-collapse issues affect SVGD in high-dimensional inverse problems. This study aims to improve the performance of SVGD within the context of FWI by utilizing, for the first time, an annealed variant of SVGD and combining it with a multi-scale strategy. Additionally, we demonstrate that Principal Component Analysis (PCA) can be used to evaluate the performance of the optimization process. Clustering techniques are also employed to provide more rigorous and meaningful statistical analysis of the particles in the presence of multi-modal distributions.

physics.geo-ph↗

arXiv2024

Signal Enhancement in Distributed Acoustic Sensing Data Using a Guided Unsupervised Deep Learning Network

Distributed Acoustic Sensing (DAS) is a promising technology introducing a new paradigm in the acquisition of high-resolution seismic data. However, DAS data often show weak signals compared to the background noise, especially in tough installation environments. In this study, we propose a new approach to denoise DAS data that leverages an unsupervised deep learning (DL) model, eliminating the need for labeled training data. The DL model aims to reconstruct the DAS signal while simultaneously attenuating DAS noise. The input DAS data undergo band-pass filtering to eliminate high-frequency content. Subsequently, a continuous wavelet transform (CWT) is performed, and the finest scale is used to guide the DL model in reconstructing the DAS signal. First, we extract 2D patches from both the band-pass filtered data and the CWT scale of the data. Then, these patches are converted using an unrolling mechanism into 1D vectors to form the input of the DL model. The architecture of the proposed DL network is composed of several fully-connected layers. A self-attention layer is further included in each layer to extract the spatial relation between the band-pass filtered data and the CWT scale. Through an iterative process, the DL model tunes its parameters to suppress DAS noise, with the band-pass filtered data serving as the target for the network. We employ the log cosh as a loss function for the DL model, enhancing its robustness against erratic noise. The denoising performance of the proposed framework is validated using field examples from the San Andreas Fault Observatory at Depth (SAFOD) and Frontier Observatory for Research in Geothermal Energy (FORGE) datasets, where the data are recorded by a fiber-optic cable. Comparative analyses against three benchmark methods reveal the robust denoising performance of the proposed framework.

physics.geo-ph↗

arXiv2024

Multidimensional deconvolution with shared bases

We address the estimation of seismic wavefields by means of Multidimensional Deconvolution (MDD) for various redatuming applications. While offering more accuracy than conventional correlation-based redatuming methods, MDD faces challenges due to the ill-posed nature of the underlying inverse problem and the requirement to handle large, dense, complex-valued matrices. These obstacles have long limited the adoption of MDD in the geophysical community. Recent interest in this technology has spurred the development of new strategies to enhance the robustness of the inversion process and reduce its computational overhead. We present a novel approach that extends the concept of block low-rank approximations, usually applied to linear operators, to simultaneously compress the operator, right-hand side, and unknowns. This technique greatly alleviates the data-heavy nature of MDD. Moreover, since in 3d applications the matrices do not lend themselves to global low rank approximations, we introduce a novel H2-like approximation. We aim to streamline MDD implementations, fostering efficiency and controlling accuracy in wavefield reconstruction. This innovation holds potential for broader applications in the geophysical domain, possibly revolutionizing the analysis of multi-dimensional seismic datasets.

math.NA↗

arXiv2024

Robust Full Waveform Inversion with deep Hessian deblurring

Full Waveform Inversion (FWI) is a technique widely used in geophysics to obtain high-resolution subsurface velocity models from waveform seismic data. Due to its large computation cost, most flavors of FWI rely only on the computation of the gradient of the loss function to estimate the update direction, therefore ignoring the contribution of the Hessian. Depending on the level of computational resources one can afford, an approximate of the inverse of the Hessian can be calculated and used to speed up the convergence of FWI towards the global (or a plausible local) minimum. In this work, we propose to use an approximate Hessian computed from a linearization of the wave-equation as commonly done in Least-Squares Migration (LSM). More precisely, we rely on the link between a migrated image and a doubly migrated image (i.e., an image obtained by demigration-migration of the migrated image) to estimate the inverse of the Hessian. However, instead of using non-stationary compact filters to link the two images and approximate the Hessian, we propose to use a deep neural network to directly learn the mapping between the FWI gradient (output) and its Hessian (blurred) counterpart (input). By doing so, the network learns to act as an approximate inverse Hessian: as such, when the trained network is applied to the FWI gradient, an enhanced update direction is obtained, which is shown to be beneficial for the convergence of FWI. The weights of the trained (deblurring) network are then transferred to the next FWI iteration to expedite convergence. We demonstrate the effectiveness of the proposed approach on two synthetic datasets and a field dataset.

