recently, the team of Zhang Kai has made new progress in the field of history matching, and the related research has been published in the Journal of Petroleum Science. The paper is titled " Multi-source information fused generative adversarial network model and data assimilation based history matching for reservoir with complex geologies ".

Innovation: VAE and GAN are integrated in this paper, VAE decoder is optimized by discriminator of GAN, and random input latent variable Z of GAN is constrained by encoder of VAE. VAE and GAN promote each other, combined with ES-MDA and constraint information. Finally, an accurate historical fitting inversion reservoir model is constructed in accordance with geological prior knowledge.

Abstract: For reservoirs with complex non-Gaussian geological characteristics, such as carbonate reservoirs or reservoirs with sedimentary facies distribution, it is difficult to implement history matching directly, especially for the ensemble-based data assimilation methods. In this paper, we propose a multi-source information fused generative adversarial network (MSIGAN) model, which is used for parameterization of the complex geologies. In MSIGAN, various information such as facies distribution, microseismic, and inter-well connectivity, can be integrated to learn the geological features. And two major generative models in deep learning, variational autoencoder (VAE) and generative adversarial network (GAN) are combined in our model. Then the proposed MSIGAN model is integrated into the ensemble smoother with multiple data assimilation (ESMDA) method to conduct history matching. We tested the proposed method on two reservoir models with fluvial facies. The experimental results show that the proposed MSIGAN model can effectively learn the complex geological features, which can promote the accuracy of history matching.

The purpose of the journal of Petroleum Science is to introduce the latest academic and scientific research achievements of China's Petroleum industry to foreign countries, carry out extensive international academic exchanges, and promote the development of China's Petroleum Science and technology. It mainly publishes scientific and technological papers reflecting the latest and highest level scientific research achievements in the field of petroleum science and technology in China. Its professional contents include petroleum exploration and development, petroleum storage and transportation engineering, petroleum refining and chemical engineering, petroleum electromechanical engineering, oilfield chemical engineering, economic management and marketing of petroleum industry and other disciplines related to petroleum industry. The SCI impact factor of this journal is 4.09 in 2020, which is in Q1 in JCR region.   

Paper link:

 https://doi.org/10.1016/j.petsci.2021.10.007.

Citation:

Kai Zhang, Hai-Qun Yu, Xiao-Peng Ma, et al. Multi-source information fused generative adversarial network model and data assimilation based history matching for reservoir with complex geologies, Petroleum Science, 2021.