Towards geological inference with process-based and deep generative modeling, part 1: training on fluvial deposits

The distribution of resources in the subsurface is deeply linked to the variations of its physical properties. Generative modeling has long been used to predict those physical properties while quantifying the associated uncertainty. But current approaches struggle to properly reproduce geological structures, and fluvial deposits in particular, because of their continuity. This study explores whether a generative adversarial network (GAN) - a type of deep-learning algorithm for generative modeling - can be trained to reproduce fluvial deposits simulated by a process-based model - a more expensive model that mimics geological processes. An ablation study shows that developments from the deep-learning community to generate large 2D images are directly transferable to 3D images of fluvial deposits. Training remains stable, and the generated samples reproduce the non-stationarity and details of the deposits without mode collapse or pure memorization of the training data. Using a process-based model to generate those training data allows us to include valuable properties other than the usual physical properties. We show how the deposition time let us monitor and validate the performance of a GAN by checking that its samples honor the law of superposition. Our work joins a series of previous studies suggesting that GANs are more robust that given credit for, at least for training datasets targeting specific geological structures. Whether this robustness transfers to larger 3D images and multimodal datasets remains to be seen. Exploring how deep generative models can leverage geological principles like the law of superposition shows a lot of promise.