Three-Dimensional Permeability Inversion Using Convolutional Neural Networks and Positron Emission Tomography

Abstract

Quantification of heterogeneous multiscale permeability in geologic porous media is key for understanding and predicting flow and transport processes in the subsurface. Recent utilization of in situ imaging, specifically positron emission tomography (PET), enables the measurement of three-dimensional (3-D) time-lapse radiotracer solute transport in geologic media. However, accurate and computationally efficient characterization of the permeability distribution that controls the solute transport process remains challenging. Leveraging the relationship between local permeability variation and solute advection behavior, an encoder-decoder based convolutional neural network (CNN) is implemented as a permeability inversion scheme using a single PET scan of a radiotracer pulse injection experiment as input. The CNN can accurately capture the 3-D spatial correlation between the permeability and the radiotracer solute arrival time difference maps in geologic cores. We first test the inversion accuracy using synthetic test datasets and then test the accuracy on a suite of experimental PET imaging datasets acquired on four different geologic cores. The network-predicted permeability maps from the geologic cores are used to parameterize forward numerical models that are directly compared with the experimental PET imaging data. The results indicate that a single trained network can generate robust 3-D permeability inversion maps in seconds. Numerical models parameterized with these permeability maps closely capture the experimentally observed solute arrival time behavior. This work provides an unprecedented approach for efficiently characterizing multiscale permeability heterogeneity in complex geologic samples.

Plain Language Summary

The first step in understanding how water and contaminants are flowing in the subsurface is to describe the ease at which fluid can flow—a hydrogeologic property termed permeability. Variation in permeability is an intrinsic property of geologic materials that arises due to differences in the underlying geologic processes that generated the materials. The use of medical imaging techniques in the field of hydrogeology enables scientists to better understand how water and contaminants flow through geologic porous media. This study leverages these imaging techniques combined with recent advances in deep learning to develop a new way for measuring permeability variation in geologic materials. In this study, we use a deep learning model to perform 3-D permeability prediction. The model is trained by guiding the model to identify the characteristics in the transport data that provide insights on permeability distribution. Compared to traditional mathematical modeling approaches, the trained deep learning model significantly reduces the computational cost while accurately predicting the 3-D permeability distributions in real geologic materials.