Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother

Abstract Ensemble-based methods have been applied with remarkable success for data assimilation in geosciences. However, they sometimes fail to preserve the geological realism of the model, which is particularly evident in reservoirs with complex facies distributions. This occurs mainly because of the underlying Gaussian assumptions on model parameters that are inherent in these methods. This fact has encouraged an intense research activity to develop Gaussian parameterizations in a latent space that maps into geologically-realistic facies realizations. Despite the large number of publications, the development of robust parameterizations for facies remains an open problem. Deep learning techniques have been delivering impressive results in a number of different areas and the first applications in data assimilation in geoscience have started to appear in the literature. The present paper reports the current results of our investigations on the use of deep neural networks towards the construction of a continuous parameterization of facies, which can be used for data assimilation with ensemble methods. Specifically, we use a convolutional variational autoencoder and the ensemble smoother with multiple data assimilation. We tested the parameterization in three synthetic history-matching problems with channelized facies. We focus on this type of facies because they are among the most challenging to preserve after the assimilation of data. The parameterization showed promising results, outperforming previous methods and generating well-defined channelized facies. However, more research is still required before deploying these methods for operational use. In particular, it is necessary to investigate procedures to improve the reconstruction accuracy in three-dimensional cases and reduce the computational requirements to train the networks.