arXiv subjects

Ruben Juanes

Publications and source records attributed to Ruben Juanes.

At least 19 recordsLinked to original sources

arXiv2026

Learning and Inferring Multiphase Flow Dynamics in Porous Media using Scientific Machine Learning: Application to the "FluidFlower" CO2 Injection Experiment

Accurate prediction and parameter identification of multiphase flow in porous media remain central challenges in geological carbon dioxide storage due to strong nonlinearities, high-dimensional parameter spaces, and limited observational data. We present a machine learning framework that integrates surrogate modeling and Bayesian inference to enable efficient forward prediction and inverse parameter estimation for CO2-brine flows in geological media. The approach is demonstrated using the "FluidFlower" experimental rig, a controlled laboratory system that provides high-resolution, time-resolved observations of CO2 migration in heterogeneous porous media. A convolutional neural network surrogate is trained on high-fidelity numerical simulations to learn the evolution of CO2 saturation and dissolved CO2 concentration fields over a wide range of multiphase flow properties. The trained surrogate is embedded within a Markov chain Monte Carlo framework for parameter inference conditioned on experimental observations. Results show that the surrogate accurately captures large-scale CO2 plume migration, dissolution dynamics, and multiphase flow behavior while providing orders-of-magnitude acceleration compared to traditional simulations. Embedding the surrogate within a Bayesian framework enables computationally tractable exploration of the parameter space and reveals both identifiable and non-identifiable parameter combinations that produce similar plume behavior. By leveraging spatially and temporally resolved full-field observations, the framework substantially improves agreement between simulations and experiments compared to previous manual calibrations based on limited plume-scale metrics. Analysis using progressively increasing observation horizons further shows that observations become more informative once the plume interacts with geological features such as faults and sealing layers.

physics.geo-ph↗

arXiv2026

Stress state, subsidence, and faulting in the Wilmington Oil Field, California: a multiphase flow-geomechanics modeling assessment (1936-2020)

Nearly a century of oil production in the Wilmington Oil Field, Los Angeles Basin, California, has modified the stress state, caused nearly 9 m of ground surface subsidence, and been associated with earthquakes that sheared wells. This offers a unique opportunity to elucidate the processes that govern these phenomena: Since the 1930s, approximately 2.5 billion barrels of oil have been produced, accompanied by water injection volumes roughly an order of magnitude larger. Combined with extensive structural and geophysical constraints, this history allows us to interrogate the long-term geomechanical impacts of reservoir operations. Here, we assess (i) how the initial stress state, typically uncertain in the shallow crust ($<5$ km depth), influences subsidence and uplift, and (ii) how production and injection operations affect fault stability. Our numerical model, calibrated with published measurements of reservoir pressures and surface displacements, incorporates a detailed representation of fault surfaces within and around the field, well-level production and injection schedules, and an elastoplastic constitutive framework. Model results show that the previously assumed stress regime in the field (reverse faulting) needs to be reassessed$\unicode{x2014}$the best match to the ground deformation data is achieved when the sedimentary section is initialized with low deviatoric stress (i.e., not critically stressed). This suggests significant variation in the stress state with depth, including a likely change in the stress regime. DCFF values suggest minor destabilization on reservoir faults and larger changes on sub-horizontal bedding planes; both could explain the faulting that led to sheared wells and seismicity between 1947 and 1961.

physics.geo-ph↗

arXiv2025

Droplet mobilization in actuated deformable tubes

We study the mobilization of an oil droplet in a deformable, actuated constricted tube subjected to two different actuation mechanisms: hydrodynamic actuation (oscillatory body force in the fluid) and dynamic wall actuation (oscillatory traction on the tube walls). Using high-resolution fluid-structure interaction simulations, we analyze the effects of actuation frequency and amplitude on droplet transport through the constriction. Our simulations show that hydrodynamic actuation leads to a monotonic increase in the droplet's mobilization time with increasing actuation frequency, and a decrease with increasing actuation amplitude. In contrast, dynamic wall actuation exhibits a resonance effect-the mobilization time reaches a minimum at a frequency near the tube's resonant frequency. Our study highlights the potential of actuation mechanisms in deformable tubes for precise control of droplet transport in bio-microfluidic applications.