physics.geo-ph↗

arXiv2024

Upside down Rayleigh-Marchenko: a practical, yet exact redatuming scheme for seabed seismic acquisitions

Ocean-bottom seismic plays a crucial role in resource exploration and monitoring. However, despite its undoubted potential, the use of coarse receiver geometries poses challenges to accurate wavefield redatuming. This in turn, affects the quality of subsequent imaging and reservoir charactherization products. We propose a reciprocal version of the Rayleigh-Marchenko method, called upside down Rayleigh-Marchenko, where all spatial integrals are performed over the (usually much better-sampled) source carpet; this results in a theoretically exact redatuming scheme, which can handle irregular and sparse receiver geometries. The proposed method requires availability of multi-component receivers and either dual-sensor sources or a pre-processing step of model-based source deghosting, and utilizes only the down-going component of the receiver-side wavefield; as such, it can be interpreted as a full-wavefield extension of the mirror imaging method commonly used in seabed settings. Two synthetic examples are used to showcase the effectiveness of the proposed method, starting from the ideal scenario of finely and regularly sampled sources and receivers, and later considering different levels of decimation for the receiver array. Migrated images as well as common-angle gathers reveal that our method can be used to produce structural and amplitude-friendly imaging outputs with minimal data pre-processing.

physics.geo-ph↗

arXiv2024

Plug-and-Play regularized 3D seismic inversion with 2D pre-trained denoisers

Post-stack seismic inversion is a widely used technique to retrieve high-resolution acoustic impedance models from migrated seismic data. Its modelling operator assumes that a migrated seismic data can be generated from the convolution of a source wavelet and the time derivative of the acoustic impedance model. Given the band-limited nature of the seismic wavelet, the convolutional model acts as a filtering operator on the acoustic impedance model, thereby making the problem of retrieving acoustic impedances from seismic data ambiguous. In order to compensate for missing frequencies, post-stack seismic inversion is often regularized, meaning that prior information about the structure of the subsurface is included in the inversion process. Recently, the Plug-and-Play methodology has gained wide interest in the inverse problem community as a new form of implicit regularization, often outperforming state-of-the-art regularization. Plug-and-Play can be applied to any proximal algorithm by simply replacing the proximal operator of the regularizer with any denoiser of choice. We propose to use Plug-and-Play regularization with a 2D pre-trained, deep denoiser for 2D post-stack seismic inversion. Additionally, we show that a generalization of Plug-and-Play, called Multi-Agent Consensus Equilibrium, can be adopted to solve 3D post-stack inversion whilst leveraging the same 2D pre-trained denoiser used in the 2D case. More precisely, Multi-Agent Consensus Equilibrium combines the results of applying such 2D denoiser in the inline, crossline, and time directions in an optimal manner. We verify the proposed methods on a portion of the SEAM Phase 1 velocity model and the Sleipner field dataset. 1

physics.geo-ph↗

arXiv2023

A reciprocity-aware, low-rank regularization for multidimensional deconvolution

This paper presents a novel factorization-based, low-rank regularization method for solving multidimensional deconvolution problems in the frequency domain. In this approach, each frequency component of the unknown wavefield is represented as a complex-valued square matrix and approximated using the product of one rectangular matrix and its transpose. The benefit of such a parametrization is two-fold: first, the size of the unknown matrix is greatly reduced compared to that of the original wavefield of interest (and halved compared to conventional factorization-based, low-rank approximations); second, the retrieved wavefield is implicitly guaranteed to comply with the reciprocity principle, as expected from theory. We further show that the proposed objective function can be successfully optimized using the accelerated proximal gradient algorithm and discuss a robust strategy to define the initial guess of the solution. Numerical examples on synthetic and field data demonstrate the effectiveness of the proposed method in compressing the retrieved Green's function while preserving its accuracy.

physics.geo-ph↗

arXiv2023

IntraSeismic: a coordinate-based learning approach to seismic inversion

Seismic imaging is the numerical process of creating a volumetric representation of the subsurface geological structures from elastic waves recorded at the surface of the Earth. As such, it is widely utilized in the energy and construction sectors for applications ranging from oil and gas prospection, to geothermal production and carbon capture and storage monitoring, to geotechnical assessment of infrastructures. Extracting quantitative information from seismic recordings, such as an acoustic impedance model, is however a highly ill-posed inverse problem, due to the band-limited and noisy nature of the data. This paper introduces IntraSeismic, a novel hybrid seismic inversion method that seamlessly combines coordinate-based learning with the physics of the post-stack modeling operator. Key features of IntraSeismic are i) unparalleled performance in 2D and 3D post-stack seismic inversion, ii) rapid convergence rates, iii) ability to seamlessly include hard constraints (i.e., well data) and perform uncertainty quantification, and iv) potential data compression and fast randomized access to portions of the inverted model. Synthetic and field data applications of IntraSeismic are presented to validate the effectiveness of the proposed method.

