arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.08284physics.geo-phcs.CV
收藏

自增强深度先验用于参数化全波反演

Self-Reinforced Deep Priors for Reparameterized Full Waveform Inversion

University of Science and Technology of China(中国科学技术大学);Shanghai Jiao Tong University(上海交通大学);Geological Exploration Technology Institute of Anhui Province(安徽省地质勘查技术院)

Guangyuan Zou, Junlun Li, Feng Liu, Xuejing Zheng, Jianjian Xie, Guoyi Chen

AI总结:

本文提出自增强深度先验FWI方法,通过自适应更新网络参数和输入,提升地下速度模型重建的精度和稳定性。

摘要:

全波反演(FWI)已成为高分辨率地下成像广泛采用的技术。然而,其内在的强非线性特性往往导致收敛于局部极小值。最近,基于深度图像先验的参数化FWI(DIP-FWI)被提出以减轻对大量训练数据的依赖。通过利用神经网络架构中的频谱偏差和隐含正则化,DIP-FWI能够有效避免局部极小值并重建更具地质合理性的速度模型。然而,现有的DIP-FWI通常在整个反演过程中使用固定随机输入,这未能利用网络输入和输出之间的映射和相关性。此外,在复杂的地质条件下,输入中缺乏信息性先验会加剧反问题的病态性,导致伪影和不稳定的重建。为了解决这些限制,我们提出了一种自增强DIP-FWI(SRDIP-FWI)框架,其中一种引导算法在每次迭代中交替更新网络参数和输入,利用当前网络输出的反馈。这种设计允许自适应的结构增强和改进的正则化,从而有效缓解FWI中的病态性。此外,我们分析了SRDIP-FWI中的网络频谱偏差,并量化其在多尺度速度模型构建中的作用。合成测试和实地陆地数据应用表明,SRDIP-FWI相比多尺度FWI实现了更高的分辨率、改进的准确性和更深入的穿透能力。更重要的是,SRDIP-FWI消除了手动选择频率带和时间窗选取的需要,大大简化了反演流程。总体而言,所提出的方法提供了一种新颖、自适应且稳健的框架,用于准确的地下速度模型重建。

英文摘要:

Full waveform inversion (FWI) has become a widely adopted technique for high-resolution subsurface imaging. However, its inherent strong nonlinearity often results in convergence toward local minima. Recently, deep image prior-based reparameterized FWI (DIP-FWI) has been proposed to alleviate the dependence on massive training data. By exploiting the spectral bias and implicit regularization in the neural network architecture, DIP-FWI can effectively avoid local minima and reconstruct more geologically plausible velocity models. Nevertheless, existing DIP-FWI typically use a fixed random input throughout the inversion process, which fails to utilize the mapping and correlation between the input and output of the network. Moreover, under complex geological conditions, the lack of informative prior in the input can exacerbate the ill-posedness of the inverse problem, leading to artifacts and unstable reconstructions. To address these limitations, we propose a self-reinforced DIP-FWI (SRDIP-FWI) framework, in which a steering algorithm alternately updates both the network parameters and the input at each iteration using feedback from the current network output. This design allows adaptive structural enhancement and improved regularization, thereby effectively mitigating the ill-posedness in FWI. Additionally, we analyze the spectral bias of the network in SRDIP-FWI and quantify its role in multiscale velocity model building. Synthetic tests and field land data application demonstrate that SRDIP-FWI achieves superior resolution, improved accuracy and greater depth penetration compared to multiscale FWI. More importantly, SRDIP-FWI eliminates the need for manual frequency-band selection and time-window picking, substantially simplifying the inversion workflow. Overall, the proposed method provides a novel, adaptive and robust framework for accurate subsurface velocity model reconstruction.

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。

↑