physics.flu-dyn↗

arXiv2025

Lithological Controls on the Permeability of Geologic Faults: Surrogate Modeling and Sensitivity Analysis

Fault zones exhibit complex and heterogeneous permeability structures influenced by stratigraphic, compositional, and structural factors, making them critical yet uncertain components in subsurface flow modeling. In this study, we investigate how lithological controls influence fault permeability using the PREDICT framework: a probabilistic workflow that couples stochastic fault geometry generation, physically constrained material placement, and flow-based upscaling. The flow-based upscaling step, however, is a very computationally expensive component of the workflow and presents a major bottleneck that makes global sensitivity analysis (GSA) intractable, as it requires millions of model evaluations. To overcome this challenge, we develop a neural network surrogate to emulate the flow-based upscaling step. This surrogate model dramatically reduces the computational cost while maintaining high accuracy, thereby making GSA feasible. The surrogate-model-enabled GSA reveals new insights into the effects of lithological controls on fault permeability. In addition to identifying dominant parameters and negligible ones, the analysis uncovers significant nonlinear interactions between parameters that cannot be captured by traditional local sensitivity methods.

physics.geo-ph↗

arXiv2025

STONet: A neural operator for modeling solute transport in micro-cracked reservoirs

In this work, we introduce a novel neural operator, the Solute Transport Operator Network (STONet), to efficiently model contaminant transport in micro-cracked porous media. STONet's model architecture is specifically designed for this problem and uniquely integrates an enriched DeepONet structure with a transformer-based multi-head attention mechanism, enhancing performance without incurring additional computational overhead compared to existing neural operators. The model combines different networks to encode heterogeneous properties effectively and predict the rate of change of the concentration field to accurately model the transport process. The training data is obtained using finite element (FEM) simulations by random sampling of micro-fracture distributions and applied pressure boundary conditions, which capture diverse scenarios of fracture densities, orientations, apertures, lengths, and balance of pressure-driven to density-driven flow. Our numerical experiments demonstrate that, once trained, STONet achieves accurate predictions, with relative errors typically below 1% compared with FEM simulations while reducing runtime by approximately two orders of magnitude. This type of computational efficiency facilitates building digital twins for rapid assessment of subsurface contamination risks and optimization of environmental remediation strategies. The data and code for the paper will be published at https://github.com/ehsanhaghighat/STONet.

cs.LG↗

arXiv2025

Simulating fluid-fluid displacement in a soft capillary tube: How compliance delays interfacial instability and bubble pinch-off

The displacement of a more viscous fluid by a less viscous immiscible fluid in confined geometries is a fundamental problem in multiphase flows. Recent experiments have shown that such fluid-fluid displacement in micro-capillary tubes can lead to interfacial instabilities and, eventually, bubble pinch-off. A critical yet often overlooked aspect of this system is the effect of the tube's deformability on the onset of interfacial instability and bubble pinch-off. Here, we present a computational fluid-structure interaction model and an algorithm to simulate this fluid-fluid displacement problem in a soft capillary tube. We use a phase-field model for the fluids and a nonlinear hyperelastic model for the solid. Our fluid-structure interaction formulation uses a boundary-fitted approach and we use isogeometric analysis for the spatial discretization. Using this computational framework, we study the effects of inlet capillary number and tube stiffness on the control of interfacial instabilities in a soft capillary tube for both imbibition and drainage. We find that tube compliance delays or even suppresses interfacial instability and bubble pinch-off, a finding that has important implications for flow in soft porous media, bio-microfluidics, and manufacturing processes.

physics.flu-dyn↗

arXiv2024

Uncertainty Quantification of Fluid Leakage and Fault Instability in Geologic CO2 Storage

Geologic CO$_2$ storage is an important strategy for reducing greenhouse gas emissions to the atmosphere and mitigating climate change. In this process, coupling between mechanical deformation and fluid flow in fault zones is a key determinant of fault instability, induced seismicity, and CO$_2$ leakage. Using a recently developed methodology, PREDICT, we obtain probability distributions of the permeability tensor in faults from the stochastic placement of clay smears that accounts for geologic uncertainty. We build a comprehensive set of fault permeability scenarios from PREDICT and investigate the effects of uncertainties from the fault zone internal structure and composition on forecasts of CO$_2$ permanence and fault stability. To tackle the prohibitively expensive computational cost of the large number of simulations required to quantify uncertainty, we develop a deep-learning-based surrogate model capable of predicting flow migration, pressure buildup, and geomechanical responses in CO$_2$ storage operations. We also compare our probabilistic estimation of CO$_2$ leakage and fault instability with previous studies based on deterministic estimates of fault permeability. The results highlight the importance of including uncertainty and anisotropy in modeling of complex fault structures and improved management of geologic CO$_2$ storage projects.

