发表机构
Universidade de São Paulo; Escola Politécnica; Imperial College London（圣保罗大学; 理工学院; 帝国理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出使用StyleGAN2的中间w空间进行集成数据同化，相比传统z空间方法，在非高斯地质参数化中提高了历史拟合效果和地质真实性。
AI 中文摘要
集成平滑器是目前用于历史拟合的最成功且高效的技术。然而，由于这些方法依赖于高斯假设，当先验地质以复杂相分布（非高斯）描述时，其性能会严重下降。因此，对于这些方法，我们需要应用高效的参数化技术。目前，执行参数化最有效的方法是深度学习模型。然而，鉴于现有深度学习模型的多样性，尽管一些重要模型已被评估，但研究尚未确定哪种模型最适合与基于集成的方法一起使用。基于最近的文献综述，选出的最有前景的模型是VAE-GAN、Latent Diffusion和StyleGAN模型。作为这项工作的新颖之处，使用第二代StyleGAN（StyleGAN2）模型分别通过潜在z空间和中间w空间进行了数据同化。它们被应用于两个二维案例研究：一个是分类（三相）的，另一个是连续的。结果表明，所有三个模型都非常高效，其中StyleGAN2模型在生成具有地质真实感的样本和在所研究案例中实现出色的数据匹配方面表现突出。我们的发现表明，使用StyleGAN2通过中间空间（w空间）进行数据同化比传统在潜在空间（z空间）中的应用获得了更好的结果。这是因为ESMDA使用线性更新，而w空间比高度纠缠的z空间更加线性和解耦，从而确保更新后的向量保持接近真实的地质模式。这些结果使用主要的地质统计和历史拟合指标进行了验证。
英文摘要
Ensemble smoothers are the most successful and efficient techniques currently available for history matching. However, because these methods rely on Gaussian assumptions, their performance is severely degraded when the prior geology is described in terms of complex facies distributions (non-Gaussian). In this way, for these methods, we need to apply efficient parameterization techniques. Currently, the most efficient methods for performing parameterization are deep learning models. However, given the variety of existing deep learning models, studies have not identified which is most suitable for use with ensemble-based methods, although some important models had already been evaluated. Based on a recent literature review, the most promising models selected were VAE-GAN, Latent Diffusion, and StyleGAN models. As a novel aspect of this work, data assimilation with the second generation of StyleGAN (StyleGAN2) model was performed using the latent z-space and intermediate w-space, separately. They were applied in two 2D case studies: one categorical (three facies) and the other continuous. The results demonstrated that all three models are highly efficient, with the StyleGAN2 model standing out for generating samples with geological realism and achieving excellent data matching in the cases studied. Our findings show that performing data assimilation with StyleGAN2 using the intermediate space (w-space) yielded better results than the traditional application in the latent space (z-space). This is due to the fact that ESMDA uses linear updates and the w-space is much more linear and disentangled than the highly entangled z-space, thereby ensuring that the updated vectors remain close to realistic geological patterns. These results were validated using main geostatistical and history matching metrics.
