Metraipolis › archive › dc_e90a516dd896

DeepWaveRL: Self-Supervised Full Waveform Inversion via Reinforcement Learning — arXiv:2611.03264

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03264
License (as archived)
CC0-1.0
Archived
2026-11-03T18:38:56.378Z
SHA-256 of the archived text
af295b9c86d1985e407e03215aed85c61f06f0aeeef695294500df47c0bee737
Stable URL of this page
https://metraipolis.com/documento/dc_e90a516dd896

How to cite

DeepWaveRL: Self-Supervised Full Waveform Inversion via Reinforcement Learning — arXiv:2611.03264 — arXiv (en), https://arxiv.org/abs/2611.03264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e90a516dd896 (Metraipolis archive dc_e90a516dd896, sha256 af295b9c86d1985e407e03215aed85c61f06f0aeeef695294500df47c0bee737)
BibTeX
@misc{dce90a516dd896,
  title = {DeepWaveRL: Self-Supervised Full Waveform Inversion via Reinforcement Learning — arXiv:2611.03264},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03264},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e90a516dd896; sha256 af295b9c86d1985e407e03215aed85c61f06f0aeeef695294500df47c0bee737},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Full Waveform Inversion (FWI) is a fundamental inverse problem in geophysics to estimate subsurface properties, such as velocity, from seismic measurements. Recently, self-supervised learning methods remove the need for ground-truth velocity maps during training by leveraging a forward operator to simulate seismic data from predictions and backpropagate the gradients of reconstruction loss through it. In this work, we consider a more challenging setting without accessing such gradients. To this end, we incorporate reinforcement learning into self-supervised FWI and propose a framework named DeepWaveRL. Specifically, we reformulate FWI as a policy learning problem, where the policy network predicts velocity maps as actions, and a forward operator is used solely for simulation. A global scalar reward is computed based on data misfit for each prediction and used to weight policy gradients. Thus, learning proceeds without accessing the gradients from the forward operator. Given the indirect and coarse supervision signals, we further identify key strategies to stabilize learning and mitigate the spatial credit assignment bottleneck. Experimental results show that, despite relying entirely on a single scalar reward, DeepWaveRL achieves competitive performance compared to supervised and self-supervised baselines. These findings suggest that our framework offers a flexible and complementary learning paradigm for the FWI research community.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Geophysics (physics.geo-ph).
Pagina del lavoro: https://arxiv.org/abs/2611.03264 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:12:54.627Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).