physics.geo-ph↗

arXiv2023

Crossover from viscous fingering to fracturing in cohesive wet granular media: a photoporomechanics study

We study fluid-induced deformation and fracture of cohesive granular media, and apply photoporomechanics to uncover the underpinning grain-scale mechanics. We fabricate photoelastic spherical particles of diameter d=2mm, and make a monolayer granular pack with tunable intergranular cohesion in a circular Hele-Shaw cell that is initially filled with viscous silicone oil. We inject water into the oil-filled photoelastic granular pack, varying the injection flow rate, defending-fluid viscosity, and intergranular cohesion. We find two different modes of fluid invasion: viscous fingering, and fracturing with leak-off of the injection fluid. We directly visualize the evolving effective stress field through the particles' photoelastic response, and discover a hoop effective stress region behind the water invasion front, where we observe tensile force chains in the circumferential direction. Outside the invasion front, we observe compressive force chains aligning in the radial direction. We conceptualize the system's behavior by means of a two-phase poroelastic continuum model. The model captures granular pack dilation and compaction with the boundary delineated by the invasion front, which explains the observed distinct alignments of the force chains. Finally, we rationalize the crossover from viscous fingering to fracturing by comparing the competing forces behind the process: viscous force from fluid injection that drives fractures, and intergranular cohesion and friction that resist fractures.

cond-mat.soft↗

arXiv2023

Soft matter physics of the ground beneath our feet

Inspired by presentations by the authors during a workshop organized at the Princeton Center for Theoretical Science (PCTS) in January 2022, we present a perspective on some of the outstanding questions related to the "physics of the ground beneath our feet." These identified challenges are intrinsically shared with the field of Soft Matter but also have unique aspects when the natural environment is studied.

cond-mat.soft↗

arXiv2023

A Darcy-Cahn-Hilliard model of multiphase fluid-driven fracture

A Darcy-Cahn-Hilliard model coupled with damage is developed to describe multiphase-flow and fluid-driven fracturing in porous media. The model is motivated by recent experimental observations in Hele-Shaw cells of the fluid-driven fracturing of a synthetic porous medium with tunable fracture resistance. The model is derived from continuum thermodynamics and employs several simplifying assumptions, such as linear poroelasticity and viscous-dominated flow. Two distinct phase fields are used to regularize the interface between an invading and a defending fluid, as well as the ensuing damage. The damage model is a cohesive version of a phase-field model for fracture, in which model parameters allow for control over both nucleation and crack growth. Model-based simulations with finite elements are then performed to calibrate the model against recent experimental results. In particular, an experimentally-inferred phase diagram differentiating two flow regimes of porous invasion and fracturing is recovered. Finally, the model is employed to explore the parameter space beyond experimental capabilities, giving rise to the construction of an expanded phase diagram that suggests a new flow regime.

physics.flu-dyn↗

arXiv2023

The FluidFlower International Benchmark Study: Process, Modeling Results, and Comparison to Experimental Data

Successful deployment of geological carbon storage (GCS) requires an extensive use of reservoir simulators for screening, ranking and optimization of storage sites. However, the time scales of GCS are such that no sufficient long-term data is available yet to validate the simulators against. As a consequence, there is currently no solid basis for assessing the quality with which the dynamics of large-scale GCS operations can be forecasted. To meet this knowledge gap, we have conducted a major GCS validation benchmark study. To achieve reasonable time scales, a laboratory-size geological storage formation was constructed (the "FluidFlower"), forming the basis for both the experimental and computational work. A validation experiment consisting of repeated GCS operations was conducted in the FluidFlower, providing what we define as the true physical dynamics for this system. Nine different research groups from around the world provided forecasts, both individually and collaboratively, based on a detailed physical and petrophysical characterization of the FluidFlower sands. The major contribution of this paper is a report and discussion of the results of the validation benchmark study, complemented by a description of the benchmarking process and the participating computational models. The forecasts from the participating groups are compared to each other and to the experimental data by means of various indicative qualitative and quantitative measures. By this, we provide a detailed assessment of the capabilities of reservoir simulators and their users to capture both the injection and post-injection dynamics of the GCS operations.

