A Forward–Inverse Dual-Constrained Transformer Framework for Shear-Wave Velocity Inversion from Rayleigh-Wave Dispersion

Summary Deep-learning-based seismic velocity inversion is often affected by observational noise and insufficient data–model consistency. To address these issues, we propose a forward–inverse dual-constrained deep learning framework for shear-wave velocity (Vs) inversion from surface-wave dispersion data. The framework consists of a convolution-free inversion subnetwork based on multi-head self-attention and a learned forward-modelling subnetwork. The learned forward-modelling subnetwork links the predicted Vs model back to the dispersion-data domain, allowing the inversion subnetwork to be constrained simultaneously by a velocity-model consistency term and a data-domain consistency term. Synthetic tests show that, compared with a single-constraint network using the same backbone, the dual-constrained network yields lower model-domain errors. After recalculating dispersion with disba, the phase-velocity error decreases, the group-velocity error is slightly higher, and the combined phase–group RMSE decreases only slightly. When applied to 11,397 Rayleigh-wave dispersion curves across East Asia, the trained network yields a regional Vs structure that is broadly consistent with the major tectonic features and shows good agreement in its principal structural patterns with the regional Vs model of Li et al. (2022). In the synthetic test, the dual-constrained framework addresses both Vs-model recovery and joint phase- and group-velocity dispersion fitting, while retaining the ability to process regional dispersion curves rapidly after training.

Authors

Institutions

Publication Details

Journal
Geophysical Journal International
Published
2026-11-13
DOI
https://doi.org/10.1093/gji/ggag495
Primary Topic
Seismic Waves and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Forward–Inverse Dual-Constrained Transformer Framework for Shear-Wave Velocity Inversion from Rayleigh-Wave Dispersion

Renwei Ding, Ziyi Wang, Lihong Zhao, 李建平 et al.
Geophysical Journal International
Seismic Waves and Analysis
article

A Forward–Inverse Dual-Constrained Transformer Framework for Shear-Wave Velocity Inversion from Rayleigh-Wave Dispersion

Renwei Ding, Ziyi Wang, Lihong Zhao, 李建平, Chaoyang Li, Xuehui Ji, Shuo Zhao, Shiguo Wu, Hongwu Ma
article en

Abstract

Summary Deep-learning-based seismic velocity inversion is often affected by observational noise and insufficient data–model consistency. To address these issues, we propose a forward–inverse dual-constrained deep learning framework for shear-wave velocity (Vs) inversion from surface-wave dispersion data. The framework consists of a convolution-free inversion subnetwork based on multi-head self-attention and a learned forward-modelling subnetwork. The learned forward-modelling subnetwork links the predicted Vs model back to the dispersion-data domain, allowing the inversion subnetwork to be constrained simultaneously by a velocity-model consistency term and a data-domain consistency term. Synthetic tests show that, compared with a single-constraint network using the same backbone, the dual-constrained network yields lower model-domain errors. After recalculating dispersion with disba, the phase-velocity error decreases, the group-velocity error is slightly higher, and the combined phase–group RMSE decreases only slightly. When applied to 11,397 Rayleigh-wave dispersion curves across East Asia, the trained network yields a regional Vs structure that is broadly consistent with the major tectonic features and shows good agreement in its principal structural patterns with the regional Vs model of Li et al. (2022). In the synthetic test, the dual-constrained framework addresses both Vs-model recovery and joint phase- and group-velocity dispersion fitting, while retaining the ability to process regional dispersion curves rapidly after training.

Geophysical Journal International
Geophysical Survey (RU), Qingdao Institute of Marine Geology (CN), Gansu Coalfield Geology Bureau (CN), Heilongjiang Institute of Technology (CN), Shandong University of Science and Technology (CN), Hainan Tropical Ocean University (CN)
Seismic Waves and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon