A comprehensive review of deep learning applications in hydrology and water resources
The global volume of digital data is expected to reach 175 zettabytes by 2025. The volume,
variety and velocity of water-related data are increasing due to large-scale sensor networks …
variety and velocity of water-related data are increasing due to large-scale sensor networks …
Deep learning in pore scale imaging and modeling
Pore-scale imaging and modeling has advanced greatly through the integration of Deep
Learning into the workflow, from image processing to simulating physical processes. In …
Learning into the workflow, from image processing to simulating physical processes. In …
Pore-scale simulation of multiphase flow and reactive transport processes involved in geologic carbon sequestration
Multiphase flow and reactive transport are two essential physicochemical processes that
govern the effectiveness of geological carbon sequestration (GCS). The interaction and …
govern the effectiveness of geological carbon sequestration (GCS). The interaction and …
Predicting porosity, permeability, and tortuosity of porous media from images by deep learning
KM Graczyk, M Matyka - Scientific reports, 2020 - nature.com
Convolutional neural networks (CNN) are utilized to encode the relation between initial
configurations of obstacles and three fundamental quantities in porous media: porosity (φ) …
configurations of obstacles and three fundamental quantities in porous media: porosity (φ) …
Unconventional hydrocarbon resources: geological statistics, petrophysical characterization, and field development strategies
Hydrocarbons exist in abundant quantity beneath the earth's surface. These hydrocarbons
are generally classified as conventional and unconventional hydrocarbons depending upon …
are generally classified as conventional and unconventional hydrocarbons depending upon …
Development of the Senseiver for efficient field reconstruction from sparse observations
The reconstruction of complex time-evolving fields from sensor observations is a grand
challenge. Frequently, sensors have extremely sparse coverage and low-resource …
challenge. Frequently, sensors have extremely sparse coverage and low-resource …
[HTML][HTML] Deep CNNs as universal predictors of elasticity tensors in homogenization
B Eidel - Computer Methods in Applied Mechanics and …, 2023 - Elsevier
In the present work, 3D convolutional neural networks (CNNs) are trained to link random
heterogeneous, multiphase materials to their elastic macroscale stiffness thus replacing …
heterogeneous, multiphase materials to their elastic macroscale stiffness thus replacing …
Computationally efficient multiscale neural networks applied to fluid flow in complex 3D porous media
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 …
This quantity can be obtained via direct flow simulation, which provides the most accurate …
[HTML][HTML] Predicting permeability from 3D rock images based on CNN with physical information
Permeability is one of the most important properties in subsurface flow problems, which
measures the ability of rocks to transmit fluid. Normally, permeability is determined through …
measures the ability of rocks to transmit fluid. Normally, permeability is determined through …
Materials processing model-driven discovery framework for porous materials using machine learning and genetic algorithm: A focus on optimization of permeability …
T Yasuda, S Ookawara, S Yoshikawa… - Chemical Engineering …, 2023 - Elsevier
This study proposes a material discovery framework for porous materials to identify design
variable recipes and the corresponding material structures that can be utilized to improve …
variable recipes and the corresponding material structures that can be utilized to improve …