A ConvNeXt‐Enhanced Reparameterized Full‐Waveform Inversion Framework for Subsurface Velocity Estimation
Geophysical Prospecting · 2026-05 · 74 (4)
DOI: 10.1111/1365-2478.70169 ↗Kurz gefasst
Fachartikel in der Zeitschrift Geophysical Prospecting, online erschienen am 29.03.2026. Verfasst von Ning Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hebei Province.
Abstract (Originalsprache)
Full‐waveform inversion (FWI) is a powerful tool for high‐resolution subsurface imaging but remains challenged by high computational demands and strong dependence on the initial model. We propose a ConvNeXt‐based reparameterized FWI framework that revisits convolutional network design for physics‐driven inversion. The framework leverages hierarchical convolutional representations to improve multiscale feature learning while maintaining favourable computational efficiency. Comparative experiments on standard benchmark models demonstrate that the proposed method achieves inversion accuracy comparable to U‐Net and Transformer‐based approaches, with more stable convergence and reduced computational cost. The method further exhibits enhanced robustness in the presence of strong noise and limited low‐frequency data, highlighting its ability to extract consistent features across frequencies. These results indicate that modernized convolutional architectures provide an effective and practical solution for high‐fidelity seismic inversion.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hebei Province
Zitieren
APA
Wang, N., Lin, Z., Geng, B., & Shi, Y. (2026). A ConvNeXt‐Enhanced Reparameterized Full‐Waveform Inversion Framework for Subsurface Velocity Estimation. Geophysical Prospecting, 74(4). https://doi.org/10.1111/1365-2478.70169
Vancouver
Wang N, Lin Z, Geng B, Shi Y. A ConvNeXt‐Enhanced Reparameterized Full‐Waveform Inversion Framework for Subsurface Velocity Estimation. Geophysical Prospecting. 2026;74(4). doi:10.1111/1365-2478.70169
BibTeX
@article{Wang2026,
author = {Wang, Ning and Lin, Zhiyuan and Geng, Bingchuan and Shi, Ying},
title = {A ConvNeXt‐Enhanced Reparameterized Full‐Waveform Inversion Framework for Subsurface Velocity Estimation},
journal = {Geophysical Prospecting},
year = {2026},
volume = {74},
number = {4},
doi = {10.1111/1365-2478.70169}
}
EUVIMED