arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.09002physics.geo-ph
收藏

WaveDiffusion: 用于物理一致的地震和速度生成的联合潜在扩散

WaveDiffusion: Joint Latent Diffusion for Physically Consistent Seismic and Velocity Generation

University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室);Google DeepMind(谷歌DeepMind);Johns Hopkins University(约翰斯·霍普金斯大学)

Yinan Feng, Hanchen Wang, Yinpeng Chen, Luoyuan Zhang, Jeeun Kang, Yixuan Wu, Young Jin Kim, Youzuo Lin

AI总结:

WaveDiffusion通过联合潜在扩散生成物理一致的地震和速度数据,利用扩散过程建模并验证了潜在空间中PDE一致性。

摘要:

全波形反演(FWI)是地下成像中的关键技术,旨在从表面测量中重建高分辨率的地下属性。声学FWI涉及两种物理模态,即地震波形和速度图,它们由声学波方程所支配。先前的工作主要集中在逆问题上,将地震和速度视为图像到图像的翻译任务。在本文中,我们从生成的角度研究它们的关系。我们的目标是探索和表征潜在空间结构,并识别生成符合支配偏微分方程(PDE)的地震-速度对的潜在向量。具体来说,我们通过扩散过程从共享的潜在空间中联合建模地震和速度数据。在实验中,我们发现扩散可以逐步将任意潜在向量细化为产生近似物理一致的地震-速度对的向量,即使没有显式的物理约束。这为PDE一致性在潜在扩散中的提供了实证证据,其中采样倾向于PDE有效解。在潜在空间中,满足声学波方程可以通过采样和梯度下降近似。我们正式化了这种物理一致的潜在建模任务,并通过大量实验量化了它。在大规模OpenFWI基准上,我们的方法产生了高保真、多样且物理一致的地震-速度对,展示了数据驱动的潜在扩散在复杂科学领域中实现物理一致生成的潜力。

英文摘要:

Full Waveform Inversion (FWI) is a critical technique in subsurface imaging, aiming to reconstruct high-resolution subsurface properties from surface measurements. Acoustic FWI involves two physical modalities, seismic waveforms and velocity maps, which are governed by the acoustic wave equation. Prior works primarily focus on the inverse problem, modeling the relationship between seismic and velocity as an image-to-image translation task. In this work, we study their relationship from a generative perspective. Our aim is to explore and characterize the latent space structure, and identify latent vectors that generate seismic-velocity pairs consistent with the governing partial differential equation (PDE). Specifically, we model seismic and velocity data jointly from a shared latent space via a diffusion process. In experiments, we find that diffusion progressively refines arbitrary latent vectors into ones that yield approximately physics-consistent seismic-velocity pairs, even without explicit physics constraints. This provides empirical evidence of PDE-consistency in latent diffusion, where sampling is biased toward PDE-valid solutions. In latent space, satisfying the acoustic wave equation can be approximated through sampling and gradient descent. We formalize this physics-consistent latent modeling task and quantify it through extensive experiments. On large-scale OpenFWI benchmarks, our approach produces high-fidelity, diverse, and physically consistent seismic-velocity pairs, demonstrating the potential of a data-driven latent diffusion for physically consistent generation in a complex scientific domain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