An official website of the United States government
Abstract The presence of well‐connected paths is commonly observed in spatially heterogeneous porous formations. Channels consisting of high hydraulic conductivity (K) values strongly affect fate and transport of dissolved species in the subsurface environment. Several studies have established a correlation between connectivity properties of the spatially variableK‐field and solute first arrival times. However, due to limited knowledge of the spatial structure of theK‐field, connectivity metrics are subject to uncertainty. In this work, we utilize the concept of the minimum hydraulic resistance and least resistance path to evaluate the connectivity of aK‐field in a stochastic framework. We employ a fast graph theory‐based algorithm to alleviate the computational burden associated with stochastic computations in order to investigate both the impact of the hydrogeological structural conceptualization and domain dimensionality (2‐D vs. 3‐D) on the uncertainty of the minimum hydraulic resistance. Finally, we propose an iterative data acquisition strategy that can be utilized to identify the least resistance path (which is linked to preferential flow channels) in real sites. A synthetic benchmark test is presented, showing the advantages of the proposed sampling strategy when compared to a regular sampling strategy. By using the iterative data sampling strategy, we were able to reduce first arrival time uncertainty by 47% (when compared to the regular sampling strategy), while maintaining site characterization efforts constant.
more »
« less
This content will become publicly available on June 1, 2026
Deep Learning for Connectivity Identification in Random Subsurface Flows: A Methodological Workflow for Early Solute Arrival Time Quantification
Abstract Identification of preferential flow paths in heterogeneous subsurface environments is key to assess early solute arrival times at environmentally sensitive targets. We propose a novel methodology that leverages the information contained in preferential flow paths to quantify early arrival times and their associated uncertainty. Our methodology is based on a two‐stage approach that combines Convolutional Neural Networks (CNN) and Multi‐Layer Perceptron (MLP) techniques. The CNN is used to identify preferential flow paths, the MLP being employed to map tortuosity of these paths and key geostatistical parameters of conductivities therein onto early arrival times. As such, our approach provides novel insights into the relationship between the geostatistical characterization of conductivities along preferential flow paths and early arrival times. The effectiveness of the approach is exemplified on synthetic two‐dimensional (randomly) heterogeneous hydraulic conductivity fields. In this context, we assess three distinct CNN architectures and two MLP architectures to determine the most effective combination between these to reliably and effectively quantifying preferential flow paths and early arrival times of solutes. The resulting framework is robust and efficient. It enhances our ability to assess early solute arrival times in heterogeneous aquifers and offers valuable insights into connectivity patterns associated with preferential flow paths therein.
more »
« less
- Award ID(s):
- 1654009
- PAR ID:
- 10629345
- Publisher / Repository:
- AGU
- Date Published:
- Journal Name:
- Journal of Geophysical Research: Machine Learning and Computation
- Volume:
- 2
- Issue:
- 2
- ISSN:
- 2993-5210
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Groundwater mixing dynamics play a crucial role in the biogeochemical cycling of shallow wetlands. In this paper, we conducted groundwater simulations to investigate the combined effects of evaporation and local heterogeneity on mixing dynamics in shallow wetland sediments. The results show that evaporation causes groundwater and solutes to upwell from deep sediments to the surface. As the solute reaches the surface, evaporation enhances the accumulation of the solute near the surface, resulting in a higher solute concentration than in deep sediments. Mapping of flow topology reveals that local heterogeneity generates spatially varied mixing patterns mainly along preferential flow pathways. The upwelling of groundwater induced by surface evaporation through heterogeneous sediments is likely to create distinct mixing hotspots that differ spatially from those generated by lateral preferential flows driven by large‐scale hydraulic gradients, which enhances the overall mixing in the subsurface. These findings have strong implications for biogeochemical processing in wetlands.more » « less
-
This study provides a kinematic explanation for why facies interfaces dominate solute transport in heterogeneous aquifers. Using flow and transport simulations, we apply kinematic metrics to quantify deformation processes that control plume evolution. Results show that strong conductivity contrasts generate preferential flow corridors, while transitional zones at facies interfaces act as persistent mixing fronts where stretching and folding intensify mixing. These cross-facies transitions emerge as the primary controls on transport observables such as dispersion and dilution, with within-facies variability exerting secondary effects. By linking sedimentary architecture to flow deformation, this work provides the mechanistic justification for earlier findings that cross-transition probabilities govern solute spreading. The results highlight the need to resolve geologic interfaces in both field characterization and remediation design. Flow topology offers a unifying framework for predicting transport in aquifers and points to opportunities for geophysical methods to target the key architectural features that regulate mixing and dilution.more » « less
-
ABSTRACT Microfluidic devices (MDs) present a novel method for detecting circulating tumor cells (CTCs), enhancing the process through targeted techniques and visual inspection. However, current approaches often yield heterogeneous CTC populations, necessitating additional processing for comprehensive analysis and phenotype identification. These procedures are often expensive, time‐consuming, and need to be performed by skilled technicians. In this study, we investigate the potential of a cost‐effective and efficient hyperuniform micropost MD approach for CTC classification. Our approach combines mathematical modeling of fluid–structure interactions in a simulated microfluidic channel with machine learning techniques. Specifically, we developed a cell‐based modeling framework to assess CTC dynamics in erythrocyte‐laden plasma flow, generating a large dataset of CTC trajectories that account for two distinct CTC phenotypes. Convolutional neural network (CNN) and recurrent neural network (RNN) were then employed to analyze the dataset and classify these phenotypes. The results demonstrate the potential effectiveness of the hyperuniform micropost MD design and analysis approach in distinguishing between different CTC phenotypes based on cell trajectory, offering a promising avenue for early cancer detection.more » « less
-
We study the mixing dynamics of solute blobs in the flow through saturated heterogeneous porous media. As the solute plume is advected through a heterogeneous porous medium it suffers a series of deformations that determine its mixing with the ambient fluid through diffusion. Key questions are the relation between the spatial disorder and the mixing dynamics and the effect of the initial solute distribution. To address these questions, we formulate the advection–diffusion problem in a coordinate system that moves and rotates along streamlines of the steady flow field. The impact of the medium heterogeneity is quantified systematically within a stochastic modelling approach. For a simple shear flow, the maximum concentration of a blob decays asymptotically as $$t^{-2}$$ . For heterogeneous porous media, the mixing of the solute blob is determined by the random sampling of flow and deformation heterogeneity along trajectories, a mechanism different from persistent shear. We derive explicit perturbation theory expressions for stretching-enhanced solute mixing that relate the medium structure and mixing behaviour. The solution is valid for moderate heterogeneity. The random sampling of shear along trajectories leads to a $$t^{-3/2}$$ decay of the maximum concentration as opposed to an equivalent homogeneous medium, for which it decays as $$t^{-1}$$ .more » « less
