Using convolutional neural networks to develop starting models for near-surface 2-D full waveform inversion
Using convolutional neural networks to develop starting models for near-surface 2-D full waveform inversion
复制标题
使用卷积神经网络开发近地表二维全波形反演的起始模型
DOI：
10.1093/gji/ggac179
复制
发表时间：
2022
影响因子：
2.8
通讯作者：
Cox, Brady R.
中科院分区：
文献类型：
--
作者：
Vantassel, Joseph P.;Kumar, Krishna;Cox, Brady R.
使用全波形反演（FWI）的非侵入性地下成像有可能从根本上改变近地表（<30米）区域特征，通过恢复高分辨率（米尺度）地下弹性材料特性的2-D/3-D地图。然而，由于FWI结果依赖于局部搜索优化技术和反演非唯一性，因此对初始模型非常敏感。由于记录的地震波场的复杂性（例如，主要的表面波与体波混合）以及在短距离内可能存在显著的空间变异性，因此对近地表FWI的启动模型依赖尤其成问题。为此，研究人员研究了卷积神经网络（cnn）作为开发近表面二维弹性wi启动模型的潜在工具。具体而言，生成了10万个地下模型，以代表经典的近地表地球物理问题；也就是说，成像一个两层，起伏的，土壤-基岩界面。从这些合成模型中开发出一个CNN，它能够将位于24个紧密间隔的表面传感器线性阵列中心的震源获得的实验波场直接转换为FWI的鲁棒启动模型。CNN方法能够产生具有地震图像失配的二维启动模型，其失配程度明显小于其他常用启动模型方法，在许多情况下甚至小于具有较差启动模型的FWI获得的失配程度。CNN在其两层训练集之外的泛化能力使用更复杂的三层、基岩上的土壤地层进行评估。虽然CNN的预测能力在这种更复杂的情况下略有下降，但它仍然能够实现与其他常用的初始模型相当的地震图像和波形失拟，尽管没有在任何三层模型上进行训练。因此，cnn显示出巨大的潜力，作为快速开发鲁棒的工具，现场特定的近表面弹性FWI启动模型。
Non-invasive subsurface imaging using full waveform inversion (FWI) has the potential to fundamentally change near-surface (<30 m) site characterization by enabling the recovery of high-resolution (metre-scale) 2-D/3-D maps of subsurface elastic material properties. Yet, FWI results are quite sensitive to their starting model due to their dependence on local-search optimization techniques and inversion non-uniqueness. Starting model dependence is particularly problematic for near-surface FWI due to the complexity of the recorded seismic wavefield (e.g. dominant surface waves intermixed with body waves) and the potential for significant spatial variability over short distances. In response, convolutional neural networks (CNNs) are investigated as a potential tool for developing starting models for near-surface 2-D elastic FWI. Specifically, 100 000 subsurface models were generated to be representative of a classic near-surface geophysics problem; namely, imaging a two-layer, undulating, soil-over-bedrock interface. A CNN has been developed from these synthetic models that is capable of transforming an experimental wavefield acquired using a seismic source located at the centre of a linear array of 24 closely spaced surface sensors directly into a robust starting model for FWI. The CNN approach was able to produce 2-D starting models with seismic image misfits that were significantly less than the misfits from other common starting model approaches, and in many cases even less than the misfits obtained by FWI with inferior starting models. The ability of the CNN to generalize outside its two-layered training set was assessed using a more complex, three-layered, soil-over-bedrock formation. While the predictive ability of the CNN was slightly reduced for this more complex case, it was still able to achieve seismic image and waveform misfits that were comparable to other commonly used starting models, despite not being trained on any three-layered models. As such, CNNs show great potential as tools for rapidly developing robust, site-specific starting models for near-surface elastic FWI.