analiza aiqbench
This research addresses a critical bottleneck in geoscience by leveraging StyleGAN2's intermediate latent space (w-space) to overcome the Gaussian limitations of traditional ensemble smoothers. By utilizing w-space, which offers greater linearity and disentanglement, the method successfully generates realistic geological facies distributions that align better with observed data than standard z-space approaches. This advancement demonstrates how generative AI can effectively enhance history matching workflows for complex, non-Gaussian subsurface models.
Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN
arXiv:2609.39626v1 Announce Type: cross Abstract: 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.
Abstract: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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.39626 [cs.LG]
(or arXiv:2609.39626v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.39626 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 358 cuvinte
Subiecte conexe
Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniques
arXiv · 10 iun. 2026
Learning Probabilistic Filters with Strictly Proper Scoring Rules
arXiv · 7 oct. 2026
You can graft SDF changes from base models onto post-trained models
LessWrong · 6 oct. 2026
ADDA: a Modular Framework for Representing, Simulating and Assimilating Dynamics with End-to-end Differentiability
arXiv · 25 aug. 2026