physics.geo-ph↗

arXiv2023

Characteristics of fluid-fluid displacement in model mixed-wet porous media: patterns, pressures, and scalings

We study the characteristics of fluid-fluid displacement in simple mixed-wet porous micromodels numerically using a dynamic pore network model. The porous micromodel consists of distinct water-wet and oil-wet regions, whose fractions are systematically varied to yield a variety of displacement patterns over a wide range of capillary numbers. We find that the impact of mixed-wettability is most prominent at low capillary number, and it depends on the complex interplay between wettability fraction and the intrinsic contact angle of the water-wet regions. For example, the fractal dimension of the displacement pattern is a monotonically increasing function of wettability fraction in flow cells with strongly water-wet clusters, but it becomes non-monotonic with respect to wettability fraction in flow cells with weakly water-wet clusters. Additionally, mixed-wettability also manifests itself in the injection-pressure signature, which exhibits fluctuations especially at low wettability fraction. Specifically, preferential filling of water-wet regions leads to reduced effective permeability and higher injection pressure, even at vanishingly small capillary numbers. Finally, we demonstrate that scaling analyses based on a weighted average description of the overall wetting state of the mixed-wet system can effectively capture the variations in observed displacement pattern morphology.

cond-mat.soft↗

arXiv2023

Direct comparison of numerical simulations and experiments of CO$_2$ injection and migration in geologic media: Value of local data and predictability

The accuracy and robustness of numerical models of geologic CO$_2$ sequestration are almost never quantified with respect to direct observations that provide a ground truth. Here, we conduct CO$_2$ injection experiments in meter-scale, quasi-2D tanks with porous media representing stratigraphic sections of the subsurface, and combine them with numerical simulations of those experiments. We evaluate (1) the value of prior knowledge of the system, expressed in terms of ex-situ measurements of the tank sands' multiphase flow properties (local data), to obtain an accurate simulation; and (2) the predictive capability of the matched numerical models, when applied to different settings. We match three different simulation models-each with access to an increasing level of local data-to a CO$_2$ injection experiment in tank 1 (89.7$\times$47$\times$1.05 cm). Matching is based on a quantitative comparison of CO$_2$ migration at different times from timelapse image analysis. Next, we simulate a different injection scenario in tank 1, and, finally, a different injection scenario in tank 2 (2.86$\times$1.3$\times$0.019 m), which represents an altogether different stratigraphic section. Our models can qualitatively match the CO$_2$ plume migration and convective mixing of the experimental truth. Quantitatively, simulations are accurate during the injection phase but their performance decreases with time. Using local data reduces the time required to history match. The predictive capability of matched models, however, is found to be similar. The sand-water-CO$_{2(\mathrm{g})}$ system is very sensitive to effective permeability and capillary pressure changes; where heterogeneous structures are present, accurate deterministic estimates of CO$_2$ migration are unlikely.

physics.flu-dyn↗

arXiv2023

Physical variability in meter-scale laboratory CO$_2$ injections in faulted geometries

Carbon, capture, and storage (CCS) is an important bridging technology to combat climate change in the transition towards net-zero. The FluidFlower concept has been developed to visualize and study CO$_2$ flow and storage mechanisms in sedimentary systems in a laboratory setting. Meter-scale multiphase flow in two geological geometries, including normal faults with and without smearing, is studied. The experimental protocols developed to provide key input parameters for numerical simulations are detailed, including an evaluation of operational parameters for the FluidFlower benchmark study. Variability in CO$_2$ migration patterns for two different geometries is quantified, both between 16 repeated laboratory runs and between history-matched models and a CO$_2$ injection experiment. The predicative capability of a history-matched model is then evaluated in a different geological setting.

physics.geo-ph↗

arXiv2022

Inverse modeling of nonisothermal multiphase poromechanics using physics-informed neural networks

