Abstract
Geological facies modeling has long been studied to predict subsurface resources. In recent years, generative adversarial networks (GANs) have been used as a new method for geological facies modeling with surprisingly good results. However, in conventional GANs, all layers are trained concurrently, and the scales of the geological features are not considered. In this study, we propose to train GANs for facies modeling based on a new training process, namely progressive growing of GANs or a progressive training process. In the progressive training process, GANs are trained layer by layer, and geological features are learned from coarse scales to fine scales. We also train a GAN in the conventional training process, and compare the conventionally trained generator with the progressively trained generator based on visual inspection, multi-scale sliced Wasserstein distance (MS-SWD), multi-dimensional scaling (MDS) plot visualization, facies proportion, variogram, and channel sinuosity, width, and length metrics. The MS-SWD reveals realism and diversity of the generated facies models, and is combined with MDS to visualize the relationship between the distributions of the generated and training facies models. The conventionally and progressively trained generators both have very good performances on all metrics. The progressively trained generator behaves especially better than the conventionally trained generator on the MS-SWD, MDS plots, and the necessary training time. The training time for the progressively trained generator can be as small as 39% of that for the conventionally trained generator. This study demonstrates the superiority of the progressive training process over the conventional one in geological facies modeling, and provides a better option for future GAN-related researches.
Highlights
Subsurface geological facies modeling is a very important part of the workflow for accurate assessment of subsurface resources such as groundwater, petroleum, and carbon storage
We propose to train generative adversarial networks (GANs) for facies modeling based on a new training process, namely progressive growing of GANs or a progressive training process
We train a GAN in the conventional training process, and compare the conventionally trained generator with the progressively trained generator based on visual inspection, multi-scale sliced Wasserstein distance (MS-SWD), multi-dimensional scaling (MDS) plot visualization, facies proportion, variogram, and channel sinuosity and width metrics
Summary
Subsurface geological facies modeling is a very important part of the workflow for accurate assessment of subsurface resources such as groundwater, petroleum, and carbon storage. Major variants of GAN include deep convolutional GAN (DCGAN) [10], Wasserstein GAN [11, 12], cycle GAN [13], progressive GAN [14], style GAN [15], and bidirectional GAN [16] These generative models have been successfully used in many areas, including digit generation [6], image generation [7, 14], audio generation [17], domain transformation [13], super-resolution image creation [18], text-to-image translation [19], and object segmentation [20]. The focus of this paper is to investigate the progressive GAN training process for geologic facies modeling, and compare the progressive training process with the conventional training process, based on a set of evaluation metrics, including realistic reproduction of facies distributions and computation time.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
