No abstract

The permeability of complex porous materials is of interest to many engineering disciplines. This quantity can be obtained via direct flow simulation, which provides the most accurate results, but is very computationally expensive. In particular, the simulation convergence time scales poorly as the simulation domains become less porous or more heterogeneous. Semi-analytical models that rely on averaged structural properties (i.e., porosity and tortuosity) have been proposed, but these features only partly summarize the domain, resulting in limited applicability. On the other hand, data-driven machine learning approaches have shown great promise for building more general models by virtue of accounting for the spatial arrangement of the domains’ solid boundaries. However, prior approaches building on the convolutional neural network (ConvNet) literature concerning 2D image recognition problems do not scale well to the large 3D domains required to obtain a representative elementary volume (REV). As such, most prior work focused on homogeneous samples, where a small REV entails that the global nature of fluid flow could be mostly neglected, and accordingly, the memory bottleneck of addressing 3D domains with ConvNets was side-stepped. Therefore, important geometries such as fractures and vuggy domains could not be modeled properly. In this work, we address this limitation with a general multiscale deep learning model that is able to learn from porous media simulation data. By using a coupled set of neural networks that view the domain on different scales, we enable the evaluation of large ($$>512^3$$ > 512 3 ) images in approximately one second on a single graphics processing unit. This model architecture opens up the possibility of modeling domain sizes that would not be feasible using traditional direct simulation tools on a desktop computer. We validate our method with a laminar fluid flow case using vuggy samples and fractures. As a result of viewing the entire domain at once, our model is able to perform accurate prediction on domains exhibiting a large degree of heterogeneity. We expect the methodology to be applicable to many other transport problems where complex geometries play a central role.

Predicting the spatial configuration of gas molecules in nanopores of shale formations is crucial for fluid flow forecasting and hydrocarbon reserves estimation. The key challenge in these tight formations is that the majority of the pore sizes are less than 50 nm. At this scale, the fluid properties are affected by nanoconfinement effects due to the increased fluid-solid interactions. For instance, gas adsorption to the pore walls could account for up to 85% of the total hydrocarbon volume in a tight reservoir. Although there are analytical solutions that describe this phenomenon for simple geometries, they are not suitable for describing realistic pores, where surface roughness and geometric anisotropy play important roles. To describe these, molecular dynamics (MD) simulations are used since they consider fluid-solid and fluid-fluid interactions at the molecular level. However, MD simulations are computationally expensive, and are not able to simulate scales larger than a few connected nanopores. Alternatively, mesoscale simulation methods that handle larger domains with complex pore geometries (i.e. the lattice-Boltzmann method) cannot directly account for nanoconfinement effects, resulting in grossly inaccurate predictions. To incorporate these effects into larger domains with complex geometries, it is necessary to accelerate the computation. We present a method for building and training physics-based deep learning surrogate models to carry out fast and accurate predictions of molecular configurations of gas inside nanopores. Since training deep learning models requires extensive databases that are computationally expensive to create, we employ active learning (AL). AL reduces the overhead of creating comprehensive sets of high-fidelity data by determining where the model uncertainty is greatest, and running simulations on the fly to minimize it. The proposed workflow enables nanoconfinement effects to be rigorously considered at the mesoscale where complex connected sets of nanopores control key applications such as hydrocarbon recovery and CO2 sequestration.

Cardiac fibrosis is a pathological process characterized by excessive tissue deposition, matrix remodeling, and tissue stiffening, which eventually leads to organ failure. On a cellular level, the development of fibrosis is associated with the activation of cardiac fibroblasts into myofibroblasts, a highly contractile and secretory phenotype. Myofibroblasts are commonly identified in vitro by the de novo assembly of alpha-smooth muscle actin stress fibers; however, there are few methods to automate stress fiber identification, which can lead to subjectivity and tedium in the process. To address this limitation, we present a computer vision model to classify and segment cells containing alpha-smooth muscle actin stress fibers into 2 classes (α-SMA SF+ and α-SMA SF-), with a high degree of accuracy (cell accuracy: 77%, F1 score 0.79). The model combines standard image processing methods with deep learning techniques to achieve semantic segmentation of the different cell phenotypes. We apply this model to cardiac fibroblasts cultured on hyaluronic acid-based hydrogels of various moduli to induce alpha-smooth muscle actin stress fiber formation. The model successfully predicts the same trends in stress fiber identification as obtained with a manual analysis. Taken together, this work demonstrates a process to automate stress fiber identification in in vitro fibrotic models, thereby increasing reproducibility in fibroblast phenotypic characterization.

No abstract