In this study, we investigate feature-based 2.5D controlled source marine electromagnetic (mCSEM) data inversion using generative priors. Two-and-half dimensional modeling using finite difference method (FDM) is adopted to compute the response of horizontal electric dipole (HED) excitation. Rather than using a neural network to approximate the entire inverse mapping in a black-box manner, we adopt a plug-andplay strategy in which a variational autoencoder (VAE) is used solely to learn prior information on conductivity distributions. During the inversion process, the conductivity model is iteratively updated using the Gauss Newton method, while the model space is constrained by projections onto the learned VAE decoder. This framework preserves explicit control over data misfit and enables flexible adaptation to different survey configurations. Numerical and field experiments demonstrate that the proposed approach effectively incorporates prior information, improves reconstruction accuracy, and exhibits good generalization performance.

翻译：本研究探讨了利用生成先验进行基于特征的2.5维海洋可控源电磁（mCSEM）数据反演。采用有限差分法（FDM）进行二维半建模，以计算水平电偶极子（HED）激励的响应。我们并未采用神经网络以黑箱方式近似整个反演映射，而是采用了一种即插即用策略，其中变分自编码器（VAE）仅用于学习电导率分布的先验信息。在反演过程中，电导率模型通过高斯-牛顿法进行迭代更新，同时模型空间通过投影到已学习的VAE解码器上加以约束。该框架保留了对数据失配的显式控制，并能灵活适应不同的勘探配置。数值实验和野外实验表明，所提出的方法能有效融入先验信息，提高重建精度，并展现出良好的泛化性能。