Hydraulic properties of natural fractures are essential parameters for the modeling fluid flow and transport in subsurface fractured porous media. The cubic law, based on parallel-plate concept, has been traditionally used to estimate hydraulic individual fractures. This upscaling approach, however, is known overestimate properties. Dozens methods have proposed literature improve accuracy law. relative performance these various not well understood. In this work, a comprehensive review...

Geological CO2 sequestration (GCS) has been proposed as an effective approach to mitigate carbon emissions in the atmosphere. Uncertainty and sensitivity analysis of fate dynamics storage are essential aspects large-scale reservoir simulations. This work presents a rigorous machine learning-assisted (ML) workflow for uncertainty global prediction deep saline aquifers. The comprises three main steps: first step concerns dataset generation, which we identify parameters impacting flow transport...

Accurate and efficient localization of CO2 leakage if occurred in subsurface formations, is significant importance achieving secure geological carbon sequestration (GCS) projects. However, this task inherently challenging due to the considerable uncertainties subsurface. In work, we develop a novel deep learning-assisted Bayesian framework for identifying potential sites based on reservoir pressure transient behavior measured at wellbores injection or observation wells. The method consists...

Uncertainties in static and dynamic subsurface parameters are involved geothermal field modeling. The quantification of such uncertainties is important to guide field-development alternatives decision-making. This work presents a novel method for estimating thermal recovery produced-enthalpy rates, combined with uncertainty optimization. We use time-continuous, multi-objective by water re-injection. ranges were determined using database 135 fields. Thermal rates then evaluated as functions...

In this work, we develop a novel streamline (SL) simulation method that integrates seamlessly within the embedded discrete fracture model (EDFM). The SL-based is developed based on hybrid of two-point flux approximation (TPFA) and mimetic finite difference (MFD) methods, which applicable to two-phase anisotropic flow in fractured reservoirs. We refer approach as EDFM-TPFA-MFD-SL. operated an IMplicit Pressure Explicit Saturation (IMPES) manner. First, work establishes EDFM utilizing TPFA-MFD...

Modeling fluid flow in fractured media is of importance many disciplines, including subsurface water management and petroleum reservoir engineering. Detailed geological characterization a commonly described by discrete-fracture model (DFM), which the fractures rock-matrix are explicitly represented unstructured grid elements. Traditional static-based flow-based upscaling methods used to generate equivalent-continuum models from DFM suffer low accuracy high computational cost, respectively....

Summary History matching is a critical process used for calibrating simulation models and assessing subsurface uncertainties. This common technique aims to align the reservoir with observed data. However, achieving this goal often challenging due nonuniqueness of solution, underlying uncertainties, usually high computational cost simulations. The traditional approach based on trial error, which exhaustive labor-intensive. Some analytical numerical proxies combined Monte Carlo simulations are...

Abstract In modeling fractured reservoirs, outcrops may offer useful insights about the subsurface characterization of heterogeneous rock formation. They provide analogs that could be replicated in reservoir to capture fracture and matrix characteristics, which are crucial assess governing recovery mechanisms. Constructing outcrop-based models is a labor-intensive process, subject personal interpretation error. this work, we propose novel workflow for reservoirs within deep learning...

Abstract Geologic CO2 Sequestration (GCS) is a promising engineering technology to reduce global greenhouse emissions. Real-time forecasting of leakage rates an essential aspect large-scale GCS deployment. This work introduces data-driven, physics-featuring surrogate model based on deep-learning technique for rate forecasting. The workflow the development includes three steps: 1) Datasets Generation: We first identify uncertainty parameters that affect objective interests (i.e., rates). For...

Abstract Geological CO2 sequestration (GCS) has been a practical approach used to mitigate global climate change. Uncertainty and sensitivity analysis of storage capacity prediction are essential aspects for large-scale sequestration. This work presents rigorous machine learning-assisted workflow the uncertainty in deep saline aquifers. The proposed comprises three main steps: 1) dataset generation — we first identify parameters that impact aquifers then determine their corresponding ranges...

Current commercial and in-house numerical simulators often employ discrete fracture models (DFM) embedded (EDFM) for flow simulation in fractured reservoirs. However, a generic projection-based model (pEDFM), which outperforms both DFM EDFM any scenario, has not yet been integrated into these simulators. In this paper, we introduce pioneering development of novel approach specifically tailored pEDFM, designed to enhance gas injection energy shale gas-condensate This method is the first its...

Summary Fractured reservoir simulation plays a crucial role in understanding various subsurface geo-energy recovery and storage processes, including shale gas/oil extraction, enhanced geothermal systems, CO2 sequestration basaltic rocks. However, such simulations often entail significant computational expenses due to the high contrast permeability pore volume (PV) between matrix fractures. To address this challenge, we introduce reduced-order model (ROM) tailored for fractured that offers...

Abstract Kolmogorov-Arnold Networks (KANs), introduced in May 2024, present a novel network structure. Early researches show they outperform Multi-Layer Perceptrons (MLPs) computational efficiency, interpretability, and interaction. This paper aims to create the first physics-informed KAN (PIKAN) by replacing MLP with PINN, assessing its performance of solving fractional flow equation waterflooding reservoirs. To build PIKAN, spatial coordinates time serve as inputs, water saturation...

Summary Monitoring carbon dioxide (CO2) saturation plume movement and pressure buildup is critical for ensuring the environmental safety of geological storage (GCS) projects. High-fidelity numerical simulations provide accurate modeling CO2 dynamics, but they are often computationally intensive. Recent advancements in data-driven models have enabled rapid prediction movement. By leveraging available simulation data sets, these offer a more efficient alternative without compromising accuracy....

Abstract Geologic CO2 sequestration (GCS) has been considered a viable engineering measure to decrease global emissions. The real-time monitoring detect possible leakage is an important part of big-scale GCS deployment. In this work, we introduce deep-learning-based algorithm using hybrid neural network for detecting based on bottom-hole pressure measurements. proposed workflow includes the generation train-validation samples, coupling process training-validating, and model evaluation. This...

Abstract Hydraulic fracturing is widely used to stimulate unconventional reservoirs, but a systematic and comprehensive investigation into the hydraulic process insufficient. In this work, discrete element‐lattice Boltzmann method implemented simulate hydro‐mechanical behavior in process. Different influential factors, including treatment parameters (injection rates fluid viscosity), formation (in situ stress states natural fractures) rock properties (heterogeneity of strengths...

Abstract History matching is critical in subsurface flow modeling. It to align the reservoir model with measured data. However, it remains challenging since solution not unique and implementation expensive. The traditional approach relies on trial error, which are exhaustive labor-intensive. In this study, we propose a new workflow utilizing Bayesian Markov Chain Monte Carlo (MCMC) automatically accurately perform history matching. We deliver four novelties within workflow: 1) use of...

Abstract The permeability of fractures, including natural and hydraulic, are essential parameters for the modeling fluid flow in conventional unconventional fractured reservoirs. However, traditional analytical cubic law (CL-based) models used to estimate fracture show unsatisfactory performance when dealing with different dynamic complexities fractures. This work presents a data-driven, physics-included model based on machine learning as an alternative methods. workflow development...

Abstract Due to the scarcity and vulnerability of physical rock samples, digital reconstruction plays an important role in numerical study reservoir properties fluid flow behaviors. With rapid development deep learning technologies, generative adversarial networks (GANs) have become a promising alternative reconstruct complex pore structures. Numerous GAN models been applied this field, but many them suffer unstable training issue. In study, we apply Wasserstin with gradient penalty, also...