physics.geo-ph↗

arXiv2023

Laterally constrained low-rank seismic data completion via cyclic-shear transform

A crucial step in seismic data processing consists in reconstructing the wavefields at spatial locations where faulty or absent sources and/or receivers result in missing data. Several developments in seismic acquisition and interpolation strive to restore signals fragmented by sampling limitations; still, seismic data frequently remain poorly sampled in the source, receiver, or both coordinates. An intrinsic limitation of real-life dense acquisition systems, which are often exceedingly expensive, is that they remain unable to circumvent various physical and environmental obstacles, ultimately hindering a proper recording scheme. In many situations, when the preferred reconstruction method fails to render the actual continuous signals, subsequent imaging studies are negatively affected by sampling artefacts. A recent alternative builds on low-rank completion techniques to deliver superior restoration results on seismic data, paving the way for data kernel compression that can potentially unlock multiple modern processing methods so far prohibited in 3D field scenarios. In this work, we propose a novel transform domain revealing the low-rank character of seismic data that prevents the inherent matrix enlargement introduced when the data are sorted in the midpoint-offset domain and develop a robust extension of the current matrix completion framework to account for lateral physical constraints that ensure a degree of proximity similarity among neighbouring points. Our strategy successfully interpolates missing sources and receivers simultaneously in synthetic and field data.

physics.geo-ph↗

arXiv2023

Seis2Rock: A Data-Driven Approach to Direct Petrophysical Inversion of Pre-Stack Seismic Data

The inversion of petrophysical parameters from seismic data represents a fundamental step in the process of characterizing the subsurface. We propose a novel, data-driven approach named Seis2Rock that utilizes optimal basis functions learned from well log information to directly link band-limited petrophysical reflectivities to pre-stack seismic data. Seis2Rock is composed of two stages: training and inference. During training, a set of optimal basis functions are identified by performing singular value decomposition on one or more synthetic AVO gathers created from measured or rock-physics synthesized elastic well-logs. In inference, seismic pre-stack data are first projected into a set of band-limited petrophysical properties using the previously computed basis functions; this is followed by regularized post-stack seismic inversion of the individual properties. In this work, we apply the Seis2Rock methodology to a synthetic dataset based on the Smeaheia reservoir model and the open Volve field dataset. Numerical results reveal the ability of the proposed method in recovering accurate porosity, shale content, and water saturation models. Finally, the proposed methodology is applied in the context of reservoir monitoring to invert time-lapse, pre-stack seismic data for water saturation changes.

physics.geo-ph↗

arXiv2023

Explainable Artificial Intelligence driven mask design for self-supervised seismic denoising

The presence of coherent noise in seismic data leads to errors and uncertainties, and as such it is paramount to suppress noise as early and efficiently as possible. Self-supervised denoising circumvents the common requirement of deep learning procedures of having noisy-clean training pairs. However, self-supervised coherent noise suppression methods require extensive knowledge of the noise statistics. We propose the use of explainable artificial intelligence approaches to see inside the black box that is the denoising network and use the gained knowledge to replace the need for any prior knowledge of the noise itself. This is achieved in practice by leveraging bias-free networks and the direct linear link between input and output provided by the associated Jacobian matrix; we show that a simple averaging of the Jacobian contributions over a number of randomly selected input pixels, provides an indication of the most effective mask to suppress noise present in the data. The proposed method therefore becomes a fully automated denoising procedure requiring no clean training labels or prior knowledge. Realistic synthetic examples with noise signals of varying complexities, ranging from simple time-correlated noise to complex pseudo rig noise propagating at the velocity of the ocean, are used to validate the proposed approach. Its automated nature is highlighted further by an application to two field datasets. Without any substantial pre-processing or any knowledge of the acquisition environment, the automatically identified blind-masks are shown to perform well in suppressing both trace-wise noise in common shot gathers from the Volve marine dataset and colored noise in post stack seismic images from a land seismic survey.

physics.geo-ph↗