We propose a way to favorably employ neural networks in the field of non-destructive testing using Full Waveform Inversion (FWI). The presented methodology discretizes the unknown material distribution in the domain with a neural network within an adjoint optimization. To further increase efficiency of the FWI, pretrained neural networks are used to provide a good starting point for the inversion. This reduces the number of iterations in the Full Waveform Inversion for specific, yet generalizable settings.

翻译：我们提出了一种在无损检测领域中有效利用神经网络进行全波形反演的方法。该方法在伴随优化框架内，通过神经网络将域内未知材料分布离散化。为进一步提升全波形反演的效率，采用预训练神经网络为反演过程提供良好的初始点。这一策略在特定但可泛化的设置下，减少了全波形反演所需的迭代次数。