We propose a solution strategy for parameter identification in multiphase thermo-hydro-mechanical (THM) processes in porous media using physics-informed neural networks (PINNs). We employ a dimensionless form of the THM governing equations that is particularly well suited for the inverse problem, and we leverage the sequential multiphysics PINN solver we developed in previous work. We validate the proposed inverse-modeling approach on multiple benchmark problems, including Terzaghi's isothermal consolidation problem, Barry-Mercer's isothermal injection-production problem, and nonisothermal consolidation of an unsaturated soil layer. We report the excellent performance of the proposed sequential PINN-THM inverse solver, thus paving the way for the application of PINNs to inverse modeling of complex nonlinear multiphysics problems.

cs.LG↗

arXiv2022

Fluid-fluid displacement in mixed-wet porous media

It is well-known that wettability exerts fundamental control over multiphase flow in porous media, which has been extensively studied in uniform-wet porous media. In contrast, multiphase flow in porous media with heterogeneous wettability (i.e., mixed-wet) is less well-understood, despite its common occurrence. Here, we study the displacement of silicone oil by water in a mostly oil-wet porous media patterned with discrete water-wet clusters that have precisely controlled wettability. Surprisingly, the macroscopic displacement pattern varies dramatically depending on the details of wettability alteration -- the invading water preferentially fills strongly water-wet clusters but encircles weakly water-wet clusters instead, resulting in significant trapping of the defending oil. We explain this counter-intuitive observation with pore-scale simulations, which reveal that the fluid-fluid interfaces at mixed-wet pores resemble an S-shaped saddle with mean curvatures close to zero. We show that incorporation of the capillary entry pressures at mixed-wet pores into a dynamic pore-network model reproduces the experiments. Our work demonstrates the complex nature of wettability control in mixed-wet porous media, and it presents experimental and numerical platforms upon which further insights can be drawn.

cond-mat.soft↗

arXiv2022

Physics-informed neural network solution of thermo-hydro-mechanical (THM) processes in porous media

Physics-Informed Neural Networks (PINNs) have received increased interest for forward, inverse, and surrogate modeling of problems described by partial differential equations (PDE). However, their application to multiphysics problem, governed by several coupled PDEs, present unique challenges that have hindered the robustness and widespread applicability of this approach. Here we investigate the application of PINNs to the forward solution of problems involving thermo-hydro-mechanical (THM) processes in porous media, which exhibit disparate spatial and temporal scales in thermal conductivity, hydraulic permeability, and elasticity. In addition, PINNs are faced with the challenges of the multi-objective and non-convex nature of the optimization problem. To address these fundamental issues, we: (1)~rewrite the THM governing equations in dimensionless form that is best suited for deep-learning algorithms; (2)~propose a sequential training strategy that circumvents the need for a simultaneous solution of the multiphysics problem and facilitates the task of optimizers in the solution search; and (3)~leverage adaptive weight strategies to overcome the stiffness in the gradient flow of the multi-objective optimization problem. Finally, we apply this framework to the solution of several synthetic problems in 1D and~2D.

cs.LG↗

arXiv2021

Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training

Physics-informed neural networks (PINNs) have received significant attention as a unified framework for forward, inverse, and surrogate modeling of problems governed by partial differential equations (PDEs). Training PINNs for forward problems, however, pose significant challenges, mainly because of the complex non-convex and multi-objective loss function. In this work, we present a PINN approach to solving the equations of coupled flow and deformation in porous media for both single-phase and multiphase flow. To this end, we construct the solution space using multi-layer neural networks. Due to the dynamics of the problem, we find that incorporating multiple differential relations into the loss function results in an unstable optimization problem, meaning that sometimes it converges to the trivial null solution, other times it moves very far from the expected solution. We report a dimensionless form of the coupled governing equations that we find most favourable to the optimizer. Additionally, we propose a sequential training approach based on the stress-split algorithms of poromechanics. Notably, we find that sequential training based on stress-split performs well for different problems, while the classical strain-split algorithm shows an unstable behaviour similar to what is reported in the context of finite element solvers. We use the approach to solve benchmark problems of poroelasticity, including Mandel's consolidation problem, Barry-Mercer's injection-production problem, and a reference two-phase drainage problem. The Python-SciANN codes reproducing the results reported in this manuscript will be made publicly available at https://github.com/sciann/sciann-applications.

cs.LG↗