Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2605.18375

DANTE: Physics-Informed Neural Operator for DAS-to-Velocity Waveform Reconstruction Without Co-located Seismometers

Isao Kurosawa
View original source ↗Read source document ↗Export metadata ↓

Abstract

Distributed Acoustic Sensing (DAS) converts existing fibre-optic cables into dense seismic arrays at near-zero deployment cost, but measures strain rate rather than particle velocity -- the quantity required by virtually all seismological analysis tools. Converting strain rate to particle velocity by numerical integration is ill-posed: the integration constant is undefined and noise accumulates without bound. We present DANTE (DAS-to-velocity via physics-informed neural operator for Acoustic-wave recoNstruction in heTErogeneous media), a Fourier Neural Operator (FNO) trained entirely on synthetic data that enforces two physics constraints: (i) the exact kinematic relation between DAS strain rate and the spatial gradient of particle velocity, and (ii) the one-dimensional elastic wave equation. These constraints resolve the undetermined integration constant and suppress noise without requiring co-located seismometers. On a test set of 200 heterogeneous synthetic wavefields, DANTE achieves a mean output SNR of $15.3 \pm 8.8$ dB, Pearson correlation $r = 0.907$, and SSIM $= 0.976$, corresponding to a mean SNR improvement of approximately $+15$ dB over the best conventional baseline (trace stacking, $n = 10$, $0.02 \pm 0.06$ dB), and up to $+28.8$ dB on the most challenging samples. Zero-shot inference on seven real microseismic events from the Utah FORGE 2019 DAS dataset yields a kinematic residual of 0.003--0.005, five times lower than the synthetic test baseline, confirming generalisation to real field data with no fine-tuning and no seismometers.

Explore related subjects

physics.geo-ph

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Isao Kurosawa. 2026-05-18. DANTE: Physics-Informed Neural Operator for DAS-to-Velocity Waveform Reconstruction Without Co-located Seismometers. https://arxiv.org/abs/2605.18375

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

SPBench: A Multi-Task Evaluation Benchmark for Exploration Seismic Processing

Exploration seismic processing underpins subsurface imaging and resource exploration, but learning-based methods remain difficult to compare across studies. Our survey of 368 papers finds widespread reliance on private or difficult-to-reproduce datasets, with only 25 providing public code. This obscures whether reported gains arise from model design or experimental settings. We introduce the Seismic Processing Benchmark (SPBench), covering six tasks: random noise attenuation, trace interpolation, ground-roll suppression, multiple suppression, deblending, and first-arrival picking. We reproduce 24 supervised methods on 10 datasets under 43 standardized settings and release datasets, implementations, configurations, evaluation scripts, and results. To complement global scores and per-trace pick errors, we introduce signal-component-resolved evaluation (SCoRE) for reconstruction and a reference-free ridge-curvature score (RC_norm) for first-arrival picking. Our analyses show that synthetic rankings do not reliably predict field rankings, with task-dependent agreement when models train within each setting. As degradation strengthens, rankings reorder more under coherent ground roll than under random-like interference. The ridge score agrees with MAE-based model rankings in the evaluated settings, with a mean Kendall correlation of 0.881 across three field surveys, while SCoRE reveals frequency- and energy-dependent differences hidden by global scores. SPBench provides a reproducible basis for comparing learning-based seismic processing methods and characterizes how their relative advantages vary across data settings, degradation strengths, and evaluation criteria.

physics.geo-ph↗
arXiv2026

Bayesian full waveform inversion with learned prior using deep convolutional autoencoder

Full waveform inversion (FWI) can be expressed in a Bayesian framework, where the associated uncertainties are captured by the posterior probability distribution (PPD). In practice, solving Bayesian FWI with sampling-based methods such as Markov chain Monte Carlo (MCMC) is computationally demanding because of the extremely high dimensionality of the model space. To alleviate this difficulty, we develop a deep convolutional autoencoder (CAE) that serves as a learned prior for the inversion. The CAE compresses detailed subsurface velocity models into a low-dimensional latent representation, achieving more effective and geologically consistent model reduction than conventional dimension reduction approaches. The inversion procedure employs an adaptive gradient-based MCMC algorithm enhanced by automatic differentiation-based FWI to compute gradients efficiently in the latent space. In addition, we implement a transfer learning strategy through online fine-tuning during inversion, enabling the framework to adapt to velocity structures not represented in the original training set. Numerical experiments with synthetic data show that the method can reconstruct velocity models and assess uncertainty with improved efficiency compared to traditional MCMC methods.

physics.geo-ph↗
arXiv2026

Assessing foundational atomistic models for iron alloys under Earth's core conditions

We assess the capability of recently developed foundational atomistic models (FAMs) to simulate iron alloys under the extreme pressures and temperatures of Earth's core. Static equations of state for hexagonal close-packed (hcp) and body-centered cubic (bcc) iron, computed using 17 FAMs, are benchmarked against ab initio calculations. Two representative models, MatterSim and MACE, are further evaluated for their ability to reproduce phonon spectra, liquid structure, and melting relations of iron at core conditions. While both models capture several key properties, MACE substantially overestimates the stability of bcc iron and fails to correctly describe the stability of hcp iron. Their performance is also examined for binary liquids, superionic phases, and a seven-component Fe-Ni-Si-S-O-H-C liquid. Although these FAMs were not explicitly trained on data from core conditions, they can reproduce several structural and dynamical properties across a wide range of compositions. However, none of the tested models consistently reproduces all first-principles benchmarks. By analyzing the origins of these discrepancies, we identify several limitations of current FAMs, particularly the lack of an explicit treatment of thermal electronic excitations, which significantly affect phase stability and thermodynamic properties under core conditions. We further discuss directions for improving FAMs to enable predictive simulations of core-forming materials under extreme conditions.

physics.geo-ph↗